necito
workbenchstudio

Marketplace

1742 handles
HandlesWorkflows
Top this week
A
@anthropic/claude-haiku-4-5-20251001T1
General

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.94
P50
562
ms
Uptime
99.70%
A
@anthropic/claude-opus-4-1-20250805T1
General

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.95
P50
300
ms
Uptime
99.77%
A
@anthropic/claude-opus-4-5-20251101T1
General

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.88
P50
202
ms
Uptime
99.96%
A
@anthropic/claude-opus-4-6T1
General

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.87
P50
480
ms
Uptime
99.97%
A
@anthropic/claude-opus-4-7T1
General

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.83
P50
568
ms
Uptime
99.85%
A
@anthropic/claude-opus-4-8T1
General

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.94
P50
186
ms
Uptime
99.90%
A
@anthropic/claude-sonnet-4-5-20250929T1
General

Price
0.000
cr/req
Uses
18
lifetime
Rep
0.83
P50
559
ms
Uptime
99.73%
A
@anthropic/claude-sonnet-4-6T1
General

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.98
P50
124
ms
Uptime
99.88%
A
@anthropic/claude-sonnet-5T1
General

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.93
P50
355
ms
Uptime
99.74%
F
@fal/ace-stepT1
General

Generate music with lyrics from text using ACE-Step

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.85
P50
437
ms
Uptime
99.73%
F
@fal/ace-step-audio-inpaintT1
General

Modify a portion of provided audio with lyrics and/or style using ACE-Step

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.88
P50
450
ms
Uptime
99.79%
F
@fal/ace-step-audio-outpaintT1
General

Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.95
P50
398
ms
Uptime
99.74%
F
@fal/ace-step-audio-to-audioT1
General

Generate music from a lyrics and example audio using ACE-Step

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.83
P50
378
ms
Uptime
99.93%
F
@fal/ace-step-prompt-to-audioT1
General

Generate music from a simple prompt using ACE-Step

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.92
P50
203
ms
Uptime
99.98%
F
@fal/ai-avatar-multiT1
General

MultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.90
P50
321
ms
Uptime
99.72%
F
@fal/ai-avatar-multi-textT1
General

MultiTalk model generates a multi-person conversation video from an image and text inputs. Converts text to speech for each person, generating a realistic conversation scene.

Price
0.000
cr/req
Uses
216
est.
Rep
0.92
P50
503
ms
Uptime
99.73%
F
@fal/ai-avatar-single-textT1
General

MultiTalk model generates a talking avatar video from an image and text. Converts text to speech automatically, then generates the avatar speaking with lip-sync.

Price
0.000
cr/req
Uses
3
lifetime
Rep
0.89
P50
362
ms
Uptime
99.97%
F
@fal/alibaba-happy-horse-image-to-videoT1
General

Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.85
P50
513
ms
Uptime
99.91%
F
@fal/alibaba-happy-horse-reference-to-videoT1
General

Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.85
P50
487
ms
Uptime
99.70%
F
@fal/alibaba-happy-horse-text-to-videoT1
General

Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.82
P50
605
ms
Uptime
99.81%
F
@fal/alibaba-happy-horse-v1-1-image-to-videoT1
General

Happy Horse 1.1 is Alibaba's #1-ranked video model. This image-to-video endpoint animates a still image into 1080p video with synchronized native audio and multilingual lip-sync

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.95
P50
305
ms
Uptime
99.80%
F
@fal/alibaba-happy-horse-v1-1-reference-to-videoT1
General

Happy Horse 1.1 is Alibaba's #1-ranked video model. This reference-to-video endpoint turns up to 9 reference images into 1080p video with synchronized native audio and multilingual lip-sync for consistent characters.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.89
P50
244
ms
Uptime
99.84%
F
@fal/alibaba-happy-horse-v1-1-text-to-videoT1
General

Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.98
P50
340
ms
Uptime
99.87%
F
@fal/alibaba-happy-horse-video-editT1
General

HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.88
P50
585
ms
Uptime
99.94%
F
@fal/amt-interpolationT1
General

Interpolate between video frames

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.86
P50
210
ms
Uptime
99.86%
F
@fal/amt-interpolation-frame-interpolationT1
General

Interpolate between image frames

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.88
P50
531
ms
Uptime
99.93%
F
@fal/argil-avatars-audio-to-videoT1
General

High-quality avatar videos that feel real, generated from your audio

Price
0.000
cr/req
Uses
118
est.
Rep
0.92
P50
367
ms
Uptime
99.86%
F
@fal/argil-avatars-text-to-videoT1
General

High-quality avatar videos that feel real, generated from your text

Price
0.000
cr/req
Uses
1
lifetime
Rep
0.90
P50
654
ms
Uptime
99.98%
F
@fal/async-tts-pro-v1-0T1
General

Generate professional-quality voiceovers in seconds with Async TTS Pro model text-based control over pauses, emphasis, and timing. Voice ids can be found at https://async.com/developer/voice-library

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.84
P50
487
ms
Uptime
99.89%
F
@fal/audio-understandingT1
General

A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.89
P50
273
ms
Uptime
99.77%
F
@fal/aura-flowT1
General

AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.94
P50
187
ms
Uptime
99.86%
F
@fal/aura-srT1
General

Upscale your images with AuraSR.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.86
P50
281
ms
Uptime
99.84%
F
@fal/auto-captionT1
General

Automatically generates text captions for your videos from the audio as per text colour/font specifications

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.86
P50
543
ms
Uptime
99.77%
F
@fal/bagelT1
General

Bagel is a 7B parameter from Bytedance-Seed multimodal model that can generate both text and images.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.86
P50
459
ms
Uptime
99.75%
F
@fal/bagel-editT1
General

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both images and text.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.85
P50
125
ms
Uptime
99.79%
F
@fal/bagel-understandT1
General

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.86
P50
598
ms
Uptime
99.88%
F
@fal/ben-v2-imageT1
General

A fast and high quality model for image background removal.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.94
P50
334
ms
Uptime
99.91%
F
@fal/ben-v2-videoT1
General

A model for high quality and smooth background removal for videos.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.86
P50
206
ms
Uptime
99.87%
F
@fal/bernini-r-edit-imageT1
General

Edit any image with a natural-language instruction using Bernini-R, changing the weather, materials, objects, or style while preserving the original composition.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.86
P50
213
ms
Uptime
99.80%
F
@fal/bernini-r-edit-videoT1
General

Edit any video with a natural-language instruction using Bernini-R, changing objects, weather, background, or camera angle while keeping the rest of the scene intact.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.86
P50
568
ms
Uptime
99.81%
F
@fal/bernini-r-reference-edit-videoT1
General

Edit a video guided by reference images with Bernini-R, bringing an object, material, background, style, or weather from a reference image into your video.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.96
P50
377
ms
Uptime
99.82%
F
@fal/bernini-r-reference-to-videoT1
General

Turn up to five reference images into one continuous, consistent video with Bernini-R, with smooth, stable camera motion and no scene cuts.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.96
P50
558
ms
Uptime
99.88%
F
@fal/bernini-r-text-to-videoT1
General

Generate high-quality video from a text prompt with Bernini-R, ByteDance's unified video generation and editing model.

Price
0.000
cr/req
Uses
723
est.
Rep
0.84
P50
622
ms
Uptime
99.84%
F
@fal/birefnetT1
General

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.86
P50
387
ms
Uptime
99.86%
F
@fal/birefnet-v2T1
General

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.91
P50
156
ms
Uptime
99.95%
F
@fal/birefnet-v2-videoT1
General

Video background removal version of bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.86
P50
522
ms
Uptime
99.87%
F
@fal/bitdanceT1
General

Image generation with BitDance. Fast, high-resolution photorealistic images using an autoregressive LLM— for efficient, high-quality results.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.84
P50
238
ms
Uptime
99.77%
F
@fal/boogu-imageT1
General

Text To Image Model using Boogu-Image

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.93
P50
533
ms
Uptime
99.90%
F
@fal/boogu-image-editT1
General

Image To Image Model using Boogu-Image

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.86
P50
450
ms
Uptime
99.77%
F
@fal/bria-background-removeT1
General

Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.97
P50
356
ms
Uptime
99.87%
F
@fal/bria-background-replaceT1
General

Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.87
P50
282
ms
Uptime
99.79%
F
@fal/bria-bria-video-eraser-erase-keypointsT1
General

A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.86
P50
180
ms
Uptime
99.76%
F
@fal/bria-bria-video-eraser-erase-maskT1
General

A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.94
P50
532
ms
Uptime
99.74%
F
@fal/bria-bria-video-eraser-erase-promptT1
General

A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.93
P50
634
ms
Uptime
99.71%
F
@fal/bria-embed-productT1
General

Seamlessly embed products into any scene with pixel-perfect control, automatic perspective, and natural lighting. Trained on licensed data - risk-free for advertising and eCommerce production.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.82
P50
340
ms
Uptime
99.86%
F
@fal/bria-eraserT1
General

Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.96
P50
149
ms
Uptime
99.81%
F
@fal/bria-expandT1
General

Bria Expand expands images beyond their borders in high quality. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.92
P50
603
ms
Uptime
99.91%
F
@fal/bria-extract-objectT1
General

Bria Extract Object uses text prompts to isolate a selected object from an image and return it as an RGBA PNG with a transparent background. Ideal for product, ecommerce, advertising, and creative editing workflows. Bria's Extract Object API leads in product shot extraction, outperforming SAM 3.1 where it counts most for commercial use.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.84
P50
432
ms
Uptime
99.95%
F
@fal/bria-fibo-bbq-preview-generateT1
General

A preview to the next level of control of Text-to-Image models.

Price
0.000
cr/req
Uses
118
est.
Rep
0.97
P50
601
ms
Uptime
99.84%
F
@fal/bria-fibo-edit-add-object-by-textT1
General

Precisely insert new objects into images with structured spatial commands. Context-aware, high-quality editing with seamless blending. Trained on licensed data for risk-free commercial and brand-safe use.

Price
0.000
cr/req
Uses
548
est.
Rep
0.86
P50
185
ms
Uptime
99.78%
F
@fal/bria-fibo-edit-blendT1
General

image composition model. Combine and blend multiple image parts into complex compositions through natural language and sequential editing.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.91
P50
236
ms
Uptime
99.79%
F
@fal/bria-fibo-edit-colorizeT1
General

Image colorization and color-grading model. Bring color to black-and-white photos or apply curated color treatments using simple style-based commands.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.83
P50
416
ms
Uptime
99.99%
F
@fal/bria-fibo-edit-editT1
General

High-fidelity image editing model with state-of-the-art controllability. Combines JSON + Mask + Image for precise, fine-grained edits ideal for production and enterprise workflows. Trained on licensed data - safe for commercial use.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.91
P50
384
ms
Uptime
99.92%
F
@fal/bria-fibo-edit-edit-structured-instructionT1
General

Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.86
P50
315
ms
Uptime
99.90%
F
@fal/bria-fibo-edit-erase-by-textT1
General

Remove unwanted objects from images with a text prompt - fast, precise editing that seamlessly blends results. Built for production scale and trained on licensed data for safe commercial use.

Price
0.000
cr/req
Uses
343
est.
Rep
0.93
P50
161
ms
Uptime
99.70%
F
@fal/bria-fibo-edit-relightT1
General

Precise, controllable photo re-lighting with structured text inputs. Apply natural lighting styles, soften harsh shadows, and transform scene illumination - production-ready and trained exclusively on licensed data.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.86
P50
172
ms
Uptime
99.92%
F
@fal/bria-fibo-edit-replace-object-by-textT1
General

Replace any object in an image using plain language with fine-grained, precise edits and strong prompt adherence. Trained on licensed data for risk-free commercial and brand-safe use.

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.97
P50
301
ms
Uptime
99.72%
F
@fal/bria-fibo-edit-reseasonT1
General

Transform the season or weather of an image - summer to winter, sunny to rainy - with realistic atmosphere and lighting. Trained exclusively on licensed data for risk-free commercial use.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.97
P50
622
ms
Uptime
99.72%
F
@fal/bria-fibo-edit-restoreT1
General

Photo restoration model that automatically denoises, deblurs, and enhances old or damaged photos - removes imperfections while preserving original character.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.86
P50
369
ms
Uptime
99.96%
F
@fal/bria-fibo-edit-restyleT1
General

Production-grade style transfer that maps photos to distinct artistic styles using curated, brand-safe presets. Trained exclusively on licensed data for risk-free commercial use.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.90
P50
388
ms
Uptime
99.97%
F
@fal/bria-fibo-edit-rewrite-textT1
General

Precisely rewrite text inside images while preserving typography, fonts, and layout. High-quality, brand-safe edits trained exclusively on licensed data for safe commercial use.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.85
P50
593
ms
Uptime
99.87%
F
@fal/bria-fibo-edit-sketch-to-colored-imageT1
General

Convert line drawings and sketches into photorealistic, fully colored images with preserved structure. Trained exclusively on licensed data for safe commercial and design use.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.90
P50
570
ms
Uptime
99.81%
F
@fal/bria-fibo-generateT1
General

SOTA open-source text-to-image model delivering high-fidelity outputs with accurate typography. JSON-structured prompts provide production-ready controllability for enterprise and agentic workflows. Trained exclusively on licensed data.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.97
P50
651
ms
Uptime
99.74%
F
@fal/bria-fibo-generate-structured-promptT1
General

Structured Prompt Generation endpoint for Fibo, Bria's SOTA Open source model.

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.85
P50
573
ms
Uptime
99.86%
F
@fal/bria-fibo-lite-generateT1
General

Fast, low-latency text-to-image model with high-quality output and full JSON-structured controllability. Open-source, trained on licensed data, and optimized for production-scale generation.

Price
0.000
cr/req
Uses
6
lifetime
Rep
0.89
P50
485
ms
Uptime
99.89%
F
@fal/bria-fibo-lite-generate-structured-promptT1
General

Convert plain text into Fibo-Lite's transparent JSON-structured prompts - Bria's unique controllability layer that no closed model offers. Built for agentic and enterprise workflows.

Price
0.000
cr/req
Uses
69
est.
Rep
0.85
P50
290
ms
Uptime
99.75%
F
@fal/bria-genfillT1
General

Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.92
P50
287
ms
Uptime
99.78%
F
@fal/bria-genfill-v2T1
General

The GenFill Route enables the generation of objects by prompt in a specific region of an image. You can define the area for object generation by using a mask that outlines the region where the object will be created. Our model is optimized to work seamlessly with blob-shaped masks.

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.89
P50
476
ms
Uptime
99.89%
F
@fal/bria-product-dimensionsT1
General

Bria Product Dimensions turns one product photo and its measurements into a marketplace-ready dimension image with callout lines, labels, and weight or capacity readouts

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.95
P50
145
ms
Uptime
99.76%
F
@fal/bria-product-shotT1
General

Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.92
P50
520
ms
Uptime
99.93%
F
@fal/bria-reimagineT1
General

Structure Reference allows generating new images while preserving the structure of an input image, guided by text prompts. Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data for safe and risk-free commercial use.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.95
P50
486
ms
Uptime
99.73%
F
@fal/bria-replace-backgroundT1
General

Generate professional, eCommerce-ready product shots by replacing backgrounds with realistic lighting and accurate perspective from a simple text prompt. Trained exclusively on licensed data for safe commercial use.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.88
P50
602
ms
Uptime
99.84%
F
@fal/bria-text-to-image-baseT1
General

Bria's Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.94
P50
495
ms
Uptime
99.94%
F
@fal/bria-text-to-image-fastT1
General

Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.85
P50
358
ms
Uptime
99.83%
F
@fal/bria-text-to-image-hdT1
General

Bria's Text-to-Image model for HD images. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.98
P50
255
ms
Uptime
99.92%
F
@fal/bria-upscale-creativeT1
General

Professional-grade creative upscaler that doubles resolution up to 10MP, regenerating sharper textures, refined details, and cleaner faces. Trained exclusively on licensed data for risk-free commercial use.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.95
P50
588
ms
Uptime
99.73%
F
@fal/bria-video-background-removalT1
General

Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.95
P50
310
ms
Uptime
99.98%
F
@fal/bria-video-background-removal-realtimeT1
General

Remove video backgrounds in real time with Bria’s VRMBG 3.0 model. Built for live streaming, real-time video apps, content creation, and low-latency workflows that need fast, accurate background removal.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.94
P50
452
ms
Uptime
99.92%
F
@fal/bria-video-background-removal-v3T1
General

Remove backgrounds from any video with Bria's VRMBG 3.0. Fast, accurate background removal across talking heads, podcasts, product videos, commercials, and cinematic footage.

Price
0.000
cr/req
Uses
186
est.
Rep
0.88
P50
215
ms
Uptime
99.97%
F
@fal/bria-video-erase-keypointsT1
General

High-fidelity keypoint-driven video object removal - minimal input, strong temporal consistency. Trained on licensed data for risk-free commercial video editing.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.92
P50
198
ms
Uptime
99.86%
F
@fal/bria-video-erase-maskT1
General

High-fidelity mask-based video object removal with strong temporal consistency. Erase unwanted objects, people, or elements while preserving aesthetic quality. Trained on licensed data for risk-free commercial use.

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.86
P50
501
ms
Uptime
99.74%
F
@fal/bria-video-erase-promptT1
General

Erase unwanted objects, people, or elements from video with a text prompt. High-fidelity output with strong temporal consistency, trained on licensed data for safe commercial use.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.84
P50
348
ms
Uptime
99.97%
F
@fal/bria-video-increase-resolutionT1
General

Professional-grade video upscaler with strong temporal consistency, enhancing videos up to 8K resolution. Trained on fully licensed and commercially safe data - risk-free for production and enterprise use.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.83
P50
238
ms
Uptime
99.98%
F
@fal/bytedance-dreamactor-v2T1
General

Transfer motion from a video to characters in an image using Dreamactor v2. Great performance for non-human and multiple characters

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.89
P50
257
ms
Uptime
99.81%
F
@fal/bytedance-dreamina-v3-1-text-to-imageT1
General

Dreamina showcases superior picture effects, with significant improvements in picture aesthetics, precise and diverse styles, and rich details.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.83
P50
323
ms
Uptime
99.82%
F
@fal/bytedance-lynxT1
General

Generate subject consistent videos using Lynx from ByteDance!

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.87
P50
463
ms
Uptime
99.91%
F
@fal/bytedance-omnihumanT1
General

OmniHuman generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.83
P50
589
ms
Uptime
99.87%
F
@fal/bytedance-omnihuman-v1-5T1
General

Omnihuman v1.5 is a new and improved version of Omnihuman. It generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.88
P50
497
ms
Uptime
99.76%
F
@fal/bytedance-seed-audio-1-0T1
General

Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.85
P50
399
ms
Uptime
99.79%
F
@fal/bytedance-seed-speech-tts-v2T1
General

Seed Speech developed by ByteDance, is a family of large-scale text-to-speech models capable of synthesizing speech that is virtually indistinguishable from human speech.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.84
P50
352
ms
Uptime
99.82%
F
@fal/bytedance-seed-v2-miniT1
General

Seed 2.0 Mini is a high-performance multimodal model optimized for low latency and high concurrency. It supports text, image, and video input with 256K context and configurable thinking/reasoning modes.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.93
P50
608
ms
Uptime
99.91%
F
@fal/bytedance-seedance-2-0-fast-image-to-videoT1
General

ByteDance's most advanced image-to-video model, fast tier. Lower latency and cost with synchronized audio, start and end frame control, and motion prompts.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.93
P50
123
ms
Uptime
99.85%
F
@fal/bytedance-seedance-2-0-fast-reference-to-videoT1
General

ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.86
P50
530
ms
Uptime
99.76%
F
@fal/bytedance-seedance-2-0-fast-text-to-videoT1
General

ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.

Price
0.000
cr/req
Uses
2
lifetime
Rep
0.88
P50
135
ms
Uptime
99.98%
F
@fal/bytedance-seedance-2-0-image-to-videoT1
General

ByteDance's most advanced image-to-video model. Animate still images into cinematic video with synchronized audio, start and end frame control, and motion prompts.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.82
P50
222
ms
Uptime
99.73%
F
@fal/bytedance-seedance-2-0-mini-image-to-videoT1
General

Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.83
P50
276
ms
Uptime
99.82%
F
@fal/bytedance-seedance-2-0-mini-reference-to-videoT1
General

Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.86
P50
479
ms
Uptime
99.73%
F
@fal/bytedance-seedance-2-0-mini-text-to-videoT1
General

Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.98
P50
293
ms
Uptime
99.72%
F
@fal/bytedance-seedance-2-0-reference-to-videoT1
General

ByteDance's most advanced reference-to-video model. Generate video from up to 9 images, 3 videos, and 3 audio clips with native audio and cinematic camera control.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.93
P50
216
ms
Uptime
99.95%
F
@fal/bytedance-seedance-2-0-text-to-videoT1
General

ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-level camera control.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.96
P50
516
ms
Uptime
99.86%
F
@fal/bytedance-seedance-v1-5-pro-image-to-videoT1
General

Generate videos with audio with Seedance 1.5 (supports start & end frame)

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.89
P50
421
ms
Uptime
99.77%
F
@fal/bytedance-seedance-v1-5-pro-text-to-videoT1
General

Generate videos with audio with Seedance 1.5

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.83
P50
525
ms
Uptime
99.99%
F
@fal/bytedance-seedance-v1-pro-fast-image-to-videoT1
General

Image to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.86
P50
125
ms
Uptime
99.92%
F
@fal/bytedance-seedance-v1-pro-fast-text-to-videoT1
General

Text to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.88
P50
409
ms
Uptime
99.86%
F
@fal/bytedance-seedance-v1-pro-image-to-videoT1
General

Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.97
P50
529
ms
Uptime
99.74%
F
@fal/bytedance-seedance-v1-pro-text-to-videoT1
General

Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.89
P50
489
ms
Uptime
99.82%
F
@fal/bytedance-seedream-v4-5-editT1
General

A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.90
P50
574
ms
Uptime
99.92%
F
@fal/bytedance-seedream-v4-5-text-to-imageT1
General

A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.91
P50
569
ms
Uptime
99.85%
F
@fal/bytedance-seedream-v4-editT1
General

A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.83
P50
416
ms
Uptime
99.94%
F
@fal/bytedance-seedream-v4-text-to-imageT1
General

A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.92
P50
549
ms
Uptime
99.71%
F
@fal/bytedance-seedream-v5-pro-editT1
General

Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.95
P50
204
ms
Uptime
99.80%
F
@fal/bytedance-seedream-v5-pro-text-to-imageT1
General

ByteDance's Seedream 5.0 Pro is flagship text-to-image model, with deep-thinking prompt understanding, native text in 14 languages, and precise control over dense layouts and structured designs.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.83
P50
145
ms
Uptime
99.94%
F
@fal/bytedance-upscaler-upscale-videoT1
General

Upscale videos with Bytedance's video upscaler.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.94
P50
149
ms
Uptime
99.81%
F
@fal/cartoonifyT1
General

Transform images into 3D cartoon artwork using an AI model that applies cartoon stylization while preserving the original image's composition and details.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.97
P50
150
ms
Uptime
99.87%
F
@fal/cassetteai-music-generatorT1
General

CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.94
P50
490
ms
Uptime
99.81%
F
@fal/cassetteai-sound-effects-generatorT1
General

Create stunningly realistic sound effects in seconds - CassetteAI's Sound Effects Model generates high-quality SFX up to 30 seconds long in just 1 second of processing time

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.82
P50
424
ms
Uptime
99.71%
F
@fal/cassetteai-video-sound-effects-generatorT1
General

Add sound effects to your videos

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.96
P50
389
ms
Uptime
99.72%
F
@fal/cat-vtonT1
General

Image based high quality Virtual Try-On

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.94
P50
579
ms
Uptime
99.86%
F
@fal/ccsrT1
General

SOTA Image Upscaler

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.91
P50
591
ms
Uptime
99.96%
F
@fal/chatterbox-speech-to-speechT1
General

Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.91
P50
502
ms
Uptime
99.72%
F
@fal/chatterbox-text-to-speechT1
General

Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.

Price
0.000
cr/req
Uses
3
lifetime
Rep
0.93
P50
502
ms
Uptime
99.72%
F
@fal/chatterbox-text-to-speech-multilingualT1
General

Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.90
P50
253
ms
Uptime
99.87%
F
@fal/chrono-editT1
General

NVIDIA's Logically Consistent and Physics-Aware Image Editing Model

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.89
P50
160
ms
Uptime
99.85%
F
@fal/chrono-edit-loraT1
General

LoRA endpoint for the Chrono Edit model.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.83
P50
593
ms
Uptime
99.88%
F
@fal/chrono-edit-lora-gallery-paintbrushT1
General

You can make edits simply by drawing a quick sketch on the input image.

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.87
P50
379
ms
Uptime
99.76%
F
@fal/chrono-edit-lora-gallery-upscalerT1
General

Upscales and cleans up the image.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.85
P50
648
ms
Uptime
99.86%
F
@fal/clarity-upscalerT1
General

Clarity upscaler for upscaling images with high very fidelity.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.83
P50
192
ms
Uptime
99.90%
F
@fal/clarityai-crystal-upscalerT1
General

An advanced image enhancement tool designed specifically for facial details and portrait photography, utilizing Clarity AI's upscaling technology.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.91
P50
473
ms
Uptime
99.92%
F
@fal/clarityai-crystal-video-upscalerT1
General

Do high precision video upscaling that respects the original video perfectly using Crystal Upscaler's new video upscaling method!

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.96
P50
562
ms
Uptime
99.73%
F
@fal/codeformerT1
General

Fix distorted or blurred photos of people with CodeFormer.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.96
P50
600
ms
Uptime
99.82%
F
@fal/cogvideox-5bT1
General

Generate videos from prompts using CogVideoX-5B

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.87
P50
350
ms
Uptime
99.75%
F
@fal/cogvideox-5b-image-to-videoT1
General

Generate videos from images and prompts using CogVideoX-5B

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.94
P50
173
ms
Uptime
99.80%
F
@fal/cogvideox-5b-video-to-videoT1
General

Generate videos from videos and prompts using CogVideoX-5B

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.97
P50
504
ms
Uptime
99.88%
F
@fal/cogview4T1
General

Generate high quality images from text prompts using CogView4. Longer text prompts will result in better quality images.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.83
P50
618
ms
Uptime
99.98%
F
@fal/cohere-transcribeT1
General

Cohere Transcribe turns your business audio into accurate text, ready for search, analytics, and automation

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.90
P50
502
ms
Uptime
99.98%
F
@fal/control-lightT1
General

ControlLight is a LoRA fine-tune of FLUX.2 [klein] 9B that enhances low-light images while preserving scene structure and fine details, with a single alpha parameter that gives continuous control over enhancement strength from subtle to full brightening.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.86
P50
560
ms
Uptime
99.84%
F
@fal/controlfoleyT1
General

Foley Control is a video-to-audio model that automatically generates synchronized sound effects for videos, using text prompts to shape the type of sound while matching the timing and action on screen.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.95
P50
381
ms
Uptime
99.88%
F
@fal/cosmos-predict-2-5-distilled-text-to-videoT1
General

Generate video from text and videos using NVIDIA's 2B Cosmos Distilled Model

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.84
P50
184
ms
Uptime
99.73%
F
@fal/cosmos-predict-2-5-image-to-videoT1
General

Generate video from text and images using NVIDIA's 2B Cosmos Post-Trained Model

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.83
P50
555
ms
Uptime
99.91%
F
@fal/cosmos-predict-2-5-text-to-videoT1
General

Generate video from text using NVIDIA's 2B Cosmos Post-Trained Model

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.90
P50
451
ms
Uptime
99.97%
F
@fal/cosmos-predict-2-5-video-to-videoT1
General

Generate video from text and videos using NVIDIA's 2B Cosmos Post-Trained Model

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.83
P50
281
ms
Uptime
99.89%
F
@fal/creatify-auroraT1
General

Generate high fidelity, studio quality videos of your avatar speaking or singing using the Aurora from Creatify team!

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.93
P50
380
ms
Uptime
99.82%
F
@fal/creative-upscalerT1
General

Create creative upscaled images.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.93
P50
554
ms
Uptime
99.73%
F
@fal/csm-1bT1
General

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.88
P50
126
ms
Uptime
99.80%
F
@fal/davinci-magihumanT1
General

Expressive facial performance, natural speech-expression coordination, realistic body motion, and accurate audio-video synchronization with DaVinci-MagiHuman model

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.84
P50
196
ms
Uptime
99.87%
F
@fal/ddcolorT1
General

Bring colors into old or new black and white photos with DDColor.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.95
P50
288
ms
Uptime
99.91%
F
@fal/decart-lucy-2-5-realtimeT1
General

Real-time, prompt-driven video editing over WebRTC. Restyle, swap backgrounds, and add or replace objects live on a webcam or streamed feed at interactive latency.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.95
P50
643
ms
Uptime
99.72%
F
@fal/decart-lucy-5b-image-to-videoT1
General

Lucy-5B is a model that can create 5-second I2V videos in under 5 seconds, achieving >1x RTF end-to-end

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.97
P50
407
ms
Uptime
99.79%
F
@fal/decart-lucy-edit-proT1
General

Edit outfits, objects, faces, or restyle your video - all with maximum detail retention.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.97
P50
597
ms
Uptime
99.99%
F
@fal/decart-lucy-restyleT1
General

Restyle videos up to 30 min long - maintaining maximum detail quality.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.86
P50
648
ms
Uptime
99.78%
F
@fal/decart-lucy2-vton-realtimeT1
General

Realtime Try On experience with Decart Lucy 2.1 VTON

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.95
P50
377
ms
Uptime
99.72%
F
@fal/deepfilternet3T1
General

Enhance speech audio by removing background noise and upsampling to 48KHz

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.89
P50
193
ms
Uptime
99.75%
F
@fal/demucsT1
General

SOTA stemming model for voice, drums, bass, guitar and more.

Price
0.000
cr/req
Uses
860
est.
Rep
0.92
P50
266
ms
Uptime
99.81%
F
@fal/depth-anything-videoT1
General

Generates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.83
P50
373
ms
Uptime
99.78%
F
@fal/dia-ttsT1
General

Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.95
P50
166
ms
Uptime
99.71%
F
@fal/dia-tts-voice-cloneT1
General

Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.85
P50
180
ms
Uptime
99.78%
F
@fal/diffrhythmT1
General

DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.83
P50
293
ms
Uptime
99.82%
F
@fal/docresT1
General

Enhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.95
P50
292
ms
Uptime
99.96%
F
@fal/docres-dewarpT1
General

Enhance wraped, folded documents with the superior quality of docres for sharper, clearer results.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.91
P50
629
ms
Uptime
99.75%
F
@fal/drct-super-resolutionT1
General

Upscale your images with DRCT-Super-Resolution.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.88
P50
181
ms
Uptime
99.81%
F
@fal/dreamomni2-editT1
General

DreamOmni2 is a unified multimodal model for text and image guided image editing.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.97
P50
525
ms
Uptime
99.95%
F
@fal/dreamshaperT1
General

Dreamshaper model.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.97
P50
145
ms
Uptime
99.83%
F
@fal/dwposeT1
General

Predict poses from images.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.87
P50
236
ms
Uptime
99.78%
F
@fal/dwpose-videoT1
General

Predict poses from videos.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.91
P50
190
ms
Uptime
99.87%
F
@fal/echomimic-v3T1
General

EchoMimic V3 generates a talking avatar model from a picture, audio and text prompt.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.84
P50
357
ms
Uptime
99.97%
F
@fal/edittoT1
General

Edit videos using instruction-based prompting using Editto model!

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.85
P50
142
ms
Uptime
99.92%
F
@fal/elevenlabs-audio-isolationT1
General

Isolate audio tracks using ElevenLabs advanced audio isolation technology.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.90
P50
480
ms
Uptime
99.99%
F
@fal/elevenlabs-dubbingT1
General

Generate dubbed videos or audios using ElevenLabs Dubbing feature!

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.93
P50
283
ms
Uptime
99.84%
F
@fal/elevenlabs-musicT1
General

Generate high quality, realistic music with fine controls using Elevenlabs Music!

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.96
P50
579
ms
Uptime
99.85%
F
@fal/elevenlabs-sound-effects-v2T1
General

Generate sound effects using ElevenLabs advanced sound effects model.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.85
P50
176
ms
Uptime
99.80%
F
@fal/elevenlabs-speech-to-textT1
General

Generate text from speech using ElevenLabs advanced speech-to-text model.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.97
P50
419
ms
Uptime
99.89%
F
@fal/elevenlabs-speech-to-text-scribe-v2T1
General

Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.95
P50
381
ms
Uptime
99.75%
F
@fal/elevenlabs-text-to-dialogue-eleven-v3T1
General

Generate realistic audio dialogues using Eleven-v3 from ElevenLabs.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.92
P50
199
ms
Uptime
99.74%
F
@fal/elevenlabs-tts-eleven-v3T1
General

Generate text-to-speech audio using Eleven-v3 from ElevenLabs.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.89
P50
333
ms
Uptime
99.86%
F
@fal/elevenlabs-tts-multilingual-v2T1
General

Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.96
P50
630
ms
Uptime
99.98%
F
@fal/elevenlabs-tts-turbo-v2-5T1
General

Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.98
P50
415
ms
Uptime
99.84%
F
@fal/elevenlabs-voice-changerT1
General

Change the voices in your audios with voices in ElevenLabs!

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.85
P50
184
ms
Uptime
99.99%
F
@fal/emu-3-5-image-edit-imageT1
General

Edit images with a text prompt using Emu 3.5 Image

Price
0.000
cr/req
Uses
245
est.
Rep
0.96
P50
567
ms
Uptime
99.79%
F
@fal/emu-3-5-image-text-to-imageT1
General

Generate images from text using Emu 3.5 Image

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.95
P50
305
ms
Uptime
99.77%
F
@fal/ernie-imageT1
General

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.86
P50
488
ms
Uptime
99.89%
F
@fal/ernie-image-loraT1
General

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.98
P50
575
ms
Uptime
99.92%
F
@fal/ernie-image-lora-turboT1
General

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.87
P50
513
ms
Uptime
99.72%
F
@fal/ernie-image-trainerT1
General

LoRA trainer for ERNIE-Image, Baidu's powerful 8B-parameter text-to-image model.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.98
P50
517
ms
Uptime
99.99%
F
@fal/ernie-image-turboT1
General

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Price
0.000
cr/req
Uses
245
est.
Rep
0.96
P50
166
ms
Uptime
99.81%
F
@fal/esrganT1
General

Upscale images by a given factor.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.87
P50
395
ms
Uptime
99.76%
F
@fal/evf-samT1
General

EVF-SAM2 combines natural language understanding with advanced segmentation capabilities, allowing you to precisely mask image regions using intuitive positive and negative text prompts.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.89
P50
509
ms
Uptime
99.77%
F
@fal/f5-ttsT1
General

F5 TTS

Price
0.000
cr/req
Uses
372
est.
Rep
0.91
P50
460
ms
Uptime
99.76%
F
@fal/fashn-tryon-v1-5T1
General

FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.88
P50
620
ms
Uptime
99.82%
F
@fal/fashn-tryon-v1-6T1
General

FASHN v1.6 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 864x1296 resolution from both on-model and flat-lay photo references.

Price
0.000
cr/req
Uses
108
est.
Rep
0.85
P50
656
ms
Uptime
99.84%
F
@fal/fast-animatediff-text-to-videoT1
General

Animate your ideas!

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.85
P50
598
ms
Uptime
99.76%
F
@fal/fast-animatediff-turbo-text-to-videoT1
General

Animate your ideas in lightning speed!

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.95
P50
478
ms
Uptime
99.82%
F
@fal/fast-animatediff-turbo-video-to-videoT1
General

Re-animate your videos in lightning speed!

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.96
P50
195
ms
Uptime
99.84%
F
@fal/fast-animatediff-video-to-videoT1
General

Re-animate your videos!

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.92
P50
634
ms
Uptime
99.94%
F
@fal/fast-fooocus-sdxl-image-to-imageT1
General

Fooocus extreme speed mode as a standalone app.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.82
P50
512
ms
Uptime
99.72%
F
@fal/fast-lcm-diffusionT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.97
P50
390
ms
Uptime
99.80%
F
@fal/fast-lcm-diffusion-image-to-imageT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.91
P50
181
ms
Uptime
99.97%
F
@fal/fast-lcm-diffusion-inpaintingT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.93
P50
511
ms
Uptime
99.80%
F
@fal/fast-lightning-sdxlT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
401
est.
Rep
0.84
P50
168
ms
Uptime
99.79%
F
@fal/fast-lightning-sdxl-image-to-imageT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.94
P50
659
ms
Uptime
99.88%
F
@fal/fast-lightning-sdxl-inpaintingT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.84
P50
138
ms
Uptime
99.74%
F
@fal/fast-sdxlT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.94
P50
469
ms
Uptime
99.97%
F
@fal/fast-sdxl-controlnet-cannyT1
General

Generate Images with ControlNet.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.83
P50
290
ms
Uptime
99.77%
F
@fal/fast-sdxl-controlnet-canny-image-to-imageT1
General

Generate Images with ControlNet.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.83
P50
222
ms
Uptime
99.97%
F
@fal/fast-sdxl-controlnet-canny-inpaintingT1
General

Generate Images with ControlNet.

Price
0.000
cr/req
Uses
528
est.
Rep
0.90
P50
287
ms
Uptime
99.76%
F
@fal/fast-sdxl-image-to-imageT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.89
P50
257
ms
Uptime
99.72%
F
@fal/fast-sdxl-inpaintingT1
General

Run SDXL at the speed of light

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.91
P50
574
ms
Uptime
99.83%
F
@fal/fast-svd-lcmT1
General

Generate short video clips from your images using SVD v1.1 at Lightning Speed

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.83
P50
466
ms
Uptime
99.99%
F
@fal/fast-svd-lcm-text-to-videoT1
General

Generate short video clips from your images using SVD v1.1 at Lightning Speed

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.98
P50
589
ms
Uptime
99.89%
F
@fal/fast-svd-text-to-videoT1
General

Generate short video clips from your prompts using SVD v1.1

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.89
P50
316
ms
Uptime
99.95%
F
@fal/ffmpeg-api-composeT1
General

Compose videos from multiple media sources using FFmpeg API.

Price
0.000
cr/req
Uses
2
lifetime
Rep
0.84
P50
168
ms
Uptime
99.81%
F
@fal/ffmpeg-api-extract-frameT1
General

ffmpeg endpoint for first, middle and last frame extraction from videos

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.90
P50
637
ms
Uptime
99.99%
F
@fal/ffmpeg-api-images-to-videoT1
General

A fal.ai endpoint that stitches an ordered list of images into an MP4 video by holding each image for a specified number of frames at a configurable frame rate

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.95
P50
503
ms
Uptime
99.85%
F
@fal/ffmpeg-api-loudnormT1
General

Get EBU R128 loudness normalization from audio files using FFmpeg API.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.87
P50
235
ms
Uptime
99.93%
F
@fal/ffmpeg-api-merge-audio-videoT1
General

Merge videos with standalone audio files or audio from video files.

Price
0.000
cr/req
Uses
1
lifetime
Rep
0.94
P50
524
ms
Uptime
99.73%
F
@fal/ffmpeg-api-merge-audiosT1
General

Merge audios into a single audio using FFmpeg API!

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.92
P50
435
ms
Uptime
99.90%
F
@fal/ffmpeg-api-merge-videosT1
General

Use ffmpeg capabilities to merge 2 or more videos.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.85
P50
188
ms
Uptime
99.82%
F
@fal/ffmpeg-api-metadataT1
General

Get encoding metadata from video and audio files using FFmpeg API.

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.94
P50
385
ms
Uptime
99.80%
F
@fal/ffmpeg-api-waveformT1
General

Get waveform data from audio files using FFmpeg API.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.92
P50
206
ms
Uptime
99.96%
F
@fal/filmT1
General

Interpolate images with FILM - Frame Interpolation for Large Motion

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.84
P50
159
ms
Uptime
99.97%
F
@fal/film-videoT1
General

Interpolate videos with FILM - Frame Interpolation for Large Motion

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.89
P50
223
ms
Uptime
99.97%
F
@fal/finegrain-eraserT1
General

Finegrain Eraser removes objects—along with their shadows, reflections, and lighting artifacts—using only natural language, seamlessly filling the scene with contextually accurate content.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.96
P50
579
ms
Uptime
99.93%
F
@fal/finegrain-eraser-bboxT1
General

Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.88
P50
231
ms
Uptime
99.78%
F
@fal/finegrain-eraser-maskT1
General

Finegrain Eraser removes any object selected with a mask—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.86
P50
509
ms
Uptime
99.87%
F
@fal/firered-image-editT1
General

FireRed Image Edit is FireRed's state of the art open source editing model, re-trained from Qwen Image Edit 2509.

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.82
P50
344
ms
Uptime
99.93%
F
@fal/firered-image-edit-v1-1T1
General

FireRed Image Edit v1.1 is an updated version of FireRed Image Edit, with improved image editing capabilities.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.91
P50
621
ms
Uptime
99.79%
F
@fal/flashheadT1
General

SoulX-FlashHead is a unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.87
P50
527
ms
Uptime
99.89%
F
@fal/flashtalkT1
General

Audio-driven talking avatar generation powered by the SoulX-FlashTalk 14B model.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.97
P50
593
ms
Uptime
99.80%
F
@fal/flashvsr-upscale-videoT1
General

Upscale your videos using FlashVSR with the fastest speeds!

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.84
P50
373
ms
Uptime
99.90%
F
@fal/florence-2-large-captionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.89
P50
346
ms
Uptime
99.75%
F
@fal/florence-2-large-caption-to-phrase-groundingT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.82
P50
648
ms
Uptime
99.74%
F
@fal/florence-2-large-dense-region-captionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.83
P50
369
ms
Uptime
99.72%
F
@fal/florence-2-large-detailed-captionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
879
est.
Rep
0.95
P50
132
ms
Uptime
99.85%
F
@fal/florence-2-large-more-detailed-captionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.89
P50
354
ms
Uptime
99.88%
F
@fal/florence-2-large-object-detectionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
108
est.
Rep
0.86
P50
636
ms
Uptime
99.84%
F
@fal/florence-2-large-ocrT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.90
P50
143
ms
Uptime
99.94%
F
@fal/florence-2-large-ocr-with-regionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.93
P50
330
ms
Uptime
99.78%
F
@fal/florence-2-large-open-vocabulary-detectionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.83
P50
630
ms
Uptime
99.78%
F
@fal/florence-2-large-referring-expression-segmentationT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.90
P50
143
ms
Uptime
99.87%
F
@fal/florence-2-large-region-proposalT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.90
P50
393
ms
Uptime
99.97%
F
@fal/florence-2-large-region-to-categoryT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
499
est.
Rep
0.90
P50
296
ms
Uptime
99.98%
F
@fal/florence-2-large-region-to-descriptionT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.97
P50
305
ms
Uptime
99.90%
F
@fal/florence-2-large-region-to-segmentationT1
General

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.98
P50
158
ms
Uptime
99.90%
F
@fal/floweditT1
General

The model provides you high quality image editing capabilities.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.83
P50
386
ms
Uptime
99.81%
F
@fal/flux-1-devT1
General

FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.92
P50
427
ms
Uptime
99.85%
F
@fal/flux-1-dev-image-to-imageT1
General

FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.83
P50
546
ms
Uptime
99.74%
F
@fal/flux-1-dev-reduxT1
General

FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.95
P50
579
ms
Uptime
99.98%
F
@fal/flux-1-kreaT1
General

FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.92
P50
435
ms
Uptime
99.73%
F
@fal/flux-1-krea-image-to-imageT1
General

FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.90
P50
219
ms
Uptime
99.81%
F
@fal/flux-1-krea-reduxT1
General

FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.89
P50
548
ms
Uptime
99.78%
F
@fal/flux-1-schnellT1
General

Fastest inference in the world for the 12 billion parameter FLUX.1 [schnell] text-to-image model.

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.94
P50
432
ms
Uptime
99.97%
F
@fal/flux-1-schnell-reduxT1
General

FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.95
P50
612
ms
Uptime
99.89%
F
@fal/flux-1-srpoT1
General

FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.96
P50
216
ms
Uptime
99.76%
F
@fal/flux-1-srpo-image-to-imageT1
General

FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.92
P50
198
ms
Uptime
99.79%
F
@fal/flux-2T1
General

Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.91
P50
536
ms
Uptime
99.84%
F
@fal/flux-2-editT1
General

Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.90
P50
636
ms
Uptime
99.73%
F
@fal/flux-2-flashT1
General

Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities— in a flash.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.84
P50
446
ms
Uptime
99.94%
F
@fal/flux-2-flash-editT1
General

Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—in a flash.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.89
P50
497
ms
Uptime
99.89%
F
@fal/flux-2-flexT1
General

Text-to-image generation with FLUX.2 [flex] from Black Forest Labs. Features adjustable inference steps and guidance scale for fine-tuned control. Enhanced typography and text rendering capabilities.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.93
P50
426
ms
Uptime
99.93%
F
@fal/flux-2-flex-editT1
General

Image editing with FLUX.2 [flex] from Black Forest Labs. Supports multi-reference editing with customizable inference steps and enhanced text rendering.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.90
P50
261
ms
Uptime
99.81%
F
@fal/flux-2-klein-4bT1
General

Text-to-image generation with FLUX.2 [klein] 4B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
411
est.
Rep
0.83
P50
479
ms
Uptime
99.82%
F
@fal/flux-2-klein-4b-baseT1
General

Text-to-image generation with FLUX.2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
655
est.
Rep
0.91
P50
633
ms
Uptime
99.71%
F
@fal/flux-2-klein-4b-base-editT1
General

Image-to-image editing with FLUX.2 [klein] 4B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.96
P50
617
ms
Uptime
99.81%
F
@fal/flux-2-klein-4b-base-edit-loraT1
General

Image-to-image editing with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.93
P50
566
ms
Uptime
99.89%
F
@fal/flux-2-klein-4b-base-loraT1
General

Text-to-image generation with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations.

Price
0.000
cr/req
Uses
128
est.
Rep
0.88
P50
256
ms
Uptime
99.88%
F
@fal/flux-2-klein-4b-editT1
General

Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.86
P50
484
ms
Uptime
99.84%
F
@fal/flux-2-klein-4b-edit-loraT1
General

Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.91
P50
215
ms
Uptime
99.82%
F
@fal/flux-2-klein-4b-loraT1
General

Text-to-image generation with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.84
P50
302
ms
Uptime
99.83%
F
@fal/flux-2-klein-9bT1
General

Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.87
P50
159
ms
Uptime
99.86%
F
@fal/flux-2-klein-9b-baseT1
General

Text-to-image generation with FLUX.2 [klein] 9B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.91
P50
274
ms
Uptime
99.76%
F
@fal/flux-2-klein-9b-base-editT1
General

Image-to-image editing with Flux 2 [klein] 9B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.83
P50
176
ms
Uptime
99.79%
F
@fal/flux-2-klein-9b-base-edit-loraT1
General

Image-to-image editing with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.87
P50
395
ms
Uptime
99.73%
F
@fal/flux-2-klein-9b-base-loraT1
General

Text-to-image generation with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.94
P50
414
ms
Uptime
99.78%
F
@fal/flux-2-klein-9b-base-trainerT1
General

Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.83
P50
614
ms
Uptime
99.91%
F
@fal/flux-2-klein-9b-base-trainer-editT1
General

Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.90
P50
363
ms
Uptime
99.73%
F
@fal/flux-2-klein-9b-editT1
General

Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.88
P50
654
ms
Uptime
99.70%
F
@fal/flux-2-klein-9b-edit-loraT1
General

Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.93
P50
250
ms
Uptime
99.91%
F
@fal/flux-2-klein-9b-loraT1
General

Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs and custom LoRA.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.92
P50
342
ms
Uptime
99.90%
F
@fal/flux-2-klein-realtimeT1
General

Realtime generation with FLUX.2 [klein] from Black Forest Labs.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.91
P50
262
ms
Uptime
99.89%
F
@fal/flux-2-loraT1
General

Text-to-image generation with LoRA support for FLUX.2 [dev] from Black Forest Labs. Custom style adaptation and fine-tuned model variations.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.89
P50
608
ms
Uptime
99.84%
F
@fal/flux-2-lora-editT1
General

Image-to-image editing with LoRA support for FLUX.2 [dev] from Black Forest Labs. Specialized style transfer and domain-specific modifications.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.97
P50
179
ms
Uptime
99.90%
F
@fal/flux-2-lora-gallery-add-backgroundT1
General

Add a background to images with white/clean background

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.94
P50
490
ms
Uptime
99.98%
F
@fal/flux-2-lora-gallery-apartment-stagingT1
General

Virtually furnishes an empty apartment

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.83
P50
386
ms
Uptime
99.79%
F
@fal/flux-2-lora-gallery-ballpoint-pen-sketchT1
General

Ballpoint pen sketch drawing style

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.91
P50
566
ms
Uptime
99.91%
F
@fal/flux-2-lora-gallery-digital-comic-artT1
General

Transforms images into comic book style

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.84
P50
631
ms
Uptime
99.89%
F
@fal/flux-2-lora-gallery-face-to-full-portraitT1
General

Extends a face into a full body portrait

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.96
P50
528
ms
Uptime
99.71%
F
@fal/flux-2-lora-gallery-hdr-styleT1
General

HDR surrealistic effect with intense colors

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.87
P50
535
ms
Uptime
99.76%
F
@fal/flux-2-lora-gallery-multiple-anglesT1
General

Generates same object from different angles (azimuth/elevation)

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.92
P50
435
ms
Uptime
99.75%
F
@fal/flux-2-lora-gallery-realismT1
General

Makes images more photorealistic and natural

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.89
P50
480
ms
Uptime
99.77%
F
@fal/flux-2-lora-gallery-satellite-view-styleT1
General

Generates satellite/aerial view style images

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.91
P50
557
ms
Uptime
99.73%
F
@fal/flux-2-lora-gallery-sepia-vintageT1
General

Applies sepia vintage effect to images

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.91
P50
333
ms
Uptime
99.91%
F
@fal/flux-2-lora-gallery-virtual-tryonT1
General

Virtual clothing try-on (2 images: person + garment)

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.97
P50
322
ms
Uptime
99.74%
F
@fal/flux-2-maxT1
General

FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.93
P50
511
ms
Uptime
99.88%
F
@fal/flux-2-max-editT1
General

FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.91
P50
172
ms
Uptime
99.93%
F
@fal/flux-2-proT1
General

Image editing with FLUX.2 [pro] from Black Forest Labs. Ideal for high-quality image manipulation, style transfer, and sequential editing workflows

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.83
P50
589
ms
Uptime
99.97%
F
@fal/flux-2-pro-editT1
General

Text-to-image generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.

Price
0.000
cr/req
Uses
274
est.
Rep
0.98
P50
449
ms
Uptime
99.86%
F
@fal/flux-2-pro-outpaintT1
General

Outpainting generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.84
P50
475
ms
Uptime
99.97%
F
@fal/flux-2-trainerT1
General

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.

Price
0.000
cr/req
Uses
450
est.
Rep
0.83
P50
230
ms
Uptime
99.91%
F
@fal/flux-2-trainer-editT1
General

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.95
P50
431
ms
Uptime
99.84%
F
@fal/flux-2-trainer-v2T1
General

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.90
P50
590
ms
Uptime
99.89%
F
@fal/flux-2-trainer-v2-editT1
General

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.97
P50
533
ms
Uptime
99.73%
F
@fal/flux-2-turboT1
General

Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities—all at turbo speed.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.84
P50
273
ms
Uptime
99.98%
F
@fal/flux-2-turbo-editT1
General

Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—all at turbo speed.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.98
P50
495
ms
Uptime
99.87%
F
@fal/flux-control-lora-cannyT1
General

FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.97
P50
204
ms
Uptime
99.86%
F
@fal/flux-control-lora-canny-image-to-imageT1
General

FLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.93
P50
398
ms
Uptime
99.78%
F
@fal/flux-control-lora-depthT1
General

FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.89
P50
455
ms
Uptime
99.95%
F
@fal/flux-control-lora-depth-image-to-imageT1
General

FLUX Control LoRA Depth is a high-performance endpoint that uses a control image using a depth map to transfer structure to the generated image and another initial image to guide color.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.88
P50
185
ms
Uptime
99.82%
F
@fal/flux-devT1
General

FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.86
P50
521
ms
Uptime
99.99%
F
@fal/flux-dev-image-to-imageT1
General

FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.97
P50
445
ms
Uptime
99.76%
F
@fal/flux-dev-reduxT1
General

FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.84
P50
142
ms
Uptime
99.83%
F
@fal/flux-generalT1
General

A versatile endpoint for the FLUX.1 [dev] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.92
P50
299
ms
Uptime
99.89%
F
@fal/flux-general-differential-diffusionT1
General

A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.88
P50
223
ms
Uptime
99.76%
F
@fal/flux-general-image-to-imageT1
General

FLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.97
P50
132
ms
Uptime
99.89%
F
@fal/flux-general-inpaintingT1
General

FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.96
P50
293
ms
Uptime
99.72%
F
@fal/flux-general-rf-inversionT1
General

A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.83
P50
433
ms
Uptime
99.80%
F
@fal/flux-kontext-devT1
General

Frontier image editing model.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.93
P50
473
ms
Uptime
99.78%
F
@fal/flux-kontext-loraT1
General

Fast endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image editing using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.96
P50
220
ms
Uptime
99.99%
F
@fal/flux-kontext-lora-inpaintT1
General

Fast inpainting endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image inpainting with reference images, while using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
69
est.
Rep
0.84
P50
458
ms
Uptime
99.76%
F
@fal/flux-kontext-lora-text-to-imageT1
General

Super fast text-to-image endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.84
P50
572
ms
Uptime
99.78%
F
@fal/flux-kontext-trainerT1
General

LoRA trainer for FLUX.1 Kontext [dev]

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.84
P50
231
ms
Uptime
99.87%
F
@fal/flux-kreaT1
General

FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.94
P50
313
ms
Uptime
99.88%
F
@fal/flux-krea-image-to-imageT1
General

FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.90
P50
165
ms
Uptime
99.75%
F
@fal/flux-krea-loraT1
General

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.88
P50
421
ms
Uptime
99.75%
F
@fal/flux-krea-lora-image-to-imageT1
General

FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.89
P50
641
ms
Uptime
99.97%
F
@fal/flux-krea-lora-inpaintingT1
General

Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.89
P50
211
ms
Uptime
99.97%
F
@fal/flux-krea-lora-streamT1
General

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.83
P50
445
ms
Uptime
99.95%
F
@fal/flux-krea-reduxT1
General

FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.86
P50
285
ms
Uptime
99.81%
F
@fal/flux-loraT1
General

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.93
P50
186
ms
Uptime
99.74%
F
@fal/flux-lora-cannyT1
General

Utilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.90
P50
316
ms
Uptime
99.81%
F
@fal/flux-lora-depthT1
General

Generate high-quality images from depth maps using Flux.1 [dev] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.94
P50
250
ms
Uptime
99.78%
F
@fal/flux-lora-fast-trainingT1
General

Train styles, people and other subjects at blazing speeds.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.95
P50
381
ms
Uptime
99.77%
F
@fal/flux-lora-fillT1
General

FLUX.1 [dev] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.94
P50
638
ms
Uptime
99.94%
F
@fal/flux-lora-image-to-imageT1
General

FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.

Price
0.000
cr/req
Uses
782
est.
Rep
0.96
P50
237
ms
Uptime
99.96%
F
@fal/flux-lora-inpaintingT1
General

Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.93
P50
152
ms
Uptime
99.70%
F
@fal/flux-lora-portrait-trainerT1
General

FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.91
P50
392
ms
Uptime
99.86%
F
@fal/flux-lora-streamT1
General

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.93
P50
409
ms
Uptime
99.90%
F
@fal/flux-pro-kontextT1
General

FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.82
P50
323
ms
Uptime
99.90%
F
@fal/flux-pro-kontext-maxT1
General

FLUX.1 Kontext [max] is a model with greatly improved prompt adherence and typography generation meet premium consistency for editing without compromise on speed.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.87
P50
147
ms
Uptime
99.93%
F
@fal/flux-pro-kontext-max-multiT1
General

Experimental version of FLUX.1 Kontext [max] with multi image handling capabilities

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.85
P50
652
ms
Uptime
99.89%
F
@fal/flux-pro-kontext-max-text-to-imageT1
General

FLUX.1 Kontext [max] text-to-image is a new premium model brings maximum performance across all aspects – greatly improved prompt adherence.

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.90
P50
181
ms
Uptime
99.93%
F
@fal/flux-pro-kontext-multiT1
General

Experimental version of FLUX.1 Kontext [pro] with multi image handling capabilities

Price
0.000
cr/req
Uses
850
est.
Rep
0.96
P50
580
ms
Uptime
99.79%
F
@fal/flux-pro-kontext-text-to-imageT1
General

The FLUX.1 Kontext [pro] text-to-image delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, and flawless typography.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.91
P50
143
ms
Uptime
99.85%
F
@fal/flux-pro-v1-1T1
General

FLUX1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.95
P50
592
ms
Uptime
99.93%
F
@fal/flux-pro-v1-1-reduxT1
General

FLUX1.1 [pro] Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.86
P50
551
ms
Uptime
99.71%
F
@fal/flux-pro-v1-1-ultraT1
General

FLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.

Price
0.000
cr/req
Uses
89
est.
Rep
0.88
P50
249
ms
Uptime
99.79%
F
@fal/flux-pro-v1-1-ultra-finetunedT1
General

FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.83
P50
525
ms
Uptime
99.73%
F
@fal/flux-pro-v1-1-ultra-reduxT1
General

FLUX1.1 [pro] ultra Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.97
P50
293
ms
Uptime
99.73%
F
@fal/flux-pro-v1-eraseT1
General

Latest object erasing model from Black Forest Labs. Remove undesired objects, texts from images.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.92
P50
371
ms
Uptime
99.91%
F
@fal/flux-pro-v1-fillT1
General

FLUX.1 [pro] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.84
P50
471
ms
Uptime
99.89%
F
@fal/flux-pro-v1-fill-finetunedT1
General

FLUX.1 [pro] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 [pro] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
313
est.
Rep
0.89
P50
611
ms
Uptime
99.92%
F
@fal/flux-pro-v1-vtoT1
General

Generate virtual try-on results from a person image plus one or more garment references.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.93
P50
650
ms
Uptime
99.81%
F
@fal/flux-pulidT1
General

An endpoint for personalized image generation using Flux as per given description.

Price
0.000
cr/req
Uses
216
est.
Rep
0.90
P50
359
ms
Uptime
99.73%
F
@fal/flux-schnellT1
General

FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.

Price
0.000
cr/req
Uses
469
est.
Rep
0.86
P50
496
ms
Uptime
99.94%
F
@fal/flux-schnell-reduxT1
General

FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.85
P50
197
ms
Uptime
99.83%
F
@fal/flux-srpoT1
General

FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.86
P50
619
ms
Uptime
99.96%
F
@fal/flux-srpo-image-to-imageT1
General

FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.87
P50
535
ms
Uptime
99.72%
F
@fal/flux-subjectT1
General

Super fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.86
P50
560
ms
Uptime
99.74%
F
@fal/flux-vision-upscalerT1
General

Flux Vision Upscaler for magnify/upscaling images with high fidelity and creativity.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.90
P50
528
ms
Uptime
99.95%
F
@fal/fooocusT1
General

Default parameters with automated optimizations and quality improvements.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.85
P50
504
ms
Uptime
99.86%
F
@fal/fooocus-image-promptT1
General

Default parameters with automated optimizations and quality improvements.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.90
P50
431
ms
Uptime
99.79%
F
@fal/fooocus-inpaintT1
General

Default parameters with automated optimizations and quality improvements.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.83
P50
432
ms
Uptime
99.86%
F
@fal/fooocus-upscale-or-varyT1
General

Default parameters with automated optimizations and quality improvements.

Price
0.000
cr/req
Uses
957
est.
Rep
0.96
P50
191
ms
Uptime
99.71%
F
@fal/framepackT1
General

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.88
P50
641
ms
Uptime
99.89%
F
@fal/framepack-f1T1
General

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.91
P50
375
ms
Uptime
99.88%
F
@fal/framepack-flf2vT1
General

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Price
0.000
cr/req
Uses
430
est.
Rep
0.88
P50
463
ms
Uptime
99.87%
F
@fal/gemini-25-flash-imageT1
General

Google's famous original image generation and editing model, a.k.a Nano Banana

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.97
P50
558
ms
Uptime
99.88%
F
@fal/gemini-25-flash-image-editT1
General

Google's famous original image generation and editing model, a.k.a Nano Banana

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.94
P50
474
ms
Uptime
99.79%
F
@fal/gemini-3-1-flash-image-previewT1
General

Gemini 3.1 Flash Image (a.k.a Nano Banana 2) is Google's new state-of-the-art fast image generation and editing model

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.85
P50
125
ms
Uptime
99.74%
F
@fal/gemini-3-1-flash-image-preview-editT1
General

Gemini 3.1 Flash Image (a.k.a. Nano Banana 2) is Google's new state-of-the-art fast image generation and editing model

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.86
P50
285
ms
Uptime
99.93%
F
@fal/gemini-3-1-flash-ttsT1
General

Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.95
P50
123
ms
Uptime
99.78%
F
@fal/gemini-3-pro-image-previewT1
General

Gemini 3 Pro Image (a.k.a Nano Banana Pro) is Google's state-of-the-art high-fidelity image generation and editing model

Price
0.000
cr/req
Uses
879
est.
Rep
0.92
P50
540
ms
Uptime
99.86%
F
@fal/gemini-3-pro-image-preview-editT1
General

Gemini 3 Pro Image (a.k.a Nano Banana Pro) is Google's state-of-the-art high-fidelity image generation and editing model

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.91
P50
557
ms
Uptime
99.86%
F
@fal/gemini-ttsT1
General

Use Gemini TTS Models to convert your prompts to real audio.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.97
P50
271
ms
Uptime
99.84%
F
@fal/ghiblifyT1
General

Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.97
P50
322
ms
Uptime
99.96%
F
@fal/glm-imageT1
General

Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.

Price
0.000
cr/req
Uses
762
est.
Rep
0.95
P50
634
ms
Uptime
99.93%
F
@fal/glm-image-image-to-imageT1
General

Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.

Price
0.000
cr/req
Uses
489
est.
Rep
0.96
P50
558
ms
Uptime
99.96%
F
@fal/google-gemini-omni-flashT1
General

Creates video with synchronized audio from text input. Grounded in Gemini's real-world knowledge, with improved physics understanding for more coherent motion and interaction.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.85
P50
628
ms
Uptime
99.84%
F
@fal/google-gemini-omni-flash-editT1
General

Edits generated video across multiple conversational turns while preserving scene coherence. Applies iterative changes through natural-language instructions without regenerating the full sequence from scratch.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.96
P50
414
ms
Uptime
99.96%
F
@fal/google-gemini-omni-flash-image-to-videoT1
General

Animates a still image into video with audio. Extends a single frame into coherent motion, grounded in Gemini's physical understanding of how scenes and subjects behave.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.95
P50
558
ms
Uptime
99.95%
F
@fal/google-gemini-omni-flash-reference-to-videoT1
General

Generates video with audio from combined multimodal references. Accepts text, images, audio, and video together as input to guide subject, motion, style, and sound in the output.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.91
P50
283
ms
Uptime
99.99%
F
@fal/google-nano-banana-2-liteT1
General

Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.82
P50
398
ms
Uptime
99.93%
F
@fal/google-nano-banana-liteT1
General

Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.88
P50
260
ms
Uptime
99.95%
F
@fal/google-nano-banana-lite-editT1
General

Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.83
P50
521
ms
Uptime
99.72%
F
@fal/got-ocr-v2T1
General

GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.89
P50
273
ms
Uptime
99.87%
F
@fal/gpt-image-1-5T1
General

GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.93
P50
287
ms
Uptime
99.76%
F
@fal/gpt-image-1-5-editT1
General

GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.86
P50
619
ms
Uptime
99.70%
F
@fal/gpt-image-1-edit-imageT1
General

OpenAI's latest image generation and editing model: gpt-1-image.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.96
P50
621
ms
Uptime
99.94%
F
@fal/gpt-image-1-miniT1
General

GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.84
P50
606
ms
Uptime
99.84%
F
@fal/gpt-image-1-mini-editT1
General

GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.89
P50
333
ms
Uptime
99.78%
F
@fal/gpt-image-1-text-to-imageT1
General

OpenAI's latest image generation and editing model: gpt-1-image.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.92
P50
557
ms
Uptime
99.88%
F
@fal/heygen-avatar3-digital-twinT1
General

Heygen Avatar V3 Model for Digital Twin

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.95
P50
381
ms
Uptime
99.71%
F
@fal/heygen-avatar4-digital-twinT1
General

Heygen Avatar 4 Digital Twin Model

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.85
P50
429
ms
Uptime
99.72%
F
@fal/heygen-avatar4-image-to-videoT1
General

Heygen Photo Avatar 4 Model

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.84
P50
428
ms
Uptime
99.80%
F
@fal/heygen-avatar5-digital-twinT1
General

Create natural HeyGen Avatar V digital twin videos from text or audio, with lip-sync, optional backgrounds, captions, and MP4/WebM output.

Price
0.000
cr/req
Uses
469
est.
Rep
0.93
P50
473
ms
Uptime
99.94%
F
@fal/heygen-v2-translate-precisionT1
General

Heygen Translate Model with Extreme Precision

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.88
P50
265
ms
Uptime
99.81%
F
@fal/heygen-v2-translate-speedT1
General

Heygen Translate Model with Extreme Speed

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.94
P50
208
ms
Uptime
99.80%
F
@fal/heygen-v2-video-agentT1
General

Heygen Text to Video Generation Model

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.91
P50
616
ms
Uptime
99.89%
F
@fal/heygen-v3-lipsync-precisionT1
General

Replace or dub audio on an existing video with high-accuracy avatar-inference lip-sync.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.93
P50
596
ms
Uptime
99.73%
F
@fal/heygen-v3-lipsync-speedT1
General

Replace or dub audio on an existing video with fast audio-only lip-sync.

Price
0.000
cr/req
Uses
665
est.
Rep
0.88
P50
252
ms
Uptime
99.73%
F
@fal/heygen-v3-video-agentT1
General

Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.92
P50
157
ms
Uptime
99.79%
F
@fal/hidream-i1-devT1
General

HiDream-I1 dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.96
P50
478
ms
Uptime
99.97%
F
@fal/hidream-i1-fastT1
General

HiDream-I1 fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within 16 steps.

Price
0.000
cr/req
Uses
948
est.
Rep
0.92
P50
296
ms
Uptime
99.98%
F
@fal/hidream-i1-fullT1
General

HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.92
P50
241
ms
Uptime
99.94%
F
@fal/hidream-i1-full-image-to-imageT1
General

HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.86
P50
273
ms
Uptime
99.77%
F
@fal/hidream-o1-imageT1
General

Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.94
P50
629
ms
Uptime
99.86%
F
@fal/hidream-o1-image-devT1
General

Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.97
P50
571
ms
Uptime
99.94%
F
@fal/hidream-o1-image-dev-editT1
General

Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.95
P50
613
ms
Uptime
99.93%
F
@fal/hidream-o1-image-editT1
General

Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.97
P50
622
ms
Uptime
99.84%
F
@fal/hunyuan-3d-v3-1-partT1
General

Split 3D models into parts with Hunyuan 3D

Price
0.000
cr/req
Uses
967
est.
Rep
0.91
P50
426
ms
Uptime
99.72%
F
@fal/hunyuan-3d-v3-1-pro-image-to-3dT1
General

Generate 3D models from images with Hunyuan 3D Pro

Price
0.000
cr/req
Uses
284
est.
Rep
0.91
P50
354
ms
Uptime
99.86%
F
@fal/hunyuan-3d-v3-1-pro-text-to-3dT1
General

Generate 3D models from text prompts with Hunyuan 3D Pro

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.90
P50
278
ms
Uptime
99.76%
F
@fal/hunyuan-3d-v3-1-rapid-image-to-3dT1
General

Rapidly generate 3D models from images using Hunyuan 3D.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.97
P50
563
ms
Uptime
99.74%
F
@fal/hunyuan-3d-v3-1-rapid-text-to-3dT1
General

Create detailed, fully-textured 3D models with text

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.91
P50
582
ms
Uptime
99.92%
F
@fal/hunyuan-3d-v3-1-smart-topologyT1
General

Optimize 3D mesh topology with Hunyuan 3D Smart Topology.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.90
P50
363
ms
Uptime
99.75%
F
@fal/hunyuan-image-v2-1-text-to-imageT1
General

Use the amazing capabilities of hunyuan image 2.1 to generate images that express the feelings of your text.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.93
P50
603
ms
Uptime
99.84%
F
@fal/hunyuan-image-v3-instruct-editT1
General

Image editing endpoint for Hunyuan Image 3.0 Instruct.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.96
P50
284
ms
Uptime
99.96%
F
@fal/hunyuan-image-v3-instruct-text-to-imageT1
General

Instruct version of Hunyuan-Image 3.0, with internal reasoning capabilities.

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.92
P50
274
ms
Uptime
99.91%
F
@fal/hunyuan-image-v3-text-to-imageT1
General

Leverage the state-of-the-art capabilities of Hunyuan Image 3.0 to generate visual content that effectively conveys the messaging of your written material.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.87
P50
374
ms
Uptime
99.88%
F
@fal/hunyuan-motionT1
General

Generate 3D human motions via text-to-generation interface of Hunyuan Motion!

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.93
P50
616
ms
Uptime
99.80%
F
@fal/hunyuan-motion-fastT1
General

Generate 3D human motions via text-to-generation interface of Hunyuan Motion!

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.90
P50
257
ms
Uptime
99.71%
F
@fal/hunyuan-videoT1
General

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.87
P50
130
ms
Uptime
99.82%
F
@fal/hunyuan-video-foleyT1
General

Use the capabilities of the hunyuan foley model to bring life to your videos by adding sound effect to them.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.95
P50
402
ms
Uptime
99.90%
F
@fal/hunyuan-video-image-to-videoT1
General

Image to Video for the high-quality Hunyuan Video I2V model.

Price
0.000
cr/req
Uses
928
est.
Rep
0.86
P50
615
ms
Uptime
99.94%
F
@fal/hunyuan-video-img2vid-loraT1
General

Image to Video for the Hunyuan Video model using a custom trained LoRA.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.89
P50
442
ms
Uptime
99.90%
F
@fal/hunyuan-video-v1-5-image-to-videoT1
General

Hunyuan Video 1.5 is Tencent's latest and best video model

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.90
P50
480
ms
Uptime
99.97%
F
@fal/hunyuan-video-v1-5-text-to-videoT1
General

Hunyuan Video 1.5 is Tencent's latest and best video model

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.96
P50
609
ms
Uptime
99.92%
F
@fal/hunyuan-video-video-to-videoT1
General

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.

Price
0.000
cr/req
Uses
948
est.
Rep
0.83
P50
335
ms
Uptime
99.99%
F
@fal/hunyuan-worldT1
General

Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.91
P50
608
ms
Uptime
99.71%
F
@fal/hunyuan-world-image-to-worldT1
General

Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.94
P50
292
ms
Uptime
99.82%
F
@fal/hunyuan3d-v2T1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
193
ms
Uptime
99.73%
F
@fal/hunyuan3d-v2-miniT1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.98
P50
499
ms
Uptime
99.83%
F
@fal/hunyuan3d-v2-mini-turboT1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.96
P50
570
ms
Uptime
99.79%
F
@fal/hunyuan3d-v2-multi-viewT1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.95
P50
317
ms
Uptime
99.98%
F
@fal/hunyuan3d-v2-multi-view-turboT1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
879
est.
Rep
0.97
P50
604
ms
Uptime
99.86%
F
@fal/hunyuan3d-v2-turboT1
General

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
860
est.
Rep
0.90
P50
219
ms
Uptime
99.79%
F
@fal/hunyuan3d-v3-image-to-3dT1
General

Transform your photos into ultra-high-resolution 3D models in seconds. Film-quality geometry with PBR textures, ready for games, e-commerce, and 3D printing.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.96
P50
373
ms
Uptime
99.83%
F
@fal/hunyuan3d-v3-sketch-to-3dT1
General

Create your imagined 3D models with just text. Production-ready, export-ready professional assets with realistic lighting and materials in minutes.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.98
P50
627
ms
Uptime
99.77%
F
@fal/hunyuan3d-v3-text-to-3dT1
General

Turn simple sketches into detailed, fully-textured 3D models. Instantly convert your concept designs into formats ready for Unity, Unreal, and Blender.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.92
P50
582
ms
Uptime
99.72%
F
@fal/hy-wu-editT1
General

Image editing with HY-WU. Transfer outfits, swap faces, and blend textures instantly—no finetuning needed, just describe what you want and provide reference images.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.98
P50
230
ms
Uptime
99.83%
F
@fal/hyper3d-rodinT1
General

Rodin by Hyper3D generates realistic and production ready 3D models from text or images.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.84
P50
525
ms
Uptime
99.90%
F
@fal/hyper3d-rodin-v2T1
General

Rodin by Hyper3D generates realistic and production ready 3D models from text or images.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.85
P50
420
ms
Uptime
99.89%
F
@fal/hyper3d-rodin-v2-5T1
General

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.89
P50
194
ms
Uptime
99.79%
F
@fal/hyper3d-rodin-v2-5-fastT1
General

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.88
P50
594
ms
Uptime
99.82%
F
@fal/hyper3d-rodin-v2-5-text-to-3dT1
General

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.83
P50
230
ms
Uptime
99.96%
F
@fal/hyper3d-rodin-v2-5-text-to-3d-fastT1
General

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.89
P50
341
ms
Uptime
99.76%
F
@fal/iclight-v2T1
General

An endpoint for re-lighting photos and changing their backgrounds per a given description

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.94
P50
157
ms
Uptime
99.95%
F
@fal/ideogram-characterT1
General

Generate consistent character appearances across multiple images. Maintain facial features, proportions, and distinctive traits for cohesive storytelling and branding

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.83
P50
597
ms
Uptime
99.97%
F
@fal/ideogram-character-editT1
General

Modify consistent characters while preserving their core identity. Edit poses, expressions, or clothing without losing recognizable character features

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.91
P50
283
ms
Uptime
99.83%
F
@fal/ideogram-character-remixT1
General

Transform your consistent character into different art styles, settings, or scenarios while maintaining their distinctive appearance and identity

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.89
P50
236
ms
Uptime
99.80%
F
@fal/ideogram-custom-modelsT1
General

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

Price
0.000
cr/req
Uses
723
est.
Rep
0.96
P50
469
ms
Uptime
99.84%
F
@fal/ideogram-custom-models-generateT1
General

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.83
P50
373
ms
Uptime
99.85%
F
@fal/ideogram-remove-backgroundT1
General

Remove backgrounds from existing images with Ideogram's remove background feature. Isolate subjects cleanly for compositing and creative reuse.

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.97
P50
225
ms
Uptime
99.71%
F
@fal/ideogram-upscaleT1
General

Ideogram Upscale enhances the resolution of the reference image by up to 2X and might enhance the reference image too. Optionally refine outputs with a prompt for guided improvements.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.93
P50
351
ms
Uptime
99.94%
F
@fal/ideogram-v2T1
General

Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.94
P50
579
ms
Uptime
99.85%
F
@fal/ideogram-v2-editT1
General

Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.87
P50
345
ms
Uptime
99.86%
F
@fal/ideogram-v2-remixT1
General

Reimagine existing images with Ideogram V2's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.91
P50
473
ms
Uptime
99.87%
F
@fal/ideogram-v2-turboT1
General

Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.93
P50
439
ms
Uptime
99.86%
F
@fal/ideogram-v2-turbo-editT1
General

Edit images faster with Ideogram V2 Turbo. Quick modifications and adjustments while preserving the high-quality standards and realistic outputs of Ideogram.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.91
P50
135
ms
Uptime
99.88%
F
@fal/ideogram-v2-turbo-remixT1
General

Rapidly create image variations with Ideogram V2 Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.85
P50
155
ms
Uptime
99.95%
F
@fal/ideogram-v2aT1
General

Generate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.97
P50
187
ms
Uptime
99.75%
F
@fal/ideogram-v2a-remixT1
General

Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.83
P50
509
ms
Uptime
99.95%
F
@fal/ideogram-v2a-turboT1
General

Accelerated image generation with Ideogram V2A Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
594
ms
Uptime
99.88%
F
@fal/ideogram-v2a-turbo-remixT1
General

Rapidly create image variations with Ideogram V2A Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.84
P50
509
ms
Uptime
99.94%
F
@fal/ideogram-v3T1
General

Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Price
0.000
cr/req
Uses
362
est.
Rep
0.90
P50
435
ms
Uptime
99.73%
F
@fal/ideogram-v3-editT1
General

Transform existing images with Ideogram V3's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.84
P50
340
ms
Uptime
99.83%
F
@fal/ideogram-v3-generate-transparentT1
General

Generate images with transparent backgrounds using Ideogram Transparent model

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.93
P50
170
ms
Uptime
99.84%
F
@fal/ideogram-v3-layerize-textT1
General

Ideogram Layerize takes an existing flat graphic, removes text, and returns structured text containers you can edit/recompose in html or json format.

Price
0.000
cr/req
Uses
665
est.
Rep
0.85
P50
222
ms
Uptime
99.73%
F
@fal/ideogram-v3-reframeT1
General

Extend existing images with Ideogram V3's reframe feature. Create expanded versions and adaptations while preserving main image and adding new creative directions through prompt guidance.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.89
P50
362
ms
Uptime
99.72%
F
@fal/ideogram-v3-remixT1
General

Reimagine existing images with Ideogram V3's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.93
P50
161
ms
Uptime
99.78%
F
@fal/ideogram-v3-replace-backgroundT1
General

Replace backgrounds existing images with Ideogram V3's replace background feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.83
P50
218
ms
Uptime
99.90%
F
@fal/ideogram-v4T1
General

Generate high-quality images, posters, and logos with Ideogram's latest V4.0q — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.96
P50
533
ms
Uptime
99.95%
F
@fal/ideogram-v4-fastT1
General

Generate high-quality images, posters, and logos with Ideogram's latest V4.0q — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs IN A SECOND.

Price
0.000
cr/req
Uses
518
est.
Rep
0.86
P50
543
ms
Uptime
99.74%
F
@fal/ideogram-v4-image-to-imageT1
General

Ideogram V4.0q Image-to-Image transforms an input image with a text prompt, restyling and reworking the composition while preserving its core structure for prompt-faithful, high-fidelity edits.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.89
P50
215
ms
Uptime
99.92%
F
@fal/ideogram-v4-image-to-image-loraT1
General

Ideogram V4.0q Image-to-Image LoRA applies a custom-trained LoRA on top of an input image, steering edits toward a specific style, subject, or brand identity while keeping the source composition intact.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.87
P50
315
ms
Uptime
99.86%
F
@fal/ideogram-v4-instantT1
General

Generate high-quality images, posters, and logos with Ideogram's latest V4.0q — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs FRACTION OF A SECOND.

Price
0.000
cr/req
Uses
811
est.
Rep
0.89
P50
569
ms
Uptime
99.70%
F
@fal/ideogram-v4-loraT1
General

Generate high-quality images, posters, and logos with Ideogram's latest V4.0q using LoRA — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.92
P50
228
ms
Uptime
99.96%
F
@fal/ideogram-v4-tilingT1
General

Ideogram V4.0q Tiling generates seamless, edge-matching textures and patterns that repeat infinitely in any direction, ideal for backgrounds, surfaces, and wallpapers.

Price
0.000
cr/req
Uses
870
est.
Rep
0.83
P50
243
ms
Uptime
99.84%
F
@fal/ideogram-v4-tiling-loraT1
General

Ideogram V4.0q Tiling LoRA produces seamless repeatable patterns guided by a custom-trained LoRA, locking a specific aesthetic or motif into tileable textures for cohesive, large-scale surface design.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.86
P50
446
ms
Uptime
99.79%
F
@fal/ideogram-v4-trainerT1
General

Train custom LoRAs for personalization, styles or other use cases on top of Ideogram V4.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.92
P50
418
ms
Uptime
99.91%
F
@fal/illusion-diffusionT1
General

Create illusions conditioned on image.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.85
P50
657
ms
Uptime
99.73%
F
@fal/image-apps-v2-age-modifyT1
General

Modify a face to look younger or older while keeping identity realistic.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.93
P50
655
ms
Uptime
99.78%
F
@fal/image-apps-v2-city-teleportT1
General

Place a person’s photo into iconic cities worldwide.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.95
P50
393
ms
Uptime
99.91%
F
@fal/image-apps-v2-expression-changeT1
General

Change facial expressions in photos with realistic results.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.91
P50
160
ms
Uptime
99.75%
F
@fal/image-apps-v2-hair-changeT1
General

Change hairstyles and hair colors in photos realistically.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.90
P50
278
ms
Uptime
99.76%
F
@fal/image-apps-v2-headshot-photoT1
General

Generate professional headshot photos with customizable backgrounds.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.92
P50
578
ms
Uptime
99.90%
F
@fal/image-apps-v2-makeup-applicationT1
General

Apply realistic makeup styles with adjustable intensity.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.96
P50
482
ms
Uptime
99.93%
F
@fal/image-apps-v2-object-removalT1
General

Remove unwanted objects seamlessly from any image.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.84
P50
158
ms
Uptime
99.70%
F
@fal/image-apps-v2-outpaintT1
General

Directional outpainting. Choose edges to expand. left, right, top, or center (uniform all sides). Only expanded areas are generated; an optional zoom-out pulls the frame back by the chosen amount.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.92
P50
308
ms
Uptime
99.95%
F
@fal/image-apps-v2-perspectiveT1
General

Easily adjust the perspective of any image to different angles.

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.93
P50
149
ms
Uptime
99.93%
F
@fal/image-apps-v2-photo-restorationT1
General

Restore old or damaged photos by fixing colors, scratches, and resolution.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.87
P50
143
ms
Uptime
99.92%
F
@fal/image-apps-v2-photography-effectsT1
General

Apply diverse photography styles and effects to transform your images.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.92
P50
219
ms
Uptime
99.80%
F
@fal/image-apps-v2-portrait-enhanceT1
General

Enhance and refine portrait photos with improved clarity and detail.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.90
P50
624
ms
Uptime
99.79%
F
@fal/image-apps-v2-product-holdingT1
General

Place products naturally in a person’s hands for realistic marketing visuals.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.84
P50
458
ms
Uptime
99.92%
F
@fal/image-apps-v2-product-photographyT1
General

Generate professional product photography with realistic lighting and backgrounds.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.93
P50
575
ms
Uptime
99.96%
F
@fal/image-apps-v2-relightingT1
General

Adjust and enhance images with different lighting styles.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.95
P50
347
ms
Uptime
99.82%
F
@fal/image-apps-v2-style-transferT1
General

Apply artistic styles like impressionism, cubism, or surrealism to your images.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.93
P50
156
ms
Uptime
99.75%
F
@fal/image-apps-v2-texture-transformT1
General

Transform objects with different surface textures like marble, wood, or fabric.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.87
P50
130
ms
Uptime
99.81%
F
@fal/image-apps-v2-virtual-try-onT1
General

Try on clothes virtually by combining person and clothing images.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.92
P50
195
ms
Uptime
99.72%
F
@fal/image-editing-age-progressionT1
General

See how you or others might look at different ages, from younger to older, while preserving core facial features.

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.82
P50
563
ms
Uptime
99.79%
F
@fal/image-editing-baby-versionT1
General

Transform any person into their baby version, while preserving the original pose and expression with childlike features.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.84
P50
231
ms
Uptime
99.95%
F
@fal/image-editing-background-changeT1
General

Replace your photo's background with any scene you desire, from beach sunsets to urban landscapes, with perfect lighting and shadows

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.97
P50
276
ms
Uptime
99.85%
F
@fal/image-editing-broccoli-haircutT1
General

Transform your character's hair into broccoli style while keeping the original characters likeness

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.93
P50
553
ms
Uptime
99.83%
F
@fal/image-editing-cartoonifyT1
General

Transform your photos into vibrant cool cartoons with bold outlines and rich colors.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.86
P50
337
ms
Uptime
99.97%
F
@fal/image-editing-color-correctionT1
General

Perfect your photos with professional color grading, balanced tones, and vibrant yet natural colors

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.85
P50
332
ms
Uptime
99.77%
F
@fal/image-editing-expression-changeT1
General

Change facial expressions in photos to any emotion you desire, from smiles to serious looks.

Price
0.000
cr/req
Uses
870
est.
Rep
0.92
P50
418
ms
Uptime
99.83%
F
@fal/image-editing-face-enhancementT1
General

Enhance facial features with professional retouching while maintaining a natural, realistic look

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.88
P50
493
ms
Uptime
99.72%
F
@fal/image-editing-hair-changeT1
General

Experiment with different hairstyles, from bald to any style you can imagine, while maintaining natural lighting and realistic results.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.91
P50
219
ms
Uptime
99.81%
F
@fal/image-editing-object-removalT1
General

Remove unwanted objects or people from your photos while seamlessly blending the background.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.85
P50
640
ms
Uptime
99.85%
F
@fal/image-editing-photo-restorationT1
General

Restore and enhance old or damaged photos by removing imperfections, adding color while preserving the original character and details of the image.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.97
P50
592
ms
Uptime
99.95%
F
@fal/image-editing-plushie-styleT1
General

Transform your photos into cool plushies while keeping the original characters likeness

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.96
P50
255
ms
Uptime
99.99%
F
@fal/image-editing-professional-photoT1
General

Turn your casual photos into stunning professional studio portraits with perfect lighting and high-end photography style.

Price
0.000
cr/req
Uses
450
est.
Rep
0.87
P50
442
ms
Uptime
99.89%
F
@fal/image-editing-realismT1
General

Add details to faces, enhance face features, remove blur.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.82
P50
461
ms
Uptime
99.83%
F
@fal/image-editing-reframeT1
General

The reframe endpoint intelligently adjusts an image's aspect ratio while preserving the main subject's position, composition, pose, and perspective

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.85
P50
163
ms
Uptime
99.81%
F
@fal/image-editing-retouchT1
General

Retouch photos of faces. Remove blemishes and improve the skin.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.94
P50
562
ms
Uptime
99.97%
F
@fal/image-editing-scene-compositionT1
General

Place your subject in any scene you imagine, from enchanted forests to urban settings, with professional composition and lighting

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.86
P50
197
ms
Uptime
99.79%
F
@fal/image-editing-style-transferT1
General

Transform your photos into artistic masterpieces inspired by famous styles like Van Gogh's Starry Night or any artistic style you choose.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.89
P50
481
ms
Uptime
99.72%
F
@fal/image-editing-text-removalT1
General

Remove all text and writing from images while preserving the background and natural appearance.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.93
P50
275
ms
Uptime
99.96%
F
@fal/image-editing-time-of-dayT1
General

Transform your photos to any time of day, from golden hour to midnight, with appropriate lighting and atmosphere.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.88
P50
426
ms
Uptime
99.82%
F
@fal/image-editing-weather-effectT1
General

Add realistic weather effects like snowfall, rain, or fog to your photos while maintaining the scene's mood.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.86
P50
543
ms
Uptime
99.83%
F
@fal/image-editing-wojak-styleT1
General

Transform your photos into wojak style while keeping the original characters likeness

Price
0.000
cr/req
Uses
713
est.
Rep
0.97
P50
592
ms
Uptime
99.82%
F
@fal/image-editing-youtube-thumbnailsT1
General

Generate YouTube thumbnails with custom text

Price
0.000
cr/req
Uses
645
est.
Rep
0.86
P50
197
ms
Uptime
99.96%
F
@fal/image-preprocessors-depth-anything-v2T1
General

Depth Anything v2 preprocessor.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.97
P50
487
ms
Uptime
99.82%
F
@fal/image-preprocessors-hedT1
General

Holistically-Nested Edge Detection (HED) preprocessor.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.93
P50
216
ms
Uptime
99.89%
F
@fal/image-preprocessors-lineartT1
General

Line art preprocessor.

Price
0.000
cr/req
Uses
752
est.
Rep
0.96
P50
533
ms
Uptime
99.90%
F
@fal/image-preprocessors-midasT1
General

MiDaS depth estimation preprocessor.

Price
0.000
cr/req
Uses
606
est.
Rep
0.93
P50
570
ms
Uptime
99.92%
F
@fal/image-preprocessors-mlsdT1
General

M-LSD line segment detection preprocessor.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.85
P50
449
ms
Uptime
99.81%
F
@fal/image-preprocessors-pidiT1
General

PIDI (Pidinet) preprocessor.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.88
P50
125
ms
Uptime
99.89%
F
@fal/image-preprocessors-samT1
General

Segment Anything Model (SAM) preprocessor.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.93
P50
258
ms
Uptime
99.93%
F
@fal/image-preprocessors-scribbleT1
General

Scribble preprocessor.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.90
P50
350
ms
Uptime
99.80%
F
@fal/image-preprocessors-teedT1
General

TEED (Temporal Edge Enhancement Detection) preprocessor.

Price
0.000
cr/req
Uses
401
est.
Rep
0.92
P50
279
ms
Uptime
99.81%
F
@fal/image-preprocessors-zoeT1
General

ZoeDepth preprocessor.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.84
P50
243
ms
Uptime
99.95%
F
@fal/image2pixelT1
General

Turn images into pixel-perfect retro art

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.89
P50
159
ms
Uptime
99.91%
F
@fal/image2svgT1
General

Image2SVG transforms raster images into clean vector graphics, preserving visual quality while enabling scalable, customizable SVG outputs with precise control over detail levels.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.93
P50
520
ms
Uptime
99.83%
F
@fal/imageutils-depthT1
General

Create depth maps using Midas depth estimation.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.93
P50
186
ms
Uptime
99.97%
F
@fal/imageutils-marigold-depthT1
General

Create depth maps using Marigold depth estimation.

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.94
P50
178
ms
Uptime
99.89%
F
@fal/imageutils-nsfwT1
General

Predict the probability of an image being NSFW.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.96
P50
570
ms
Uptime
99.80%
F
@fal/imageutils-rembgT1
General

Remove the background from an image.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.90
P50
456
ms
Uptime
99.79%
F
@fal/imagineart-imagineart-1-5-preview-text-to-imageT1
General

ImagineArt 1.5 text-to-image model generates high-fidelity professional-grade visuals with lifelike realism, strong aesthetics, and text that actually reads correctly.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.94
P50
313
ms
Uptime
99.76%
F
@fal/imagineart-imagineart-1-5-pro-preview-text-to-imageT1
General

ImagineArt 1.5 Pro is an advanced text-to-image model that creates ultra-high-fidelity 4K visuals with lifelike realism, refined aesthetics, and powerful creative output suited for professional use.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.97
P50
638
ms
Uptime
99.72%
F
@fal/imagineart-imagineart-2-0-edit-preview-image-to-imageT1
General

ImagineArt 2.0 Edit delivers precise prompt-guided image editing at 2K resolution, preserving fine detail and realism while accurately applying targeted changes across one or more reference images.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.86
P50
450
ms
Uptime
99.93%
F
@fal/imagineart-imagineart-2-0-preview-text-to-imageT1
General

ImagineArt 2.0 is ImagineArt's latest state-of-the-art visual reasoning text-to-image model, generating high-fidelity, professional-grade visuals with lifelike realism, cinematic effects, and strong aesthetic quality.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.91
P50
367
ms
Uptime
99.97%
F
@fal/index-tts-2-text-to-speechT1
General

Generate natural, clear speeches using Index TTS 2.0 from IndexTeam

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.91
P50
379
ms
Uptime
99.79%
F
@fal/infinitalkT1
General

Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

Price
0.000
cr/req
Uses
577
est.
Rep
0.87
P50
468
ms
Uptime
99.84%
F
@fal/infinitalk-single-textT1
General

Infinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.83
P50
635
ms
Uptime
99.74%
F
@fal/infinitalk-video-to-videoT1
General

Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.89
P50
396
ms
Uptime
99.96%
F
@fal/infinity-star-text-to-videoT1
General

InfinityStar’s unified 8B spacetime autoregressive engine to turn any text prompt into crisp 720p videos - 10× faster than diffusion models.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.89
P50
459
ms
Uptime
99.74%
F
@fal/inpaintT1
General

Inpaint images with SD and SDXL

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.83
P50
412
ms
Uptime
99.89%
F
@fal/instant-characterT1
General

InstantCharacter creates high-quality, consistent characters from text prompts, supporting diverse poses, styles, and appearances with strong identity control.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.88
P50
231
ms
Uptime
99.83%
F
@fal/invisible-watermarkT1
General

Invisible Watermark is a model that can add an invisible watermark to an image.

Price
0.000
cr/req
Uses
928
est.
Rep
0.95
P50
381
ms
Uptime
99.93%
F
@fal/inworld-ttsT1
General

Text to Speech Endpoint for Inworld's TTS-1.5 Max.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.97
P50
297
ms
Uptime
99.75%
F
@fal/ip-adapter-face-idT1
General

High quality zero-shot personalization

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.97
P50
347
ms
Uptime
99.93%
F
@fal/janusT1
General

DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.90
P50
148
ms
Uptime
99.72%
F
@fal/joyai-image-editT1
General

All-in-one image AI with JoyAI-Image. Understand, create, and edit images through natural language—the model's deep visual understanding powers more accurate generation and precise editing in a unified system.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.94
P50
419
ms
Uptime
99.86%
F
@fal/kandinsky5-pro-image-to-videoT1
General

Kandinsky 5.0 Pro is a diffusion model for fast, high-quality image-to-video generation.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.95
P50
212
ms
Uptime
99.90%
F
@fal/kandinsky5-pro-text-to-videoT1
General

Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.92
P50
515
ms
Uptime
99.93%
F
@fal/kandinsky5-text-to-videoT1
General

Kandinsky 5.0 is a diffusion model for fast, high-quality text-to-video generation.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.98
P50
120
ms
Uptime
99.83%
F
@fal/kandinsky5-text-to-video-distillT1
General

Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation.

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.96
P50
187
ms
Uptime
99.96%
F
@fal/kling-image-o1T1
General

Perform precise image edits using strong reference control, transforming subjects, styles, and local details while preserving visual consistency.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.87
P50
438
ms
Uptime
99.92%
F
@fal/kling-image-o3-image-to-imageT1
General

Kling Omni 3: Top-tier image-to-image with flawless consistency.

Price
0.000
cr/req
Uses
645
est.
Rep
0.91
P50
658
ms
Uptime
99.98%
F
@fal/kling-image-o3-text-to-imageT1
General

Kling Omni 3: Top-tier text-to-image with flawless consistency.

Price
0.000
cr/req
Uses
616
est.
Rep
0.96
P50
293
ms
Uptime
99.91%
F
@fal/kling-image-v3-image-to-imageT1
General

Kling Image V3: Latest kling image model

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.95
P50
132
ms
Uptime
99.91%
F
@fal/kling-image-v3-text-to-imageT1
General

Kling V3: Latest Kling Image model

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.89
P50
552
ms
Uptime
99.78%
F
@fal/kling-v1-5-kolors-virtual-try-onT1
General

Kling Kolors Virtual TryOn v1.5 is a high quality image based Try-On endpoint which can be used for commercial try on.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.91
P50
624
ms
Uptime
99.86%
F
@fal/kling-video-ai-avatar-v2-proT1
General

Kling AI Avatar v2 Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.97
P50
647
ms
Uptime
99.77%
F
@fal/kling-video-ai-avatar-v2-standardT1
General

Kling AI Avatar v2 Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.83
P50
504
ms
Uptime
99.92%
F
@fal/kling-video-create-voiceT1
General

Create Voices to be used with Kling Models Voice Control

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.94
P50
486
ms
Uptime
99.93%
F
@fal/kling-video-lipsync-audio-to-videoT1
General

Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.88
P50
434
ms
Uptime
99.93%
F
@fal/kling-video-lipsync-text-to-videoT1
General

Kling LipSync is a text-to-video model that generates realistic lip movements from text input.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.97
P50
389
ms
Uptime
99.96%
F
@fal/kling-video-o1-image-to-videoT1
General

Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.89
P50
599
ms
Uptime
99.70%
F
@fal/kling-video-o1-reference-to-videoT1
General

Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.

Price
0.000
cr/req
Uses
50
est.
Rep
0.87
P50
222
ms
Uptime
99.74%
F
@fal/kling-video-o1-standard-image-to-videoT1
General

Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.90
P50
182
ms
Uptime
99.70%
F
@fal/kling-video-o1-standard-reference-to-videoT1
General

Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.96
P50
542
ms
Uptime
99.98%
F
@fal/kling-video-o1-standard-video-to-video-editT1
General

Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.88
P50
395
ms
Uptime
99.93%
F
@fal/kling-video-o1-standard-video-to-video-referenceT1
General

Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.

Price
0.000
cr/req
Uses
225
est.
Rep
0.93
P50
321
ms
Uptime
99.75%
F
@fal/kling-video-o1-video-to-video-editT1
General

Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.93
P50
388
ms
Uptime
99.77%
F
@fal/kling-video-o1-video-to-video-referenceT1
General

Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.94
P50
123
ms
Uptime
99.94%
F
@fal/kling-video-o3-4k-image-to-videoT1
General

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.92
P50
157
ms
Uptime
99.89%
F
@fal/kling-video-o3-4k-reference-to-videoT1
General

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Price
0.000
cr/req
Uses
860
est.
Rep
0.92
P50
528
ms
Uptime
99.80%
F
@fal/kling-video-o3-4k-text-to-videoT1
General

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.93
P50
591
ms
Uptime
99.87%
F
@fal/kling-video-o3-pro-image-to-videoT1
General

Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.83
P50
246
ms
Uptime
99.90%
F
@fal/kling-video-o3-pro-reference-to-videoT1
General

Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.98
P50
196
ms
Uptime
99.78%
F
@fal/kling-video-o3-pro-text-to-videoT1
General

Generate realistic videos using Kling O3 from Kling Team!

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.95
P50
474
ms
Uptime
99.83%
F
@fal/kling-video-o3-pro-video-to-video-editT1
General

Edit videos using Kling O3 from Kling Team!

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.82
P50
449
ms
Uptime
99.75%
F
@fal/kling-video-o3-pro-video-to-video-referenceT1
General

Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.95
P50
271
ms
Uptime
99.97%
F
@fal/kling-video-o3-standard-image-to-videoT1
General

Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.

Price
0.000
cr/req
Uses
430
est.
Rep
0.95
P50
499
ms
Uptime
99.87%
F
@fal/kling-video-o3-standard-reference-to-videoT1
General

Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.

Price
0.000
cr/req
Uses
421
est.
Rep
0.96
P50
643
ms
Uptime
99.83%
F
@fal/kling-video-o3-standard-text-to-videoT1
General

Generate realistic videos using Kling O3 from Kling Team!

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.90
P50
553
ms
Uptime
99.88%
F
@fal/kling-video-o3-standard-video-to-video-editT1
General

Edit videos using Kling O3 from Kling Team!

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.83
P50
357
ms
Uptime
99.75%
F
@fal/kling-video-o3-standard-video-to-video-referenceT1
General

Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.87
P50
236
ms
Uptime
99.85%
F
@fal/kling-video-v1-5-pro-effectsT1
General

Generate video clips from your prompts using Kling 1.5 (pro)

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.83
P50
213
ms
Uptime
99.93%
F
@fal/kling-video-v1-5-pro-image-to-videoT1
General

Generate video clips from your images using Kling 1.5 (pro)

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.87
P50
189
ms
Uptime
99.92%
F
@fal/kling-video-v1-5-pro-text-to-videoT1
General

Generate video clips from your prompts using Kling 1.5 (pro)

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.83
P50
588
ms
Uptime
99.71%
F
@fal/kling-video-v1-6-pro-effectsT1
General

Generate video clips from your prompts using Kling 1.6 (pro)

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.87
P50
151
ms
Uptime
99.80%
F
@fal/kling-video-v1-6-pro-elementsT1
General

Generate video clips from your multiple image references using Kling 1.6 (pro)

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.97
P50
129
ms
Uptime
99.94%
F
@fal/kling-video-v1-6-pro-image-to-videoT1
General

Generate video clips from your images using Kling 1.6 (pro)

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.90
P50
194
ms
Uptime
99.85%
F
@fal/kling-video-v1-6-pro-text-to-videoT1
General

Generate video clips from your prompts using Kling 1.6 (pro)

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.91
P50
211
ms
Uptime
99.76%
F
@fal/kling-video-v1-6-standard-effectsT1
General

Generate video clips from your prompts using Kling 1.6 (std)

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.86
P50
611
ms
Uptime
99.73%
F
@fal/kling-video-v1-6-standard-elementsT1
General

Generate video clips from your multiple image references using Kling 1.6 (standard)

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.84
P50
550
ms
Uptime
99.77%
F
@fal/kling-video-v1-6-standard-image-to-videoT1
General

Generate video clips from your images using Kling 1.6 (std)

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.92
P50
595
ms
Uptime
99.79%
F
@fal/kling-video-v1-6-standard-text-to-videoT1
General

Generate video clips from your prompts using Kling 1.6 (std)

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.91
P50
283
ms
Uptime
99.78%
F
@fal/kling-video-v1-pro-ai-avatarT1
General

Kling AI Avatar Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

Price
0.000
cr/req
Uses
235
est.
Rep
0.93
P50
321
ms
Uptime
99.80%
F
@fal/kling-video-v1-standard-ai-avatarT1
General

Kling AI Avatar Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

Price
0.000
cr/req
Uses
333
est.
Rep
0.94
P50
406
ms
Uptime
99.96%
F
@fal/kling-video-v1-standard-effectsT1
General

Generate video clips from your prompts using Kling 1.0

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.91
P50
223
ms
Uptime
99.82%
F
@fal/kling-video-v1-standard-image-to-videoT1
General

Generate video clips from your images using Kling 1.0

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.97
P50
469
ms
Uptime
99.94%
F
@fal/kling-video-v1-standard-text-to-videoT1
General

Generate video clips from your prompts using Kling 1.0

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.97
P50
500
ms
Uptime
99.80%
F
@fal/kling-video-v1-ttsT1
General

Generate speech from text prompts and different voices using the Kling TTS model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
489
est.
Rep
0.94
P50
503
ms
Uptime
99.97%
F
@fal/kling-video-v2-1-master-image-to-videoT1
General

Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.94
P50
161
ms
Uptime
99.79%
F
@fal/kling-video-v2-1-master-text-to-videoT1
General

Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.88
P50
649
ms
Uptime
99.71%
F
@fal/kling-video-v2-1-pro-image-to-videoT1
General

Kling 2.1 Pro is an advanced endpoint for the Kling 2.1 model, offering professional-grade videos with enhanced visual fidelity, precise camera movements, and dynamic motion control, perfect for cinematic storytelling.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.90
P50
506
ms
Uptime
99.93%
F
@fal/kling-video-v2-1-standard-image-to-videoT1
General

Kling 2.1 Standard is a cost-efficient endpoint for the Kling 2.1 model, delivering high-quality image-to-video generation

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.91
P50
194
ms
Uptime
99.87%
F
@fal/kling-video-v2-5-turbo-pro-image-to-videoT1
General

Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.82
P50
276
ms
Uptime
99.85%
F
@fal/kling-video-v2-5-turbo-pro-text-to-videoT1
General

Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.85
P50
610
ms
Uptime
99.78%
F
@fal/kling-video-v2-5-turbo-standard-image-to-videoT1
General

Kling 2.5 Turbo Standard: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
598
ms
Uptime
99.94%
F
@fal/kling-video-v2-6-pro-image-to-videoT1
General

Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.98
P50
537
ms
Uptime
99.92%
F
@fal/kling-video-v2-6-pro-motion-controlT1
General

Transfer movements from a reference video to any character image. Pro mode delivers higher quality output, ideal for complex dance moves and gestures.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.86
P50
142
ms
Uptime
99.80%
F
@fal/kling-video-v2-6-pro-text-to-videoT1
General

Kling 2.6 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.90
P50
346
ms
Uptime
99.80%
F
@fal/kling-video-v2-6-standard-motion-controlT1
General

Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.96
P50
356
ms
Uptime
99.91%
F
@fal/kling-video-v2-master-image-to-videoT1
General

Generate video clips from your images using Kling 2.0 Master

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.93
P50
553
ms
Uptime
99.83%
F
@fal/kling-video-v2-master-text-to-videoT1
General

Generate video clips from your prompts using Kling 2.0 Master

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.85
P50
134
ms
Uptime
99.70%
F
@fal/kling-video-v3-4k-image-to-videoT1
General

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.86
P50
488
ms
Uptime
99.75%
F
@fal/kling-video-v3-4k-text-to-videoT1
General

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.94
P50
520
ms
Uptime
99.94%
F
@fal/kling-video-v3-pro-image-to-videoT1
General

Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.95
P50
570
ms
Uptime
99.91%
F
@fal/kling-video-v3-pro-motion-controlT1
General

Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.94
P50
536
ms
Uptime
99.87%
F
@fal/kling-video-v3-pro-text-to-videoT1
General

Kling 3.0 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.92
P50
148
ms
Uptime
99.70%
F
@fal/kling-video-v3-standard-image-to-videoT1
General

Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

Price
0.000
cr/req
Uses
430
est.
Rep
0.85
P50
256
ms
Uptime
99.86%
F
@fal/kling-video-v3-standard-motion-controlT1
General

Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.84
P50
652
ms
Uptime
99.93%
F
@fal/kling-video-v3-standard-text-to-videoT1
General

Kling 3.0 Standard: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.

Price
0.000
cr/req
Uses
518
est.
Rep
0.88
P50
455
ms
Uptime
99.73%
F
@fal/kling-video-v3-turbo-pro-image-to-videoT1
General

Generate high quality 1080p videos from images using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.82
P50
298
ms
Uptime
99.92%
F
@fal/kling-video-v3-turbo-pro-text-to-videoT1
General

Generate high quality 1080p videos using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.93
P50
528
ms
Uptime
99.81%
F
@fal/kling-video-v3-turbo-standard-image-to-videoT1
General

Kling 3.0 Turbo Standard animates a first and last frame reference image into 720P video with native audio, delivering quick, affordable image-driven motion for fast turnaround

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.97
P50
529
ms
Uptime
99.75%
F
@fal/kling-video-v3-turbo-standard-text-to-videoT1
General

Kling 3.0 Turbo Standard is a fast, cost-efficient video generation model that turns text prompts directly into 720P video with native audio, optimized for rapid iteration and high-volume production

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.88
P50
649
ms
Uptime
99.80%
F
@fal/kling-video-video-to-audioT1
General

Generate audio from input videos using Kling

Price
0.000
cr/req
Uses
177
est.
Rep
0.90
P50
265
ms
Uptime
99.98%
F
@fal/kokoro-american-englishT1
General

Kokoro is a lightweight text-to-speech model that delivers comparable quality to larger models while being significantly faster and more cost-efficient.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.83
P50
348
ms
Uptime
99.91%
F
@fal/kokoro-brazilian-portugueseT1
General

A natural and expressive Brazilian Portuguese text-to-speech model optimized for clarity and fluency.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.97
P50
246
ms
Uptime
99.89%
F
@fal/kokoro-british-englishT1
General

A high-quality British English text-to-speech model offering natural and expressive voice synthesis.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.89
P50
493
ms
Uptime
99.97%
F
@fal/kokoro-frenchT1
General

An expressive and natural French text-to-speech model for both European and Canadian French.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.92
P50
216
ms
Uptime
99.82%
F
@fal/kokoro-hindiT1
General

A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.95
P50
427
ms
Uptime
99.94%
F
@fal/kokoro-italianT1
General

A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.92
P50
561
ms
Uptime
99.79%
F
@fal/kokoro-japaneseT1
General

A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.

Price
0.000
cr/req
Uses
382
est.
Rep
0.86
P50
180
ms
Uptime
99.77%
F
@fal/kokoro-mandarin-chineseT1
General

A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.97
P50
651
ms
Uptime
99.90%
F
@fal/kokoro-spanishT1
General

A natural-sounding Spanish text-to-speech model optimized for Latin American and European Spanish.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.85
P50
449
ms
Uptime
99.71%
F
@fal/kolorsT1
General

Photorealistic Text-to-Image

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.89
P50
194
ms
Uptime
99.75%
F
@fal/kolors-image-to-imageT1
General

Photorealistic Image-to-Image

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.88
P50
282
ms
Uptime
99.70%
F
@fal/krea-2-trainerT1
General

Train a custom LoRA on your own images to teach Krea 2 a new subject, character, or style. Provide a set of training images (and an optional trigger word), and the trainer outputs LoRA weights you can use for inference with the Krea 2 LoRA endpoint.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.85
P50
555
ms
Uptime
99.90%
F
@fal/krea-2-turboT1
General

Generate high-fidelity images from text in seconds with Krea 2 Turbo, the speed-optimized open-source version of Krea 2, preserving its aesthetic range for rapid ideation.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.95
P50
132
ms
Uptime
99.84%
F
@fal/krea-2-turbo-loraT1
General

Generate high-fidelity images from text with Krea 2 using a custom-trained LoRA. Apply your LoRA weights to carry a learned subject, character, or style into new generations, with aspect ratio, creativity, and seed controls.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.92
P50
528
ms
Uptime
99.77%
F
@fal/krea-2-turbo-styleT1
General

Generate high-fidelity images from text with Krea 2 using a style reference image. Apply a reference image to guide the visual style into new generations, with aspect ratio, creativity, and seed controls.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.83
P50
441
ms
Uptime
99.98%
F
@fal/krea-v2-large-text-to-imageT1
General

Generate high-fidelity images from text with Krea 2 Large, supporting aspect ratio, creativity, seed controls, and optional style references.

Price
0.000
cr/req
Uses
177
est.
Rep
0.86
P50
438
ms
Uptime
99.95%
F
@fal/krea-v2-medium-text-to-imageT1
General

Generate high-quality images from text with Krea 2 Medium, supporting aspect ratio, creativity controls, seeds, and optional style references.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.87
P50
408
ms
Uptime
99.93%
F
@fal/krea-v2-medium-turbo-text-to-imageT1
General

Generate high-fidelity images extremely fast from text with Krea 2 Medium Turbo, supporting aspect ratio, creativity, seed controls, and optional style references.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.96
P50
254
ms
Uptime
99.93%
F
@fal/krea-wan-14b-text-to-videoT1
General

Fast Text-to-Video endpoint for Krea's Wan 14b model.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.90
P50
193
ms
Uptime
99.76%
F
@fal/krea-wan-14b-video-to-videoT1
General

Superfast video model based on Wan 2.1 14b by Krea, excelling at real-time video-editing.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.85
P50
154
ms
Uptime
99.94%
F
@fal/latentsyncT1
General

LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.89
P50
422
ms
Uptime
99.97%
F
@fal/lcm-sd15-i2iT1
General

Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.92
P50
557
ms
Uptime
99.75%
F
@fal/leffa-pose-transferT1
General

Leffa Pose Transfer is an endpoint for changing pose of an image with a reference image.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.94
P50
575
ms
Uptime
99.89%
F
@fal/leffa-virtual-tryonT1
General

Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.87
P50
307
ms
Uptime
99.94%
F
@fal/lightx-recameraT1
General

Use the capabilities of lightx to relight and recamera your videos.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.89
P50
291
ms
Uptime
99.76%
F
@fal/lightx-relightT1
General

Use tlightx capabilities to relight and recamera your videos.

Price
0.000
cr/req
Uses
235
est.
Rep
0.90
P50
536
ms
Uptime
99.78%
F
@fal/live-portraitT1
General

Transfer expression from a video to a portrait.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.86
P50
306
ms
Uptime
99.73%
F
@fal/live-portrait-imageT1
General

Transfer expression from a video to a portrait.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.85
P50
513
ms
Uptime
99.85%
F
@fal/llava-nextT1
General

Vision

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.98
P50
166
ms
Uptime
99.92%
F
@fal/longcat-imageT1
General

LongCat image is a 6B parameter model excelling at multilingual text rendering, photorealism and deployment efficiency.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.90
P50
400
ms
Uptime
99.82%
F
@fal/longcat-image-editT1
General

LongCat image Edit is a 6B parameter image editing model excelling at multilingual text rendering, photorealism and deployment efficiency.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.91
P50
240
ms
Uptime
99.81%
F
@fal/longcat-single-avatar-audio-to-videoT1
General

LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.83
P50
470
ms
Uptime
99.87%
F
@fal/longcat-single-avatar-image-audio-to-videoT1
General

LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.97
P50
212
ms
Uptime
99.95%
F
@fal/longcat-video-distilled-image-to-video-480pT1
General

Generate long videos from images using LongCat Video Distilled

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.91
P50
161
ms
Uptime
99.73%
F
@fal/longcat-video-distilled-image-to-video-720pT1
General

Generate long videos in 720p/30fps from images using LongCat Video Distilled

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.87
P50
577
ms
Uptime
99.95%
F
@fal/longcat-video-distilled-text-to-video-480pT1
General

Generate long videos from text using LongCat Video Distilled

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.83
P50
555
ms
Uptime
99.75%
F
@fal/longcat-video-distilled-text-to-video-720pT1
General

Generate long videos in 720p/30fps from text using LongCat Video Distilled

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.87
P50
484
ms
Uptime
99.94%
F
@fal/longcat-video-image-to-video-480pT1
General

Generate long videos from images using LongCat Video

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.83
P50
310
ms
Uptime
99.99%
F
@fal/longcat-video-image-to-video-720pT1
General

Generate long videos in 720p/30fps from images using LongCat Video

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.93
P50
364
ms
Uptime
99.95%
F
@fal/longcat-video-text-to-video-480pT1
General

Generate long videos from text using LongCat Video

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.94
P50
650
ms
Uptime
99.96%
F
@fal/longcat-video-text-to-video-720pT1
General

Generate long videos in 720p/30fps from text using LongCat Video

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.91
P50
291
ms
Uptime
99.80%
F
@fal/loraT1
General

Run Any Stable Diffusion model with customizable LoRA weights.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.90
P50
459
ms
Uptime
99.79%
F
@fal/lora-image-to-imageT1
General

Run Any Stable Diffusion model with customizable LoRA weights.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.89
P50
379
ms
Uptime
99.93%
F
@fal/lora-inpaintT1
General

Run Any Stable Diffusion model with customizable LoRA weights.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.89
P50
252
ms
Uptime
99.97%
F
@fal/ltx-2-19b-audio-to-videoT1
General

Generate video with audio from audio, text and images using LTX-2

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.83
P50
479
ms
Uptime
99.94%
F
@fal/ltx-2-19b-audio-to-video-loraT1
General

Generate video with audio from audio, text and images using LTX-2 and custom LoRA

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.88
P50
379
ms
Uptime
99.82%
F
@fal/ltx-2-19b-distilled-audio-to-videoT1
General

Generate video with audio from audio, text and images using LTX-2 Distilled

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.94
P50
161
ms
Uptime
99.89%
F
@fal/ltx-2-19b-distilled-audio-to-video-loraT1
General

Generate video with audio from audio, text and images using LTX-2 Distilled and custom LoRA

Price
0.000
cr/req
Uses
469
est.
Rep
0.83
P50
618
ms
Uptime
99.93%
F
@fal/ltx-2-19b-distilled-extend-videoT1
General

Extend videos with audio using LTX-2 Distilled

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.87
P50
560
ms
Uptime
99.97%
F
@fal/ltx-2-19b-distilled-extend-video-loraT1
General

Extend videos with audio using LTX-2 Distilled and custom LoRA

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.96
P50
360
ms
Uptime
99.88%
F
@fal/ltx-2-19b-distilled-image-to-videoT1
General

Generate video with audio from images using LTX-2 Distilled

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.88
P50
438
ms
Uptime
99.78%
F
@fal/ltx-2-19b-distilled-image-to-video-loraT1
General

Generate video with audio from images using LTX-2 Distilled and custom LoRA

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.94
P50
553
ms
Uptime
99.89%
F
@fal/ltx-2-19b-distilled-text-to-videoT1
General

Generate video with audio from text using LTX-2 Distilled

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.92
P50
494
ms
Uptime
99.73%
F
@fal/ltx-2-19b-distilled-text-to-video-loraT1
General

Generate video with audio from text using LTX-2 Distilled and custom LoRA

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
163
ms
Uptime
99.95%
F
@fal/ltx-2-19b-distilled-video-to-videoT1
General

Generate video with audio from videos using LTX-2 Distilled

Price
0.000
cr/req
Uses
489
est.
Rep
0.94
P50
406
ms
Uptime
99.98%
F
@fal/ltx-2-19b-distilled-video-to-video-loraT1
General

Generate video with audio from videos using LTX-2 Distilled and custom LoRA

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.95
P50
140
ms
Uptime
99.86%
F
@fal/ltx-2-19b-extend-videoT1
General

Extend video with audio using LTX-2

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.93
P50
440
ms
Uptime
99.76%
F
@fal/ltx-2-19b-extend-video-loraT1
General

Extend video with audio using LTX-2 and custom LoRA

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.98
P50
297
ms
Uptime
99.81%
F
@fal/ltx-2-19b-image-to-videoT1
General

Generate video with audio from images using LTX-2

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.95
P50
377
ms
Uptime
99.71%
F
@fal/ltx-2-19b-image-to-video-loraT1
General

Generate video with audio from images using LTX-2 and custom LoRA

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.94
P50
532
ms
Uptime
99.90%
F
@fal/ltx-2-19b-text-to-videoT1
General

Generate video with audio from text using LTX-2

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.91
P50
519
ms
Uptime
99.98%
F
@fal/ltx-2-19b-text-to-video-loraT1
General

Generate video with audio from text using LTX-2 and custom LoRA

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.84
P50
184
ms
Uptime
99.94%
F
@fal/ltx-2-19b-video-to-videoT1
General

Generate video with audio from videos using LTX-2

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.87
P50
362
ms
Uptime
99.88%
F
@fal/ltx-2-19b-video-to-video-loraT1
General

Generate video with audio from videos using LTX-2 and custom LoRA

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.92
P50
498
ms
Uptime
99.75%
F
@fal/ltx-2-3-22b-audio-to-videoT1
General

Generate video with audio from audio, text and images using LTX-2

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.93
P50
153
ms
Uptime
99.79%
F
@fal/ltx-2-3-22b-audio-to-video-loraT1
General

Generate video with audio from audio, text and images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.82
P50
158
ms
Uptime
99.82%
F
@fal/ltx-2-3-22b-distilled-audio-to-videoT1
General

Generate video with audio from audio, text and images using LTX-2 Distilled

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.95
P50
293
ms
Uptime
99.81%
F
@fal/ltx-2-3-22b-distilled-audio-to-video-loraT1
General

Generate video with audio from audio, text and images using LTX-2.3 Distilled and custom LoRA

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.85
P50
526
ms
Uptime
99.81%
F
@fal/ltx-2-3-22b-distilled-image-to-videoT1
General

Generate video with audio from images using LTX-2.3 Distilled

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.96
P50
136
ms
Uptime
99.70%
F
@fal/ltx-2-3-22b-distilled-image-to-video-loraT1
General

Generate video with audio from images using LTX-2.3 Distilled and custom LoRA

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.89
P50
531
ms
Uptime
99.94%
F
@fal/ltx-2-3-22b-distilled-reference-video-to-videoT1
General

Generate video with audio from reference videos using LTX-2.3 Distilled

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.87
P50
382
ms
Uptime
99.88%
F
@fal/ltx-2-3-22b-distilled-reference-video-to-video-loraT1
General

Generate video with audio from reference videos using LTX-2.3 Distilled and custom LoRA

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.91
P50
565
ms
Uptime
99.95%
F
@fal/ltx-2-3-22b-distilled-text-to-videoT1
General

Generate video with audio from text using LTX-2.3 Distilled

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.92
P50
139
ms
Uptime
99.97%
F
@fal/ltx-2-3-22b-distilled-text-to-video-loraT1
General

Generate video with audio from text using LTX-2.3 Distilled and custom LoRA

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.92
P50
401
ms
Uptime
99.77%
F
@fal/ltx-2-3-22b-distilled-video-to-videoT1
General

Generate video with audio from videos using LTX-2.3 Distilled

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.87
P50
556
ms
Uptime
99.95%
F
@fal/ltx-2-3-22b-distilled-video-to-video-loraT1
General

Generate video with audio from videos using LTX-2.3 Distilled and custom LoRA

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.90
P50
447
ms
Uptime
99.87%
F
@fal/ltx-2-3-22b-extend-videoT1
General

Extend video with audio using LTX-2.3

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.84
P50
323
ms
Uptime
99.79%
F
@fal/ltx-2-3-22b-extend-video-loraT1
General

Extend video with audio using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.89
P50
189
ms
Uptime
99.90%
F
@fal/ltx-2-3-22b-image-to-videoT1
General

Generate video with audio from images using LTX-2.3

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.88
P50
447
ms
Uptime
99.72%
F
@fal/ltx-2-3-22b-image-to-video-loraT1
General

Generate video with audio from images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
499
est.
Rep
0.93
P50
612
ms
Uptime
99.98%
F
@fal/ltx-2-3-22b-reference-video-to-videoT1
General

Generate video with audio from reference video, text and images using LTX-2.3

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.96
P50
554
ms
Uptime
99.81%
F
@fal/ltx-2-3-22b-reference-video-to-video-loraT1
General

Generate video with audio from reference video, text and images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.92
P50
359
ms
Uptime
99.89%
F
@fal/ltx-2-3-22b-text-to-videoT1
General

Generate video with audio from text using LTX-2.3

Price
0.000
cr/req
Uses
284
est.
Rep
0.86
P50
260
ms
Uptime
99.86%
F
@fal/ltx-2-3-22b-text-to-video-loraT1
General

Generate video with audio from text using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.94
P50
431
ms
Uptime
99.92%
F
@fal/ltx-2-3-22b-video-to-videoT1
General

Generate video with audio from videos using LTX-2.3

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.93
P50
524
ms
Uptime
99.94%
F
@fal/ltx-2-3-22b-video-to-video-loraT1
General

Generate video with audio from videos using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.91
P50
435
ms
Uptime
99.73%
F
@fal/ltx-2-3-audio-to-videoT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.88
P50
143
ms
Uptime
99.87%
F
@fal/ltx-2-3-extend-videoT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.84
P50
226
ms
Uptime
99.86%
F
@fal/ltx-2-3-image-to-videoT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.94
P50
266
ms
Uptime
99.95%
F
@fal/ltx-2-3-image-to-video-fastT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.92
P50
578
ms
Uptime
99.80%
F
@fal/ltx-2-3-quality-audio-to-videoT1
General

Generate high-quality video with audio from audio, text and images using LTX-2.3

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.94
P50
562
ms
Uptime
99.81%
F
@fal/ltx-2-3-quality-audio-to-video-loraT1
General

Generate high-quality video with audio from audio, text and images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.94
P50
182
ms
Uptime
99.97%
F
@fal/ltx-2-3-quality-colorizationT1
General

Colorize high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.94
P50
178
ms
Uptime
99.72%
F
@fal/ltx-2-3-quality-cross-eyedT1
General

Cross-eyes for high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.94
P50
300
ms
Uptime
99.71%
F
@fal/ltx-2-3-quality-day-to-nightT1
General

Day to Night for high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
733
est.
Rep
0.87
P50
324
ms
Uptime
99.87%
F
@fal/ltx-2-3-quality-deblurT1
General

Deblur high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.92
P50
266
ms
Uptime
99.73%
F
@fal/ltx-2-3-quality-decompressionT1
General

Decompression / Denoise high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.87
P50
240
ms
Uptime
99.97%
F
@fal/ltx-2-3-quality-extend-videoT1
General

Extend high-quality video with audio from input video using LTX-2.3

Price
0.000
cr/req
Uses
938
est.
Rep
0.87
P50
236
ms
Uptime
99.95%
F
@fal/ltx-2-3-quality-extend-video-loraT1
General

Extend high-quality video with audio from input video using LTX-2.3 with Lora

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.88
P50
189
ms
Uptime
99.76%
F
@fal/ltx-2-3-quality-hdrT1
General

Generate HDR from reference video using LTX-2.3

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.83
P50
593
ms
Uptime
99.76%
F
@fal/ltx-2-3-quality-hdr-loraT1
General

Generate HDR from reference video using LTX-2.3 with lora

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.82
P50
575
ms
Uptime
99.89%
F
@fal/ltx-2-3-quality-image-to-videoT1
General

Generate high-quality video with audio from images using LTX-2.3

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.91
P50
502
ms
Uptime
99.73%
F
@fal/ltx-2-3-quality-image-to-video-loraT1
General

Generate high-quality video with audio from images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.89
P50
152
ms
Uptime
99.93%
F
@fal/ltx-2-3-quality-ingredientT1
General

Generate high-quality video with audio from reference, character sheet, storyboard using LTX-2.3

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.83
P50
546
ms
Uptime
99.92%
F
@fal/ltx-2-3-quality-inpaintT1
General

Inpaint high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.93
P50
617
ms
Uptime
99.70%
F
@fal/ltx-2-3-quality-inpaint-loraT1
General

Inpaint high-quality video using LTX-2.3 with lora

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.88
P50
214
ms
Uptime
99.90%
F
@fal/ltx-2-3-quality-instant-shaveT1
General

Instant shave high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.82
P50
226
ms
Uptime
99.91%
F
@fal/ltx-2-3-quality-outpaintT1
General

Outpaint high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.94
P50
165
ms
Uptime
99.92%
F
@fal/ltx-2-3-quality-outpaint-loraT1
General

Outpaint high-quality video using LTX-2.3 with Lora

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.97
P50
200
ms
Uptime
99.79%
F
@fal/ltx-2-3-quality-reference-video-to-videoT1
General

Generate high-quality video with audio from reference video, text and images using LTX-2.3

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.95
P50
541
ms
Uptime
99.80%
F
@fal/ltx-2-3-quality-reference-video-to-video-loraT1
General

Generate high-quality video with audio from reference video, text and images using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.96
P50
651
ms
Uptime
99.82%
F
@fal/ltx-2-3-quality-render-to-realT1
General

Transform your 3D video render into realistic using first frame with Ltx 2.3

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.94
P50
284
ms
Uptime
99.89%
F
@fal/ltx-2-3-quality-text-to-audioT1
General

Text to Audio high-quality using LTX-2.3

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.89
P50
616
ms
Uptime
99.96%
F
@fal/ltx-2-3-quality-text-to-audio-loraT1
General

Text to Audio high-quality using LTX-2.3 with Lora

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.91
P50
371
ms
Uptime
99.92%
F
@fal/ltx-2-3-quality-text-to-videoT1
General

Generate high-quality video with audio from text using LTX-2.3

Price
0.000
cr/req
Uses
40
est.
Rep
0.85
P50
378
ms
Uptime
99.71%
F
@fal/ltx-2-3-quality-text-to-video-loraT1
General

Generate high-quality video with audio from text using LTX-2.3 and custom LoRA

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.91
P50
418
ms
Uptime
99.76%
F
@fal/ltx-2-3-quality-water-simulationT1
General

Water Simulation transformation for high-quality video using LTX-2.3

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.96
P50
470
ms
Uptime
99.78%
F
@fal/ltx-2-3-reframeT1
General

LTX-2.3 Reframe converts your videos to any aspect ratio without destructive cropping. It intelligently recenters the original footage and generatively fills the newly exposed areas with content that seamlessly matches the scene, so the result looks like it was shot natively in the target format. Turn landscape footage into vertical 9:16 for social, square 1:1 for feeds, or anything in between. Supports videos up to 60 seconds, with 720p and 1080p outputs across 1:1, 4:5, 5:4, 9:16 and 16:9.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.93
P50
523
ms
Uptime
99.70%
F
@fal/ltx-2-3-retake-videoT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.94
P50
144
ms
Uptime
99.97%
F
@fal/ltx-2-3-text-to-videoT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.87
P50
454
ms
Uptime
99.96%
F
@fal/ltx-2-3-text-to-video-fastT1
General

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Price
0.000
cr/req
Uses
177
est.
Rep
0.83
P50
487
ms
Uptime
99.96%
F
@fal/ltx-2-audio-to-videoT1
General

Generate video from audio using LTX-2

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.94
P50
233
ms
Uptime
99.84%
F
@fal/ltx-2-extend-videoT1
General

Extends videos with audio using LTX-2

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.92
P50
506
ms
Uptime
99.94%
F
@fal/ltx-2-image-to-videoT1
General

Create high-fidelity video with audio from images with LTX-2 Pro

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.85
P50
619
ms
Uptime
99.83%
F
@fal/ltx-2-image-to-video-fastT1
General

Create high-fidelity video with audio from images with LTX-2 Fast

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.90
P50
460
ms
Uptime
99.97%
F
@fal/ltx-2-retake-videoT1
General

Change sections of a video using LTX-2

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.95
P50
136
ms
Uptime
99.79%
F
@fal/ltx-2-text-to-videoT1
General

Create high-fidelity video with audio from text with LTX-2 Pro.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.82
P50
656
ms
Uptime
99.70%
F
@fal/ltx-2-text-to-video-fastT1
General

Create high-fidelity video with audio from text with LTX-2 Fast

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.89
P50
333
ms
Uptime
99.96%
F
@fal/ltx-videoT1
General

Generate videos from prompts using LTX Video

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.89
P50
291
ms
Uptime
99.93%
F
@fal/ltx-video-13b-distilledT1
General

Generate videos from prompts using LTX Video-0.9.7 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.88
P50
455
ms
Uptime
99.78%
F
@fal/ltx-video-13b-distilled-extendT1
General

Extend videos using LTX Video-0.9.7 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
40
est.
Rep
0.85
P50
488
ms
Uptime
99.98%
F
@fal/ltx-video-13b-distilled-image-to-videoT1
General

Generate videos from prompts and images using LTX Video-0.9.7 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.96
P50
158
ms
Uptime
99.98%
F
@fal/ltx-video-13b-distilled-multiconditioningT1
General

Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.87
P50
417
ms
Uptime
99.78%
F
@fal/ltx-video-image-to-videoT1
General

Generate videos from images using LTX Video

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.95
P50
352
ms
Uptime
99.97%
F
@fal/ltx-video-v095T1
General

Generate videos from prompts using LTX Video-0.9.5

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.90
P50
274
ms
Uptime
99.97%
F
@fal/ltx-video-v095-extendT1
General

Generate videos from prompts and videos using LTX Video-0.9.5

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.94
P50
368
ms
Uptime
99.71%
F
@fal/ltx-video-v095-multiconditioningT1
General

Generate videos from prompts,images, and videos using LTX Video-0.9.5

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.97
P50
175
ms
Uptime
99.85%
F
@fal/ltx23-trainer-v2-a2aT1
General

Train a LoRA that transforms one audio clip into another, learning a reference→target mapping from paired audio examples.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.87
P50
569
ms
Uptime
99.77%
F
@fal/ltx23-trainer-v2-a2vT1
General

Train a LoRA that generates video from a start image plus a conditioning audio track, producing motion that matches the sound.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.94
P50
612
ms
Uptime
99.97%
F
@fal/ltx23-trainer-v2-audio-extend-prefixT1
General

Train a LoRA that continues an audio clip forward in time, generating the audio that follows a short clean prefix.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.93
P50
275
ms
Uptime
99.92%
F
@fal/ltx23-trainer-v2-audio-extend-suffixT1
General

Train a LoRA that generates the lead-in to an audio clip, extending audio backward in time from its ending.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.91
P50
401
ms
Uptime
99.75%
F
@fal/ltx23-trainer-v2-audio-inpaintT1
General

Train a LoRA that regenerates masked time spans of an audio clip while keeping the rest unchanged.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.94
P50
254
ms
Uptime
99.81%
F
@fal/ltx23-trainer-v2-av2avT1
General

Train a LoRA for a joint audio+video transformation, conditioned on a reference clip (its video and audio) to produce a matching target clip.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.97
P50
521
ms
Uptime
99.81%
F
@fal/ltx23-trainer-v2-av2av-maskedT1
General

Train a LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.98
P50
390
ms
Uptime
99.87%
F
@fal/ltx23-trainer-v2-extend-prefixT1
General

Train a LoRA that continues a video forward in time — supply an opening clip at inference and the model generates what comes next.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.87
P50
151
ms
Uptime
99.92%
F
@fal/ltx23-trainer-v2-extend-suffixT1
General

Train a LoRA that generates the lead-in to a video, extending a clip backward in time from its ending.

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.90
P50
122
ms
Uptime
99.80%
F
@fal/ltx23-trainer-v2-i2vT1
General

Fine-tune LTX 2.3 to animate a starting image — supply a still plus a prompt at inference and the model generates a video that begins from that frame.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.95
P50
591
ms
Uptime
99.99%
F
@fal/ltx23-trainer-v2-ic-lora-a2aT1
General

Train an IC-LoRA that transforms one audio clip into another, conditioned at inference on a reference audio clip.

Price
0.000
cr/req
Uses
186
est.
Rep
0.89
P50
290
ms
Uptime
99.99%
F
@fal/ltx23-trainer-v2-ic-lora-av2avT1
General

Train an IC-LoRA for a joint audio+video transformation, conditioned on a reference clip's video and audio to produce a matching target.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.86
P50
408
ms
Uptime
99.93%
F
@fal/ltx23-trainer-v2-ic-lora-av2av-maskedT1
General

Train an IC-LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.90
P50
468
ms
Uptime
99.89%
F
@fal/ltx23-trainer-v2-ic-lora-v2vT1
General

Train an IC-LoRA that learns a video-to-video transformation from paired before/after clips, conditioned at inference on a reference (control) video.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.90
P50
439
ms
Uptime
99.88%
F
@fal/ltx23-trainer-v2-ic-lora-v2v-maskedT1
General

Train an IC-LoRA that regenerates only the masked region of a video, guided by the kept pixels and a separate reference/control video.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.95
P50
630
ms
Uptime
99.89%
F
@fal/ltx23-trainer-v2-inpaintT1
General

Train a LoRA that regenerates a masked region of a video while keeping the rest unchanged, blending the new content with its surroundings.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.89
P50
623
ms
Uptime
99.85%
F
@fal/ltx23-trainer-v2-interpolateT1
General

Train a LoRA that generates the video between keyframes — supply first/last (and optional middle) frames at inference and the model fills the in-between motion.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.86
P50
497
ms
Uptime
99.81%
F
@fal/ltx23-trainer-v2-outpaintT1
General

Train a LoRA that expands the video frame outward, keeping an inner rectangle fixed and generating the surrounding region.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.87
P50
531
ms
Uptime
99.75%
F
@fal/ltx23-trainer-v2-t2aT1
General

Train a LoRA that generates audio from a text prompt — the audio counterpart of text-to-video — learning a sound or style from your clips.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.89
P50
573
ms
Uptime
99.82%
F
@fal/ltx23-trainer-v2-t2vT1
General

Fine-tune LTX 2.3 on your own clips to teach it a new subject, character, object, or visual style, then generate full videos from a text prompt.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.84
P50
450
ms
Uptime
99.83%
F
@fal/ltx23-trainer-v2-v2aT1
General

Train a LoRA that generates audio (foley / sound design) for a silent video, learning a soundtrack that matches the on-screen action.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.85
P50
437
ms
Uptime
99.77%
F
@fal/ltx23-trainer-v2-v2vT1
General

Train a LoRA that learns a video-to-video transformation from paired before/after clips, steered at inference by a reference (control) video.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.97
P50
461
ms
Uptime
99.90%
F
@fal/ltx23-trainer-v2-v2v-maskedT1
General

Train a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.90
P50
287
ms
Uptime
99.79%
F
@fal/ltx23-v2v-trainerT1
General

Train LTX-2.3 22B for video transformation or video-conditioned generation.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.96
P50
191
ms
Uptime
99.95%
F
@fal/ltx23-video-trainerT1
General

Train LTX-2.3 22B for custom styles and effects.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.85
P50
269
ms
Uptime
99.83%
F
@fal/ltxv-13b-098-distilledT1
General

Generate long videos from prompts using LTX Video-0.9.8 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.96
P50
271
ms
Uptime
99.82%
F
@fal/ltxv-13b-098-distilled-extendT1
General

Extend videos using LTX Video-0.9.8 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.82
P50
470
ms
Uptime
99.93%
F
@fal/ltxv-13b-098-distilled-image-to-videoT1
General

Generate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.91
P50
195
ms
Uptime
99.85%
F
@fal/ltxv-13b-098-distilled-multiconditioningT1
General

Generate long videos from prompts, images, and videos using LTX Video-0.9.8 13B Distilled and custom LoRA

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.94
P50
292
ms
Uptime
99.81%
F
@fal/luma-agent-ray-v3-2-image-to-videoT1
General

Luma Ray 3.2 animates a source image into cinematic motion guided by a text prompt, preserving the starting frame's look while controlling resolution, duration, and seamless looping.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.94
P50
161
ms
Uptime
99.75%
F
@fal/luma-agent-ray-v3-2-reframeT1
General

Luma Ray 3.2 reframes an existing video into a new aspect ratio guided by a text prompt, preserving the original footage frame-for-frame while controlling resolution and outpainting the surrounding canvas.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.89
P50
409
ms
Uptime
99.80%
F
@fal/luma-agent-ray-v3-2-text-to-videoT1
General

Luma Ray 3.2 generates cinematic video from a text prompt, with control over resolution, duration, and seamless looping, plus reference images to lock in subject and style.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.97
P50
225
ms
Uptime
99.73%
F
@fal/luma-agent-ray-v3-2-video-to-videoT1
General

Luma Ray 3.2 re-renders an existing video into new cinematic motion guided by a text prompt, preserving the source's look and movement while controlling resolution, duration, and HDR.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.85
P50
581
ms
Uptime
99.93%
F
@fal/luma-agent-uni-1-v1-editT1
General

Luma Uni-1 Edit reworks a source image from a text instruction, preserving the original composition while applying style changes and following optional reference images to steer the result.

Price
0.000
cr/req
Uses
821
est.
Rep
0.89
P50
569
ms
Uptime
99.74%
F
@fal/luma-agent-uni-1-v1-maxT1
General

Luma Uni-1 Max generates a single image at the model's highest fidelity, delivering richer detail and stronger prompt adherence than the base tier for hero-quality stills.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.82
P50
154
ms
Uptime
99.85%
F
@fal/luma-agent-uni-1-v1-max-editT1
General

Luma Uni-1 Max Edit applies text-guided edits to a source image at maximum fidelity, holding the original structure while honoring reference images for precise, high-detail revisions.

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.92
P50
397
ms
Uptime
99.82%
F
@fal/luma-agent-uni-1-v1-text-to-imageT1
General

Luma Uni-1 turns a text prompt into a single high-fidelity image, with control over aspect ratio and visual style, plus optional web-sourced and reference-image guidance for sharper grounding.

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.91
P50
249
ms
Uptime
99.95%
F
@fal/luma-dream-machine-ray-2T1
General

Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.92
P50
371
ms
Uptime
99.82%
F
@fal/luma-dream-machine-ray-2-flashT1
General

Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.93
P50
414
ms
Uptime
99.77%
F
@fal/luma-dream-machine-ray-2-flash-image-to-videoT1
General

Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.84
P50
438
ms
Uptime
99.73%
F
@fal/luma-dream-machine-ray-2-flash-modifyT1
General

Ray2 Flash Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.90
P50
144
ms
Uptime
99.93%
F
@fal/luma-dream-machine-ray-2-flash-reframeT1
General

Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.88
P50
519
ms
Uptime
99.88%
F
@fal/luma-dream-machine-ray-2-image-to-videoT1
General

Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.93
P50
182
ms
Uptime
99.77%
F
@fal/luma-dream-machine-ray-2-modifyT1
General

Ray2 Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.

Price
0.000
cr/req
Uses
811
est.
Rep
0.95
P50
237
ms
Uptime
99.72%
F
@fal/luma-dream-machine-ray-2-reframeT1
General

Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.93
P50
570
ms
Uptime
99.84%
F
@fal/luma-photonT1
General

Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.97
P50
326
ms
Uptime
99.95%
F
@fal/luma-photon-flashT1
General

Generate images from your prompts using Luma Photon Flash. Photon Flash is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.88
P50
362
ms
Uptime
99.91%
F
@fal/luma-photon-flash-modifyT1
General

Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Price
0.000
cr/req
Uses
264
est.
Rep
0.97
P50
293
ms
Uptime
99.83%
F
@fal/luma-photon-flash-reframeT1
General

This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched speed and quality for creators at a fraction of the cost.

Price
0.000
cr/req
Uses
577
est.
Rep
0.89
P50
578
ms
Uptime
99.84%
F
@fal/luma-photon-modifyT1
General

Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.98
P50
605
ms
Uptime
99.93%
F
@fal/luma-photon-reframeT1
General

Extend and reframe images with Luma Photon Reframe. This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched personalization and quality for creators at a fraction of the cost.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.95
P50
267
ms
Uptime
99.94%
F
@fal/lumina-image-v2T1
General

Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.97
P50
576
ms
Uptime
99.73%
F
@fal/lyria2T1
General

Lyria 2 is Google's latest music generation model, you can generate any type of music with this model.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.85
P50
643
ms
Uptime
99.97%
F
@fal/lyria3T1
General

Lyria 3 is most recent music model from Google

Price
0.000
cr/req
Uses
50
est.
Rep
0.93
P50
410
ms
Uptime
99.70%
F
@fal/lyria3-proT1
General

Lyria 3 Pro is the latest music model from Google

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.88
P50
295
ms
Uptime
99.84%
F
@fal/magi-distilledT1
General

MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.89
P50
641
ms
Uptime
99.96%
F
@fal/magi-distilled-extend-videoT1
General

MAGI-1 distilled extends videos faster with an exceptional understanding of physical interactions and prompts

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.83
P50
323
ms
Uptime
99.77%
F
@fal/magi-distilled-image-to-videoT1
General

MAGI-1 distilled generates videos faster from images with exceptional understanding of physical interactions and prompting

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.91
P50
544
ms
Uptime
99.90%
F
@fal/marlinT1
General

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.82
P50
445
ms
Uptime
99.83%
F
@fal/marlin-findT1
General

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?

Price
0.000
cr/req
Uses
450
est.
Rep
0.97
P50
318
ms
Uptime
99.89%
F
@fal/mayaT1
General

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.84
P50
631
ms
Uptime
99.96%
F
@fal/maya-batchT1
General

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.84
P50
378
ms
Uptime
99.89%
F
@fal/maya-streamT1
General

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.93
P50
144
ms
Uptime
99.75%
F
@fal/meshy-riggingT1
General

Rig humanoid 3D models from GLB URLs with Meshy, returning rigged GLB/FBX files plus basic animations.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.95
P50
128
ms
Uptime
99.70%
F
@fal/meshy-rigging-multi-animationT1
General

Meshy auto-rigs a humanoid 3D model fitting a skeleton and binding the mesh, then applies several motion presets from its animation library

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.83
P50
365
ms
Uptime
99.97%
F
@fal/meshy-v5-multi-image-to-3dT1
General

Meshy-5 multi image generates realistic and production ready 3D models from multiple images.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.86
P50
581
ms
Uptime
99.89%
F
@fal/meshy-v5-remeshT1
General

Meshy-5 remesh allows you to remesh and export existing 3D models into various formats

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.85
P50
428
ms
Uptime
99.86%
F
@fal/meshy-v5-retextureT1
General

Meshy-5 retexture applies new, high-quality textures to existing 3D models using either text prompts or reference images. It supports PBR material generation for realistic, production-ready results.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.86
P50
576
ms
Uptime
99.84%
F
@fal/meshy-v6-image-to-3dT1
General

Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.83
P50
487
ms
Uptime
99.73%
F
@fal/meshy-v6-multi-image-to-3dT1
General

Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.93
P50
245
ms
Uptime
99.74%
F
@fal/meshy-v6-preview-image-to-3dT1
General

Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.

Price
0.000
cr/req
Uses
928
est.
Rep
0.92
P50
384
ms
Uptime
99.95%
F
@fal/meshy-v6-preview-text-to-3dT1
General

Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.87
P50
340
ms
Uptime
99.90%
F
@fal/meshy-v6-text-to-3dT1
General

Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.94
P50
477
ms
Uptime
99.94%
F
@fal/microsoft-mai-image-2-5T1
General

MAI-Image-2.5 is Microsoft's photorealistic image generation and editing model that turns text prompts or uploaded images into high-quality, design-ready visuals with fine-grained, pixel-level control.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.89
P50
232
ms
Uptime
99.72%
F
@fal/microsoft-mai-image-2-5-editT1
General

MAI-Image-2.5 is Microsoft's photorealistic image generation and editing model that turns text prompts or uploaded images into high-quality, design-ready visuals with fine-grained, pixel-level control.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.86
P50
395
ms
Uptime
99.98%
F
@fal/minimax-hailuo-02-fast-image-to-videoT1
General

Create blazing fast and economical videos with MiniMax Hailuo-02 Image To Video API at 512p resolution

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.86
P50
497
ms
Uptime
99.99%
F
@fal/minimax-hailuo-02-pro-image-to-videoT1
General

MiniMax Hailuo-02 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.85
P50
421
ms
Uptime
99.75%
F
@fal/minimax-hailuo-02-pro-text-to-videoT1
General

MiniMax Hailuo-02 Text To Video API (Pro, 1080p): Advanced video generation model with 1080p resolution

Price
0.000
cr/req
Uses
372
est.
Rep
0.82
P50
508
ms
Uptime
99.74%
F
@fal/minimax-hailuo-02-standard-image-to-videoT1
General

MiniMax Hailuo-02 Image To Video API (Standard, 768p, 512p): Advanced image-to-video generation model with 768p and 512p resolutions

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.94
P50
148
ms
Uptime
99.94%
F
@fal/minimax-hailuo-02-standard-text-to-videoT1
General

MiniMax Hailuo-02 Text To Video API (Standard, 768p): Advanced video generation model with 768p resolution

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.94
P50
190
ms
Uptime
99.90%
F
@fal/minimax-hailuo-2-3-fast-pro-image-to-videoT1
General

MiniMax Hailuo-2.3-Fast Image To Video API (Pro, 1080p): Advanced fast image-to-video generation model with 1080p resolution

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.87
P50
155
ms
Uptime
99.92%
F
@fal/minimax-hailuo-2-3-fast-standard-image-to-videoT1
General

MiniMax Hailuo-2.3-Fast Image To Video API (Standard, 768p): Advanced fast image-to-video generation model with 768p resolution

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.93
P50
621
ms
Uptime
99.74%
F
@fal/minimax-hailuo-2-3-pro-image-to-videoT1
General

MiniMax Hailuo-2.3 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution

Price
0.000
cr/req
Uses
752
est.
Rep
0.87
P50
606
ms
Uptime
99.91%
F
@fal/minimax-hailuo-2-3-pro-text-to-videoT1
General

MiniMax Hailuo-2.3 Text To Video API (Pro, 1080p): Advanced text-to-video generation model with 1080p resolution

Price
0.000
cr/req
Uses
313
est.
Rep
0.88
P50
142
ms
Uptime
99.94%
F
@fal/minimax-hailuo-2-3-standard-image-to-videoT1
General

MiniMax Hailuo-2.3 Image To Video API (Standard, 768p): Advanced image-to-video generation model with 768p resolution

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.92
P50
566
ms
Uptime
99.87%
F
@fal/minimax-hailuo-2-3-standard-text-to-videoT1
General

MiniMax Hailuo-2.3 Text To Video API (Standard, 768p): Advanced text-to-video generation model with 768p resolution

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.87
P50
522
ms
Uptime
99.74%
F
@fal/minimax-image-01T1
General

Generate high quality images from text prompts using MiniMax Image-01. Longer text prompts will result in better quality images.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.93
P50
591
ms
Uptime
99.81%
F
@fal/minimax-image-01-subject-referenceT1
General

Generate images from text and a reference image using MiniMax Image-01 for consistent character appearance.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.94
P50
495
ms
Uptime
99.87%
F
@fal/minimax-musicT1
General

Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.85
P50
458
ms
Uptime
99.98%
F
@fal/minimax-music-v1-5T1
General

Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.96
P50
326
ms
Uptime
99.93%
F
@fal/minimax-music-v2T1
General

Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.

Price
0.000
cr/req
Uses
235
est.
Rep
0.98
P50
196
ms
Uptime
99.78%
F
@fal/minimax-music-v2-5T1
General

MiniMax Music 2.5 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.92
P50
485
ms
Uptime
99.78%
F
@fal/minimax-music-v2-6T1
General

MiniMax Music 2.6 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.97
P50
137
ms
Uptime
99.98%
F
@fal/minimax-preview-speech-2-5-hdT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.88
P50
138
ms
Uptime
99.83%
F
@fal/minimax-preview-speech-2-5-turboT1
General

Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
928
est.
Rep
0.94
P50
524
ms
Uptime
99.93%
F
@fal/minimax-speech-02-hdT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.94
P50
578
ms
Uptime
99.77%
F
@fal/minimax-speech-02-turboT1
General

Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
421
est.
Rep
0.85
P50
214
ms
Uptime
99.83%
F
@fal/minimax-speech-2-6-hdT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.94
P50
380
ms
Uptime
99.96%
F
@fal/minimax-speech-2-6-turboT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
655
est.
Rep
0.88
P50
468
ms
Uptime
99.99%
F
@fal/minimax-speech-2-8-hdT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.83
P50
323
ms
Uptime
99.91%
F
@fal/minimax-speech-2-8-turboT1
General

Generate speech from text prompts and different voices using the MiniMax Speech-2.8 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.89
P50
324
ms
Uptime
99.76%
F
@fal/minimax-video-01T1
General

Generate video clips from your prompts using MiniMax model

Price
0.000
cr/req
Uses
294
est.
Rep
0.94
P50
389
ms
Uptime
99.89%
F
@fal/minimax-video-01-directorT1
General

Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control.

Price
0.000
cr/req
Uses
694
est.
Rep
0.83
P50
420
ms
Uptime
99.77%
F
@fal/minimax-video-01-director-image-to-videoT1
General

Generate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.91
P50
616
ms
Uptime
99.74%
F
@fal/minimax-video-01-image-to-videoT1
General

Generate video clips from your images using MiniMax Video model

Price
0.000
cr/req
Uses
831
est.
Rep
0.97
P50
504
ms
Uptime
99.74%
F
@fal/minimax-video-01-liveT1
General

Generate video clips from your prompts using MiniMax model

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.95
P50
612
ms
Uptime
99.78%
F
@fal/minimax-video-01-live-image-to-videoT1
General

Generate video clips from your images using MiniMax Video model

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.95
P50
427
ms
Uptime
99.89%
F
@fal/minimax-video-01-subject-referenceT1
General

Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.91
P50
493
ms
Uptime
99.79%
F
@fal/minimax-voice-cloneT1
General

Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.97
P50
593
ms
Uptime
99.89%
F
@fal/minimax-voice-designT1
General

Design a personalized voice from a text description, and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.90
P50
586
ms
Uptime
99.85%
F
@fal/mirelo-ai-sfx-v1-5-video-to-audioT1
General

Generate synced sounds for any video, and return the new sound track (like MMAudio)

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.98
P50
524
ms
Uptime
99.74%
F
@fal/mirelo-ai-sfx-v1-5-video-to-videoT1
General

Generate synced sounds for any video, and return it with its new sound track (like MMAudio)

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.91
P50
468
ms
Uptime
99.75%
F
@fal/mirelo-ai-sfx-v1-video-to-audioT1
General

Generate synced sounds for any video, and return the new sound track (like MMAudio)

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.89
P50
620
ms
Uptime
99.83%
F
@fal/mirelo-ai-sfx-v1-video-to-videoT1
General

Generate synced sounds for any video, and return it with its new sound track (like MMAudio)

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.85
P50
125
ms
Uptime
99.83%
F
@fal/mirelo-ai-sfx1-6-extend-audioT1
General

Extend any sound effect with seamless, natural tails.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.94
P50
364
ms
Uptime
99.94%
F
@fal/mirelo-ai-sfx1-6-inpaint-audioT1
General

Erase and replace any moment in your audio with AI-driven precision.

Price
0.000
cr/req
Uses
840
est.
Rep
0.96
P50
638
ms
Uptime
99.78%
F
@fal/mirelo-ai-sfx1-6-text-to-audioT1
General

Generate ambient sounds for any text prompt. Now you can turn any SFX into a natural loop for ambient soundscapes.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.84
P50
285
ms
Uptime
99.96%
F
@fal/mirelo-ai-sfx1-6-video-to-videoT1
General

Generate synced sounds for any video, and return it with its new sound track (like MMAudio). Now up to 60 seconds!

Price
0.000
cr/req
Uses
723
est.
Rep
0.84
P50
513
ms
Uptime
99.84%
F
@fal/mmaudio-v2T1
General

MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.93
P50
566
ms
Uptime
99.75%
F
@fal/mmaudio-v2-text-to-audioT1
General

MMAudio generates synchronized audio given text inputs. It can generate sounds described by a prompt.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.87
P50
121
ms
Uptime
99.84%
F
@fal/moondream-batchedT1
General

Answer questions from the images.

Price
0.000
cr/req
Uses
430
est.
Rep
0.90
P50
156
ms
Uptime
99.87%
F
@fal/moondream-nextT1
General

MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.86
P50
134
ms
Uptime
99.71%
F
@fal/moondream-next-batchT1
General

MoonDreamNext Batch is a multimodal vision-language model for batch captioning.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.87
P50
539
ms
Uptime
99.97%
F
@fal/moondream-next-detectionT1
General

MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.97
P50
529
ms
Uptime
99.89%
F
@fal/moondream2T1
General

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
459
ms
Uptime
99.94%
F
@fal/moondream2-object-detectionT1
General

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.94
P50
431
ms
Uptime
99.75%
F
@fal/moondream2-point-object-detectionT1
General

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.91
P50
616
ms
Uptime
99.99%
F
@fal/moondream2-visual-queryT1
General

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.94
P50
554
ms
Uptime
99.87%
F
@fal/moondream3-preview-captionT1
General

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.94
P50
638
ms
Uptime
99.91%
F
@fal/moondream3-preview-detectT1
General

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Price
0.000
cr/req
Uses
499
est.
Rep
0.88
P50
610
ms
Uptime
99.70%
F
@fal/moondream3-preview-pointT1
General

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.91
P50
160
ms
Uptime
99.73%
F
@fal/moondream3-preview-queryT1
General

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.89
P50
384
ms
Uptime
99.86%
F
@fal/moondream3-preview-segmentT1
General

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.82
P50
440
ms
Uptime
99.91%
F
@fal/moonvalley-marey-i2vT1
General

Generate a video starting from an image as the first frame with Marey, a generative video model trained exclusively on fully licensed data.

Price
0.000
cr/req
Uses
577
est.
Rep
0.86
P50
547
ms
Uptime
99.85%
F
@fal/moonvalley-marey-motion-transferT1
General

Pull motion from a reference video and apply it to new subjects or scenes.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.97
P50
276
ms
Uptime
99.84%
F
@fal/moonvalley-marey-pose-transferT1
General

Ideal for matching human movement. Your input video determines human poses, gestures, and body movements that will appear in the generated video.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.92
P50
460
ms
Uptime
99.70%
F
@fal/moonvalley-marey-t2vT1
General

Generate a video from a text prompt with Marey, a generative video model trained exclusively on fully licensed data.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.84
P50
508
ms
Uptime
99.72%
F
@fal/musetalkT1
General

MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.92
P50
249
ms
Uptime
99.97%
F
@fal/nafnet-deblurT1
General

Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.

Price
0.000
cr/req
Uses
206
est.
Rep
0.82
P50
542
ms
Uptime
99.73%
F
@fal/nafnet-denoiseT1
General

Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.84
P50
412
ms
Uptime
99.87%
F
@fal/nano-bananaT1
General

Google's famous original image generation and editing model

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.92
P50
418
ms
Uptime
99.92%
F
@fal/nano-banana-2T1
General

Nano Banana 2 is Google's new state-of-the-art fast image generation and editing model

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.95
P50
549
ms
Uptime
99.74%
F
@fal/nano-banana-2-editT1
General

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.89
P50
240
ms
Uptime
99.74%
F
@fal/nano-banana-editT1
General

Google's famous original image generation and editing model

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.98
P50
221
ms
Uptime
99.90%
F
@fal/nano-banana-proT1
General

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.86
P50
573
ms
Uptime
99.88%
F
@fal/nano-banana-pro-editT1
General

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.89
P50
485
ms
Uptime
99.86%
F
@fal/nemotron-diffusion-vlmT1
General

Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.

Price
0.000
cr/req
Uses
899
est.
Rep
0.90
P50
649
ms
Uptime
99.90%
F
@fal/nucleus-imageT1
General

Nucleus-Image is a text-to-image generation model built on a sparse mixture-of-experts (MoE) diffusion transformer architecture.

Price
0.000
cr/req
Uses
645
est.
Rep
0.96
P50
529
ms
Uptime
99.97%
F
@fal/nvidia-cosmos-3-super-image-to-videoT1
General

Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.88
P50
384
ms
Uptime
99.82%
F
@fal/nvidia-cosmos-3-super-text-to-imageT1
General

Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.97
P50
238
ms
Uptime
99.71%
F
@fal/nvidia-nemotron-3-nano-omniT1
General

Open, efficient reasoning model from NVIDIA. 30B A3B hybrid Transformer-Mamba MoE, built for enterprise agentic workflows.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.87
P50
374
ms
Uptime
99.72%
F
@fal/nvidia-nemotron-3-nano-omni-audioT1
General

Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts audio plus a prompt and returns text.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.94
P50
478
ms
Uptime
99.74%
F
@fal/nvidia-nemotron-3-nano-omni-videoT1
General

Video reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts video plus a prompt and returns text.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.96
P50
263
ms
Uptime
99.90%
F
@fal/nvidia-nemotron-3-nano-omni-visionT1
General

Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts an image plus a prompt and returns text.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.85
P50
134
ms
Uptime
99.97%
F
@fal/nvidia-nemotron-asr-multilingual-asrT1
General

Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual transcription across both low-latency streaming and high-throughput batch workloads.

Price
0.000
cr/req
Uses
967
est.
Rep
0.83
P50
479
ms
Uptime
99.72%
F
@fal/object-removalT1
General

Removes objects and their visual effects using natural language, replacing them with contextually appropriate content

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.95
P50
360
ms
Uptime
99.91%
F
@fal/object-removal-bboxT1
General

Removes box-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.85
P50
412
ms
Uptime
99.88%
F
@fal/object-removal-maskT1
General

Removes mask-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.82
P50
238
ms
Uptime
99.97%
F
@fal/omni-zeroT1
General

Any pose, any style, any identity

Price
0.000
cr/req
Uses
938
est.
Rep
0.86
P50
527
ms
Uptime
99.94%
F
@fal/omnigen-v1T1
General

OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.87
P50
417
ms
Uptime
99.87%
F
@fal/omnigen-v2T1
General

OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.96
P50
381
ms
Uptime
99.73%
F
@fal/omnilottieT1
General

Convert your assets into lottie using Omnilottie.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.84
P50
593
ms
Uptime
99.82%
F
@fal/omnilottie-image-to-lottieT1
General

Convert your assets into lottie using Omnilottie.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.92
P50
161
ms
Uptime
99.90%
F
@fal/omnilottie-video-to-lottieT1
General

Convert your assets into lottie using Omnilottie.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.87
P50
399
ms
Uptime
99.81%
F
@fal/one-to-all-animation-1-3bT1
General

One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.83
P50
373
ms
Uptime
99.88%
F
@fal/one-to-all-animation-14bT1
General

One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.93
P50
284
ms
Uptime
99.76%
F
@fal/openai-gpt-image-2T1
General

GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.95
P50
317
ms
Uptime
99.82%
F
@fal/openai-gpt-image-2-editT1
General

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.96
P50
276
ms
Uptime
99.71%
F
@fal/openrouter-routerT1
General

Run any LLM with fal. Access Claude (Anthropic), ChatGPT / GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), DeepSeek, Llama (Meta), Qwen (Alibaba), Mistral, and 200+ more models through a single API. Supports reasoning, structured output, and streaming. Powered by OpenRouter.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.86
P50
500
ms
Uptime
99.92%
F
@fal/openrouter-router-audioT1
General

Run any audio capable LLM with fal. Process audio files — transcription, analysis, understanding, understand— using Gemini (Google) models. Supports wav, mp3, aiff, aac, ogg, flac, m4a. Powered by OpenRouter.

Price
0.000
cr/req
Uses
635
est.
Rep
0.94
P50
621
ms
Uptime
99.96%
F
@fal/openrouter-router-enterpriseT1
General

Run any LLM (Large Language Model) with fal, powered by OpenRouter.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.96
P50
436
ms
Uptime
99.77%
F
@fal/openrouter-router-openai-v1-chat-completionsT1
General

OpenAI-compatible chat completions API. Drop-in replacement for the OpenAI API — use any OpenAI SDK or client to access Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral, and all OpenAI models (GPT-5, GPT-4o, o3) through fal. Powered by OpenRouter.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.88
P50
125
ms
Uptime
99.95%
F
@fal/openrouter-router-openai-v1-embeddingsT1
General

Generate text embeddings using OpenAI-compatible API. Access embedding models like text-embedding-3-small, text-embedding-3-large (OpenAI), and other embedding models available through OpenRouter. Drop-in replacement for the OpenAI embeddings API. Powered by OpenRouter.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.91
P50
299
ms
Uptime
99.84%
F
@fal/openrouter-router-openai-v1-responsesT1
General

The OpenRouter Responses API with fal, powered by OpenRouter, provides unified access to a wide range of large language models - including GPT, Claude, Gemini, and many others through a single API interface.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.88
P50
164
ms
Uptime
99.83%
F
@fal/openrouter-router-videoT1
General

Run any video-capable LLM with fal. Analyze, summarize, and understand video files using Gemini (Google) models. Supports mp4, mpeg, mov, webm, and YouTube links. Powered by OpenRouter.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.91
P50
152
ms
Uptime
99.89%
F
@fal/openrouter-router-video-enterpriseT1
General

Run any VLM (Video Language Model) with fal, powered by OpenRouter.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.89
P50
354
ms
Uptime
99.91%
F
@fal/openrouter-router-visionT1
General

Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter.

Price
0.000
cr/req
Uses
372
est.
Rep
0.87
P50
547
ms
Uptime
99.76%
F
@fal/orpheus-ttsT1
General

Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.91
P50
616
ms
Uptime
99.90%
F
@fal/oviT1
General

A unified paradigm for audio-video generation

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.85
P50
504
ms
Uptime
99.73%
F
@fal/ovi-image-to-videoT1
General

Ovi can generate videos with audio from image and text inputs.

Price
0.000
cr/req
Uses
304
est.
Rep
0.84
P50
217
ms
Uptime
99.93%
F
@fal/ovis-imageT1
General

Ovis-Image is a 7B text-to-image model specifically optimized for quick, high quality text rendering.

Price
0.000
cr/req
Uses
469
est.
Rep
0.95
P50
266
ms
Uptime
99.94%
F
@fal/pasdT1
General

Pixel-Aware Diffusion Model for Realistic Image Super-Resolution and Personalized Stylization

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.86
P50
164
ms
Uptime
99.79%
F
@fal/patinaT1
General

PATINA creates seamless high-resolution normal, roughness, basecolor (albedo), height (displacement) and metalness maps from images

Price
0.000
cr/req
Uses
274
est.
Rep
0.87
P50
378
ms
Uptime
99.86%
F
@fal/patina-materialT1
General

Generate complete seamlessly tiling PBR materials including normal, roughness, basecolor, height and metalness maps up to 8K

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.93
P50
591
ms
Uptime
99.96%
F
@fal/patina-material-extractT1
General

Extract seamless tiling textures with PBR attribute maps from images

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.84
P50
386
ms
Uptime
99.78%
F
@fal/perceptron-isaac-01T1
General

Isaac-01 is a multimodal vision-language model from Perceptron for various vision language tasks.

Price
0.000
cr/req
Uses
206
est.
Rep
0.84
P50
547
ms
Uptime
99.73%
F
@fal/perceptron-isaac-01-openai-v1-chat-completionsT1
General

OpenAI spec compatible endpoint of Isaac-01 which is a multimodal vision-language model from Perceptron for various vision language tasks.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.97
P50
166
ms
Uptime
99.96%
F
@fal/personaplexT1
General

PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.84
P50
597
ms
Uptime
99.99%
F
@fal/personaplex-realtimeT1
General

PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.86
P50
273
ms
Uptime
99.73%
F
@fal/photaT1
General

Phota's model empowers developers, photographers, and creators with personalized photograph generation and editing.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.85
P50
594
ms
Uptime
99.79%
F
@fal/phota-create-profileT1
General

Generate profiles using 30-50 images of a subject with Phota.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.89
P50
308
ms
Uptime
99.96%
F
@fal/phota-editT1
General

Phota's model enables personalized photo editing, preserving identity while erasing distractions seamlessly.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.97
P50
651
ms
Uptime
99.85%
F
@fal/phota-enhanceT1
General

Enhance images while preserving identities with Phota

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.85
P50
303
ms
Uptime
99.97%
F
@fal/photomakerT1
General

Customizing Realistic Human Photos via Stacked ID Embedding

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.83
P50
277
ms
Uptime
99.80%
F
@fal/pika-v2-1-image-to-videoT1
General

Turn photos into mind-blowing, dynamic videos. Your images can can come to life with sharp details, impressive character control and cinematic camera moves.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.90
P50
148
ms
Uptime
99.79%
F
@fal/pika-v2-1-text-to-videoT1
General

Start with a simple text input to create dynamic generations that defy expectations. Anything you dream can come to life with sharp details, impressive character control and cinematic camera moves.

Price
0.000
cr/req
Uses
245
est.
Rep
0.85
P50
483
ms
Uptime
99.81%
F
@fal/pika-v2-2-image-to-videoT1
General

Turn photos into mind-blowing, dynamic videos in up to 1080p. Experience better image clarity and crisper, sharper visuals.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.94
P50
368
ms
Uptime
99.86%
F
@fal/pika-v2-2-pikaframesT1
General

Discover ultimate control with Pikaframes key frame interpolation, a stunning image-to-video feature that allows you to upload up to 5 keyframes, customize their transition length and prompt, and see their images come to life as seamless videos.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.96
P50
246
ms
Uptime
99.76%
F
@fal/pika-v2-2-pikascenesT1
General

Pika Scenes v2.2 creates videos from a images with high quality output.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.85
P50
193
ms
Uptime
99.80%
F
@fal/pika-v2-2-text-to-videoT1
General

Start with a simple text input to create dynamic generations that defy expectations in up to 1080p. Experience better image clarity and crisper, sharper visuals.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.97
P50
470
ms
Uptime
99.78%
F
@fal/pika-v2-turbo-image-to-videoT1
General

Turbo is the model to use when you feel the need for speed. Turn your image to stunning video up to 3x faster – all with high quality outputs.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.91
P50
257
ms
Uptime
99.90%
F
@fal/pika-v2-turbo-text-to-videoT1
General

Pika v2 Turbo creates videos from a text prompt with high quality output.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.83
P50
458
ms
Uptime
99.72%
F
@fal/pixal3dT1
General

Pixal3D turns a single image into a high-fidelity 3D model with detailed geometry and realistic textures.

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.85
P50
192
ms
Uptime
99.77%
F
@fal/pixart-sigmaT1
General

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.97
P50
609
ms
Uptime
99.77%
F
@fal/pixelcut-background-removalT1
General

Pixelcut’s Background Remover enables fast, ultra high-quality removal of backgrounds from images. Perfect for e-commerce and image editing workflows. Powered by advanced AI for clean, perfect cutouts every time.

Price
0.000
cr/req
Uses
606
est.
Rep
0.87
P50
261
ms
Uptime
99.91%
F
@fal/pixelcut-video-background-removalT1
General

Pixelcut's Video Background Remover is an AI segmentation model that erases backgrounds frame by frame, with seamless temporal consistency.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.87
P50
151
ms
Uptime
99.70%
F
@fal/pixverse-c1-image-to-videoT1
General

Animate images into cinematic videos with PixVerse C1, supporting 1080p resolution and native audio generation.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.92
P50
341
ms
Uptime
99.71%
F
@fal/pixverse-c1-reference-to-videoT1
General

Generate character-consistent videos from reference images using PixVerse C1, with subject and background references.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.97
P50
368
ms
Uptime
99.94%
F
@fal/pixverse-c1-text-to-videoT1
General

Generate film-grade videos from text prompts with native audio, up to 1080p and 15 seconds, using PixVerse C1.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.83
P50
137
ms
Uptime
99.94%
F
@fal/pixverse-c1-transitionT1
General

Create seamless cinematic transitions between two images with PixVerse C1, with native audio and up to 1080p.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.84
P50
652
ms
Uptime
99.94%
F
@fal/pixverse-extendT1
General

PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.93
P50
414
ms
Uptime
99.96%
F
@fal/pixverse-extend-fastT1
General

PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques

Price
0.000
cr/req
Uses
684
est.
Rep
0.92
P50
341
ms
Uptime
99.78%
F
@fal/pixverse-lipsyncT1
General

Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with PixVerse Lipsync model

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.86
P50
307
ms
Uptime
99.77%
F
@fal/pixverse-sound-effectsT1
General

Add immersive sound effects and background music to your videos using PixVerse sound effects generation

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.89
P50
371
ms
Uptime
99.85%
F
@fal/pixverse-swapT1
General

Generate high quality video clips by swapping person, objects and background using Pixverse Swap.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.98
P50
441
ms
Uptime
99.80%
F
@fal/pixverse-v3-5-effectsT1
General

Generate high quality video clips with different effects using PixVerse v3.5

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.87
P50
311
ms
Uptime
99.96%
F
@fal/pixverse-v3-5-image-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v3.5

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.93
P50
380
ms
Uptime
99.95%
F
@fal/pixverse-v3-5-image-to-video-fastT1
General

Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.95
P50
583
ms
Uptime
99.96%
F
@fal/pixverse-v3-5-text-to-videoT1
General

Generate high quality video clips from text prompts using PixVerse v3.5

Price
0.000
cr/req
Uses
99
est.
Rep
0.92
P50
414
ms
Uptime
99.79%
F
@fal/pixverse-v3-5-text-to-video-fastT1
General

Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.83
P50
179
ms
Uptime
99.93%
F
@fal/pixverse-v3-5-transitionT1
General

Create seamless transition between images using PixVerse v3.5

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.94
P50
292
ms
Uptime
99.90%
F
@fal/pixverse-v4-5-effectsT1
General

Generate high quality video clips with different effects using PixVerse v4.5

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.89
P50
164
ms
Uptime
99.84%
F
@fal/pixverse-v4-5-image-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v4.5

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.83
P50
373
ms
Uptime
99.72%
F
@fal/pixverse-v4-5-image-to-video-fastT1
General

Generate fast high quality video clips from text and image prompts using PixVerse v4.5

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.89
P50
139
ms
Uptime
99.89%
F
@fal/pixverse-v4-5-text-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v4.5

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.94
P50
148
ms
Uptime
99.97%
F
@fal/pixverse-v4-5-text-to-video-fastT1
General

Generate high quality and fast video clips from text and image prompts using PixVerse v4.5 fast

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.88
P50
341
ms
Uptime
99.75%
F
@fal/pixverse-v4-5-transitionT1
General

Create seamless transition between images using PixVerse v4.5

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.84
P50
614
ms
Uptime
99.97%
F
@fal/pixverse-v4-effectsT1
General

Generate high quality video clips with different effects using PixVerse v4

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.89
P50
548
ms
Uptime
99.90%
F
@fal/pixverse-v4-image-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v4

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.98
P50
609
ms
Uptime
99.92%
F
@fal/pixverse-v4-image-to-video-fastT1
General

Generate fast high quality video clips from text and image prompts using PixVerse v4

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.88
P50
181
ms
Uptime
99.72%
F
@fal/pixverse-v4-text-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v4

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.95
P50
575
ms
Uptime
99.92%
F
@fal/pixverse-v4-text-to-video-fastT1
General

Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.94
P50
630
ms
Uptime
99.78%
F
@fal/pixverse-v5-5-effectsT1
General

Pixverse Effects

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.92
P50
229
ms
Uptime
99.91%
F
@fal/pixverse-v5-5-image-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v5.5

Price
0.000
cr/req
Uses
704
est.
Rep
0.93
P50
279
ms
Uptime
99.81%
F
@fal/pixverse-v5-5-text-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v5.5

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.89
P50
599
ms
Uptime
99.73%
F
@fal/pixverse-v5-5-transitionT1
General

Pixverse Transition

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.86
P50
155
ms
Uptime
99.89%
F
@fal/pixverse-v5-6-image-to-videoT1
General

Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.87
P50
446
ms
Uptime
99.79%
F
@fal/pixverse-v5-6-text-to-videoT1
General

Use the latest pixverse v5.6 model to turn your texts into amazing videos.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.92
P50
342
ms
Uptime
99.94%
F
@fal/pixverse-v5-6-transitionT1
General

Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.94
P50
512
ms
Uptime
99.98%
F
@fal/pixverse-v5-effectsT1
General

Generate high quality video clips with different effects using PixVerse v5

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.89
P50
353
ms
Uptime
99.77%
F
@fal/pixverse-v5-image-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v5

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.96
P50
490
ms
Uptime
99.93%
F
@fal/pixverse-v5-text-to-videoT1
General

Generate high quality video clips from text and image prompts using PixVerse v5

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.86
P50
176
ms
Uptime
99.92%
F
@fal/pixverse-v5-transitionT1
General

Create seamless transition between images using PixVerse v5

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.94
P50
220
ms
Uptime
99.82%
F
@fal/pixverse-v6-extendT1
General

Pixverse's latest v6 Model.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.96
P50
187
ms
Uptime
99.98%
F
@fal/pixverse-v6-image-to-videoT1
General

Pixverse's latest V6 Model

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.97
P50
242
ms
Uptime
99.98%
F
@fal/pixverse-v6-text-to-videoT1
General

Pixverse's latest v6 Model.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.96
P50
410
ms
Uptime
99.77%
F
@fal/pixverse-v6-transitionT1
General

Pixverse's latest v6 Model.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.94
P50
191
ms
Uptime
99.79%
F
@fal/playground-v25T1
General

State-of-the-art open-source model in aesthetic quality

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.86
P50
429
ms
Uptime
99.71%
F
@fal/playground-v25-image-to-imageT1
General

State-of-the-art open-source model in aesthetic quality

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.88
P50
168
ms
Uptime
99.80%
F
@fal/playground-v25-inpaintingT1
General

State-of-the-art open-source model in aesthetic quality

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.98
P50
340
ms
Uptime
99.82%
F
@fal/pony-v7T1
General

Pony V7 is a finetuned text to image for superior aesthetics and prompt following.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.94
P50
516
ms
Uptime
99.75%
F
@fal/post-processingT1
General

Post Processing is an endpoint that can enhance images using a variety of techniques including grain, blur, sharpen, and more.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.95
P50
621
ms
Uptime
99.98%
F
@fal/post-processing-blurT1
General

Apply Gaussian or Kuwahara blur effects with adjustable radius and sigma parameters

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.85
P50
551
ms
Uptime
99.83%
F
@fal/post-processing-chromatic-aberrationT1
General

Create chromatic aberration by shifting red, green, and blue channels horizontally or vertically with customizable shift amounts.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.92
P50
528
ms
Uptime
99.82%
F
@fal/post-processing-color-correctionT1
General

Adjust color temperature, brightness, contrast, saturation, and gamma values for color correction.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.85
P50
171
ms
Uptime
99.74%
F
@fal/post-processing-color-tintT1
General

Apply various color tints (sepia, red, green, blue, cyan, magenta, yellow, purple, orange, warm, cool, lime, navy, vintage, rose, teal, maroon, peach, lavender, olive) with adjustable strength.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.93
P50
300
ms
Uptime
99.97%
F
@fal/post-processing-desaturateT1
General

Reduce color saturation using different methods (luminance Rec.709, luminance Rec.601, average, lightness) with adjustable factor.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.88
P50
391
ms
Uptime
99.89%
F
@fal/post-processing-dissolveT1
General

Blend two images together using smooth linear interpolation with a configurable blend factor.

Price
0.000
cr/req
Uses
294
est.
Rep
0.93
P50
460
ms
Uptime
99.89%
F
@fal/post-processing-dodge-burnT1
General

Apply dodge and burn effects with multiple modes and adjustable intensity.

Price
0.000
cr/req
Uses
460
est.
Rep
0.87
P50
236
ms
Uptime
99.91%
F
@fal/post-processing-grainT1
General

Apply film grain effect with different styles (modern, analog, kodak, fuji, cinematic, newspaper) and customizable intensity and scale

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.86
P50
450
ms
Uptime
99.85%
F
@fal/post-processing-parabolizeT1
General

Apply a parabolic distortion effect with configurable coefficient and vertex position.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.89
P50
282
ms
Uptime
99.95%
F
@fal/post-processing-sharpenT1
General

Apply sharpening effects with three modes: basic unsharp mask, smart sharpening with edge preservation, and Contrast Adaptive Sharpening (CAS).

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.85
P50
155
ms
Uptime
99.79%
F
@fal/post-processing-solarizeT1
General

Apply solarization effect by inverting pixel values above a threshold

Price
0.000
cr/req
Uses
450
est.
Rep
0.96
P50
596
ms
Uptime
99.89%
F
@fal/post-processing-vignetteT1
General

Add a darkening vignette effect around the edges of the image with adjustable strength

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.90
P50
325
ms
Uptime
99.78%
F
@fal/pulidT1
General

Tuning-free ID customization.

Price
0.000
cr/req
Uses
879
est.
Rep
0.82
P50
323
ms
Uptime
99.85%
F
@fal/qwen-3-tts-clone-voice-0-6bT1
General

Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.93
P50
207
ms
Uptime
99.95%
F
@fal/qwen-3-tts-clone-voice-1-7bT1
General

Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.96
P50
339
ms
Uptime
99.92%
F
@fal/qwen-3-tts-text-to-speech-0-6bT1
General

Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.96
P50
175
ms
Uptime
99.72%
F
@fal/qwen-3-tts-text-to-speech-1-7bT1
General

Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.91
P50
405
ms
Uptime
99.78%
F
@fal/qwen-3-tts-voice-design-1-7bT1
General

Create custom voices using Qwen3-TTS Voice Design model and later use Clone Voice model to create your own voices!

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.98
P50
254
ms
Uptime
99.87%
F
@fal/qwen-imageT1
General

Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.83
P50
158
ms
Uptime
99.79%
F
@fal/qwen-image-2-editT1
General

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.92
P50
443
ms
Uptime
99.89%
F
@fal/qwen-image-2-pro-editT1
General

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.89
P50
611
ms
Uptime
99.98%
F
@fal/qwen-image-2-pro-text-to-imageT1
General

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.82
P50
648
ms
Uptime
99.90%
F
@fal/qwen-image-2-text-to-imageT1
General

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.85
P50
513
ms
Uptime
99.76%
F
@fal/qwen-image-2512T1
General

Qwen Image 2512 is an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.84
P50
289
ms
Uptime
99.84%
F
@fal/qwen-image-2512-loraT1
General

LoRA inference endpoint for Qwen Image 2512, an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.95
P50
604
ms
Uptime
99.77%
F
@fal/qwen-image-2512-trainerT1
General

Qwen Image 2512 LoRA training

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.95
P50
445
ms
Uptime
99.87%
F
@fal/qwen-image-editT1
General

Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.92
P50
206
ms
Uptime
99.91%
F
@fal/qwen-image-edit-2509T1
General

Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.84
P50
311
ms
Uptime
99.70%
F
@fal/qwen-image-edit-2509-loraT1
General

LoRA endpoint for the Qwen Image Edit 2509 model.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.84
P50
622
ms
Uptime
99.94%
F
@fal/qwen-image-edit-2509-lora-gallery-add-backgroundT1
General

Add a realistic scene behind the object with white background

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.85
P50
298
ms
Uptime
99.82%
F
@fal/qwen-image-edit-2509-lora-gallery-face-to-full-portraitT1
General

Generate full portrait from a cropped face photo

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.84
P50
470
ms
Uptime
99.75%
F
@fal/qwen-image-edit-2509-lora-gallery-group-photoT1
General

Create group photos

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.85
P50
458
ms
Uptime
99.83%
F
@fal/qwen-image-edit-2509-lora-gallery-integrate-productT1
General

Blend products into backgrounds with automatic perspective and lighting correction

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.82
P50
609
ms
Uptime
99.71%
F
@fal/qwen-image-edit-2509-lora-gallery-lighting-restorationT1
General

Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.91
P50
654
ms
Uptime
99.98%
F
@fal/qwen-image-edit-2509-lora-gallery-multiple-anglesT1
General

Precise camera position and angle control (rotation, zoom, vertical movement)

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.97
P50
297
ms
Uptime
99.87%
F
@fal/qwen-image-edit-2509-lora-gallery-next-sceneT1
General

Create cinematic transitions and scene progressions (camera movements, framing changes)

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.85
P50
260
ms
Uptime
99.78%
F
@fal/qwen-image-edit-2509-lora-gallery-remove-elementT1
General

Remove unwanted elements (objects, people, text) while maintaining image consistency

Price
0.000
cr/req
Uses
89
est.
Rep
0.93
P50
397
ms
Uptime
99.80%
F
@fal/qwen-image-edit-2509-lora-gallery-remove-lightingT1
General

Remove existing lighting and apply soft, even illumination

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.97
P50
301
ms
Uptime
99.91%
F
@fal/qwen-image-edit-2509-lora-gallery-shirt-designT1
General

Apply designs/graphics onto people's shirts

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.87
P50
341
ms
Uptime
99.94%
F
@fal/qwen-image-edit-2509-trainerT1
General

LoRA trainer for Qwen Image Edit 2509

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.88
P50
607
ms
Uptime
99.73%
F
@fal/qwen-image-edit-2511T1
General

Endpoint for Qwen's Image Editing 2511 model.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.97
P50
508
ms
Uptime
99.82%
F
@fal/qwen-image-edit-2511-loraT1
General

Endpoint for Qwen's Image Editing 2511 model with LoRa support.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.90
P50
274
ms
Uptime
99.98%
F
@fal/qwen-image-edit-2511-multiple-anglesT1
General

Generates same scene from different angles (azimuth/elevation) with Qwen image Edit 2511 and the Lora Multiple Angles

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.89
P50
518
ms
Uptime
99.85%
F
@fal/qwen-image-edit-image-to-imageT1
General

Image to Image Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.85
P50
614
ms
Uptime
99.88%
F
@fal/qwen-image-edit-inpaintT1
General

Inpainting Endpoint for the Qwen Edit Image editing model.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.86
P50
290
ms
Uptime
99.94%
F
@fal/qwen-image-edit-loraT1
General

LoRA inference endpoint for the Qwen Image Editing model.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.97
P50
162
ms
Uptime
99.90%
F
@fal/qwen-image-edit-plusT1
General

Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.93
P50
452
ms
Uptime
99.83%
F
@fal/qwen-image-edit-plus-loraT1
General

LoRA endpoint for the Qwen Image Edit Plus model.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.92
P50
641
ms
Uptime
99.75%
F
@fal/qwen-image-edit-plus-lora-gallery-add-backgroundT1
General

Add a realistic scene behind the object with white background

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.84
P50
175
ms
Uptime
99.70%
F
@fal/qwen-image-edit-plus-lora-gallery-face-to-full-portraitT1
General

Generate full portrait from a cropped face photo

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.96
P50
368
ms
Uptime
99.85%
F
@fal/qwen-image-edit-plus-lora-gallery-group-photoT1
General

Create group photos

Price
0.000
cr/req
Uses
108
est.
Rep
0.85
P50
568
ms
Uptime
99.84%
F
@fal/qwen-image-edit-plus-lora-gallery-integrate-productT1
General

Blend products into backgrounds with automatic perspective and lighting correction

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.83
P50
288
ms
Uptime
99.71%
F
@fal/qwen-image-edit-plus-lora-gallery-lighting-restorationT1
General

Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.85
P50
614
ms
Uptime
99.89%
F
@fal/qwen-image-edit-plus-lora-gallery-multiple-anglesT1
General

Precise camera position and angle control (rotation, zoom, vertical movement)

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.86
P50
514
ms
Uptime
99.92%
F
@fal/qwen-image-edit-plus-lora-gallery-next-sceneT1
General

Create cinematic transitions and scene progressions (camera movements, framing changes)

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.90
P50
636
ms
Uptime
99.85%
F
@fal/qwen-image-edit-plus-lora-gallery-remove-elementT1
General

Remove unwanted elements (objects, people, text) while maintaining image consistency

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.94
P50
448
ms
Uptime
99.73%
F
@fal/qwen-image-edit-plus-lora-gallery-remove-lightingT1
General

Remove existing lighting and apply soft, even illumination

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.93
P50
617
ms
Uptime
99.77%
F
@fal/qwen-image-edit-plus-lora-gallery-shirt-designT1
General

Apply designs/graphics onto people's shirts

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.87
P50
615
ms
Uptime
99.93%
F
@fal/qwen-image-image-to-imageT1
General

Qwen-Image (Image-to-Image) transforms and edits input images with high fidelity, enabling precise style transfer, enhancement, and creative modification.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.87
P50
261
ms
Uptime
99.83%
F
@fal/qwen-image-layeredT1
General

Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.86
P50
205
ms
Uptime
99.78%
F
@fal/qwen-image-layered-loraT1
General

Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. Use loras to get your custom outputs.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.86
P50
366
ms
Uptime
99.81%
F
@fal/qwen-image-max-editT1
General

Image editing endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.92
P50
401
ms
Uptime
99.71%
F
@fal/qwen-image-max-text-to-imageT1
General

Text-to-Image endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.

Price
0.000
cr/req
Uses
996
est.
Rep
0.91
P50
549
ms
Uptime
99.77%
F
@fal/realistic-visionT1
General

Generate realistic images.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.93
P50
553
ms
Uptime
99.72%
F
@fal/reconviagen-0-5T1
General

Generate 3D models from one or more images using ReconViaGen 0.5

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.86
P50
420
ms
Uptime
99.81%
F
@fal/recraft-20bT1
General

Recraft 20b is a new and affordable text-to-image model.

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.97
P50
487
ms
Uptime
99.81%
F
@fal/recraft-upscale-creativeT1
General

Enhances a given raster image using the 'creative upscale' tool, increasing image resolution, making the image sharper and cleaner.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.82
P50
516
ms
Uptime
99.71%
F
@fal/recraft-upscale-crispT1
General

Enhances a given raster image using 'crisp upscale' tool, boosting resolution with a focus on refining small details and faces.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.86
P50
286
ms
Uptime
99.86%
F
@fal/recraft-v3-create-styleT1
General

Recraft V3 Create Style is capable of creating unique styles for Recraft V3 based on your images.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.83
P50
171
ms
Uptime
99.94%
F
@fal/recraft-v3-image-to-imageT1
General

Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.84
P50
357
ms
Uptime
99.89%
F
@fal/recraft-v3-text-to-imageT1
General

Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.85
P50
378
ms
Uptime
99.97%
F
@fal/recraft-v4-1-pro-text-to-imageT1
General

Recraft V4.1 Pro pushes the V4.1 model into high-resolution territory — up to 2048×2048 and ultra-wide formats. Made for hero imagery, campaign work, and print, it preserves the same design taste at sizes ready for the final deliverable.

Price
0.000
cr/req
Uses
840
est.
Rep
0.88
P50
641
ms
Uptime
99.79%
F
@fal/recraft-v4-1-pro-text-to-vectorT1
General

Recraft V4.1 Pro Vector generates large-format, fully editable SVGs with the structural clarity professional illustrators expect. Built for poster art, complex brand assets, and detailed scene illustration, it scales without losing geometric integrity.

Price
0.000
cr/req
Uses
430
est.
Rep
0.89
P50
506
ms
Uptime
99.85%
F
@fal/recraft-v4-1-text-to-imageT1
General

Recraft V4.1 builds on the design-first foundation of V4 with sharper prompt control and cleaner composition. Tuned for brand systems and editorial work, it delivers production-ready raster images that hold up next to a designer's hand.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.91
P50
443
ms
Uptime
99.87%
F
@fal/recraft-v4-1-text-to-vectorT1
General

Recraft V4.1 Vector turns prompts into fully editable SVGs with structured layers and clean geometry. Built for logos, icons, and illustration systems, it produces artwork that goes straight from generation into Figma or Illustrator.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.95
P50
196
ms
Uptime
99.83%
F
@fal/recraft-v4-1-utility-pro-text-to-imageT1
General

Recraft V4.1 Utility Pro pairs the high-resolution output of V4.1 Pro with a faster, cost-efficient runtime. Designed for studios shipping large-format work at scale, it makes premium-quality raster generation viable across full creative pipelines.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.98
P50
580
ms
Uptime
99.89%
F
@fal/recraft-v4-1-utility-text-to-imageT1
General

Recraft V4.1 Utility is a faster, lighter variant of V4.1 made for high-volume creative workflows. Ideal for ideation, A/B exploration, and content pipelines, it keeps Recraft's design sensibility while optimizing for throughput and cost.

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.91
P50
237
ms
Uptime
99.96%
F
@fal/recraft-v4-pro-text-to-imageT1
General

Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.94
P50
220
ms
Uptime
99.87%
F
@fal/recraft-v4-pro-text-to-vectorT1
General

Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.96
P50
596
ms
Uptime
99.93%
F
@fal/recraft-v4-text-to-imageT1
General

Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.98
P50
588
ms
Uptime
99.87%
F
@fal/recraft-v4-text-to-vectorT1
General

Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.94
P50
617
ms
Uptime
99.74%
F
@fal/recraft-vectorizeT1
General

Converts a given raster image to SVG format using Recraft model.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.96
P50
440
ms
Uptime
99.85%
F
@fal/resemble-ai-chatterboxhd-speech-to-speechT1
General

Transform voices using Resemble AI's Chatterbox. Convert audio to new voices or your own samples, with expressive results and built-in perceptual watermarking.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.93
P50
233
ms
Uptime
99.73%
F
@fal/resemble-ai-chatterboxhd-text-to-speechT1
General

Generate expressive, natural speech with Resemble AI's Chatterbox. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.82
P50
213
ms
Uptime
99.86%
F
@fal/retoucherT1
General

Automatically retouches faces to smooth skin and remove blemishes.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.86
P50
602
ms
Uptime
99.78%
F
@fal/reve-2-1-editT1
General

Edit images from text prompts with strong prompt adherence, layout intelligence, and accurate text rendering using Reve 2.1

Price
0.000
cr/req
Uses
840
est.
Rep
0.88
P50
519
ms
Uptime
99.77%
F
@fal/reve-2-1-remixT1
General

Remix images from text prompts with strong prompt adherence, layout intelligence, and accurate text rendering using Reve 2.1

Price
0.000
cr/req
Uses
889
est.
Rep
0.96
P50
323
ms
Uptime
99.85%
F
@fal/reve-2-1-text-to-imageT1
General

Generate high-quality images from text prompts with strong prompt adherence, layout intelligence, and accurate text rendering using Reve 2.1.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.84
P50
391
ms
Uptime
99.98%
F
@fal/rifeT1
General

Interpolate images with RIFE - Real-Time Intermediate Flow Estimation

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.88
P50
252
ms
Uptime
99.81%
F
@fal/rife-videoT1
General

Interpolate videos with RIFE - Real-Time Intermediate Flow Estimation

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.88
P50
527
ms
Uptime
99.96%
F
@fal/rundiffusion-fal-juggernaut-flux-baseT1
General

Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.93
P50
422
ms
Uptime
99.91%
F
@fal/rundiffusion-fal-juggernaut-flux-base-image-to-imageT1
General

Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.85
P50
374
ms
Uptime
99.80%
F
@fal/rundiffusion-fal-juggernaut-flux-lightningT1
General

Juggernaut Lightning Flux by RunDiffusion provides blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.

Price
0.000
cr/req
Uses
79
est.
Rep
0.84
P50
306
ms
Uptime
99.79%
F
@fal/rundiffusion-fal-juggernaut-flux-loraT1
General

Juggernaut Base Flux LoRA by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.97
P50
449
ms
Uptime
99.86%
F
@fal/rundiffusion-fal-juggernaut-flux-lora-inpaintingT1
General

Juggernaut Base Flux LoRA Inpainting by RunDiffusion is a drop-in replacement for Flux [Dev] inpainting that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.88
P50
641
ms
Uptime
99.78%
F
@fal/rundiffusion-fal-juggernaut-flux-proT1
General

Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.94
P50
422
ms
Uptime
99.81%
F
@fal/rundiffusion-fal-juggernaut-flux-pro-image-to-imageT1
General

Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.89
P50
527
ms
Uptime
99.93%
F
@fal/rundiffusion-fal-rundiffusion-photo-fluxT1
General

RunDiffusion Photo Flux provides insane realism. With this enhancer, textures and skin details burst to life, turning your favorite prompts into vivid, lifelike creations. Recommended to keep it at 0.65 to 0.80 weight. Supports resolutions up to 1536x1536.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.93
P50
431
ms
Uptime
99.77%
F
@fal/sa2va-4b-imageT1
General

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.91
P50
367
ms
Uptime
99.97%
F
@fal/sa2va-4b-videoT1
General

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.95
P50
178
ms
Uptime
99.82%
F
@fal/sa2va-8b-imageT1
General

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.97
P50
469
ms
Uptime
99.70%
F
@fal/sa2va-8b-videoT1
General

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.89
P50
350
ms
Uptime
99.77%
F
@fal/sadtalkerT1
General

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.93
P50
494
ms
Uptime
99.74%
F
@fal/sadtalker-referenceT1
General

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.94
P50
629
ms
Uptime
99.92%
F
@fal/sam-3-1-imageT1
General

SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.94
P50
355
ms
Uptime
99.74%
F
@fal/sam-3-1-image-rleT1
General

SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.86
P50
628
ms
Uptime
99.71%
F
@fal/sam-3-1-videoT1
General

SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.83
P50
559
ms
Uptime
99.76%
F
@fal/sam-3-1-video-rleT1
General

SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.95
P50
423
ms
Uptime
99.77%
F
@fal/sam-3-3d-alignT1
General

SAM 3D enables full scene reconstructions, placing objects and humans in a shared context together.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.97
P50
655
ms
Uptime
99.93%
F
@fal/sam-3-3d-bodyT1
General

SAM 3D allows for accurate 3D reconstruction of human body shape and position from a single image.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.82
P50
200
ms
Uptime
99.93%
F
@fal/sam-3-3d-objectsT1
General

SAM 3D enables precise 3D reconstruction of objects from real images, while accurately reconstructing their geometry and texture.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.93
P50
190
ms
Uptime
99.90%
F
@fal/sam-3-imageT1
General

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.95
P50
287
ms
Uptime
99.92%
F
@fal/sam-3-image-embedT1
General

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.95
P50
466
ms
Uptime
99.96%
F
@fal/sam-3-image-rleT1
General

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.91
P50
553
ms
Uptime
99.75%
F
@fal/sam-3-videoT1
General

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.95
P50
204
ms
Uptime
99.98%
F
@fal/sam-3-video-rleT1
General

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.84
P50
366
ms
Uptime
99.98%
F
@fal/sam-audio-separateT1
General

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.92
P50
236
ms
Uptime
99.72%
F
@fal/sam-audio-span-separateT1
General

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.97
P50
580
ms
Uptime
99.92%
F
@fal/sam-audio-visual-separateT1
General

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.88
P50
451
ms
Uptime
99.77%
F
@fal/sam2-auto-segmentT1
General

SAM 2 is a model for segmenting images automatically. It can return individual masks or a single mask for the entire image.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.86
P50
421
ms
Uptime
99.84%
F
@fal/sam2-imageT1
General

SAM 2 is a model for segmenting images and videos in real-time.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.83
P50
247
ms
Uptime
99.86%
F
@fal/sam2-videoT1
General

SAM 2 is a model for segmenting images and videos in real-time.

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.85
P50
598
ms
Uptime
99.82%
F
@fal/sanaT1
General

Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, with the ability to generate 4K images in less than a second.

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.85
P50
513
ms
Uptime
99.95%
F
@fal/sana-sprintT1
General

Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.89
P50
421
ms
Uptime
99.93%
F
@fal/sana-v1-5-1-6bT1
General

Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.93
P50
532
ms
Uptime
99.86%
F
@fal/sana-v1-5-4-8bT1
General

Sana v1.5 4.8B is a powerful text-to-image model that generates ultra-high quality 4K images with remarkable detail.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.90
P50
438
ms
Uptime
99.76%
F
@fal/scail-2T1
General

SCAIL-2 is an end-to-end character animation model that drives a reference character from a source video without relying on intermediate pose representations like skeleton maps.

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.96
P50
563
ms
Uptime
99.74%
F
@fal/scene-finderT1
General

Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.93
P50
650
ms
Uptime
99.95%
F
@fal/sdxl-controlnet-unionT1
General

An efficent SDXL multi-controlnet text-to-image model.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.86
P50
379
ms
Uptime
99.94%
F
@fal/sdxl-controlnet-union-image-to-imageT1
General

An efficent SDXL multi-controlnet image-to-image model.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.91
P50
359
ms
Uptime
99.82%
F
@fal/sdxl-controlnet-union-inpaintingT1
General

An efficent SDXL multi-controlnet inpainting model.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.89
P50
598
ms
Uptime
99.76%
F
@fal/seedvr-upscale-imageT1
General

Use SeedVR2 to upscale your images

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.96
P50
191
ms
Uptime
99.96%
F
@fal/seedvr-upscale-image-seamlessT1
General

Use SeedVR2 to upscale images, retaining seamless tiling

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.83
P50
425
ms
Uptime
99.77%
F
@fal/seedvr-upscale-videoT1
General

Upscale your videos using SeedVR2 with temporal consistency!

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.85
P50
568
ms
Uptime
99.87%
F
@fal/sensenova-u1-infographicT1
General

Generate Infographic Image with Sensenova U1

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.85
P50
370
ms
Uptime
99.77%
F
@fal/silero-vadT1
General

Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.92
P50
278
ms
Uptime
99.78%
F
@fal/smart-resizeT1
General

Smart image resize to arbitrary dimensions, powered by Nano Banana Pro with vision-LLM-guided prompting for composition-aware recomposition. Crop, cropping, resize ads.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.89
P50
556
ms
Uptime
99.94%
F
@fal/smart-turnT1
General

An open source, community-driven and native audio turn detection model by Pipecat AI.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.84
P50
530
ms
Uptime
99.74%
F
@fal/smoretalk-ai-rembg-enhanceT1
General

Rembg-enhance is optimized for 2D vector images, 3D graphics, and photos by leveraging matting technology.

Price
0.000
cr/req
Uses
801
est.
Rep
0.85
P50
433
ms
Uptime
99.99%
F
@fal/sonilo-v1-1-text-to-musicT1
General

Generates licensed, commercial-use-safe music from a single text prompt, with full control over style, mood, instrumentation, and exact duration.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.84
P50
205
ms
Uptime
99.74%
F
@fal/sonilo-v1-1-video-to-musicT1
General

Analyzes your video’s pacing, mood, and timing to generate a frame-synced, licensed, commercial-use-safe soundtrack in seconds.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.96
P50
512
ms
Uptime
99.88%
F
@fal/sonilo-v1-1-video-to-videoT1
General

Generates perfectly synced music for any video. Return a licensed music soundtrack ready for commercial use (optional preservation of the original speech in video)

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.87
P50
455
ms
Uptime
99.92%
F
@fal/speech-to-textT1
General

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.97
P50
356
ms
Uptime
99.81%
F
@fal/speech-to-text-streamT1
General

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.83
P50
416
ms
Uptime
99.95%
F
@fal/speech-to-text-turboT1
General

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.90
P50
130
ms
Uptime
99.75%
F
@fal/speech-to-text-turbo-streamT1
General

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Price
0.000
cr/req
Uses
430
est.
Rep
0.91
P50
409
ms
Uptime
99.87%
F
@fal/stable-audioT1
General

Open source text-to-audio model.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.84
P50
167
ms
Uptime
99.78%
F
@fal/stable-audio-25-audio-to-audioT1
General

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.83
P50
150
ms
Uptime
99.88%
F
@fal/stable-audio-25-inpaintT1
General

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.90
P50
232
ms
Uptime
99.79%
F
@fal/stable-audio-25-text-to-audioT1
General

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.85
P50
556
ms
Uptime
99.73%
F
@fal/stable-audio-3-medium-audio-inpaintingT1
General

Stable Audio 3 Medium audio inpainting is a 1.4 billion parameter latent diffusion model that fills in or reworks selected segments of a stereo track guided by text prompts, supporting single- and multi-segment editing.

Price
0.000
cr/req
Uses
548
est.
Rep
0.90
P50
181
ms
Uptime
99.81%
F
@fal/stable-audio-3-medium-audio-outpaintingT1
General

Stable Audio 3 Medium audio outpainting is a 1.4 billion parameter latent diffusion model that extends existing stereo audio beyond its original endpoint via causal continuation guided by text prompts.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.86
P50
513
ms
Uptime
99.74%
F
@fal/stable-audio-3-medium-audio-to-audioT1
General

Stable Audio 3 Medium audio-to-audio is a 1.4 billion parameter latent diffusion model that transforms an input audio clip into new stereo variations up to 6 minutes guided by a text prompt.

Price
0.000
cr/req
Uses
831
est.
Rep
0.86
P50
438
ms
Uptime
99.75%
F
@fal/stable-audio-3-medium-base-audio-inpaintingT1
General

Stable Audio 3 Medium Base audio inpainting is the foundational 1.4 billion parameter checkpoint for editing or filling selected stereo audio segments guided by text prompts.

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.83
P50
391
ms
Uptime
99.72%
F
@fal/stable-audio-3-medium-base-audio-outpaintingT1
General

Stable Audio 3 Medium Base audio outpainting is the foundational 1.4 billion parameter checkpoint that extends existing stereo audio with causal continuation guided by text prompts.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.84
P50
415
ms
Uptime
99.77%
F
@fal/stable-audio-3-medium-base-audio-to-audioT1
General

Stable Audio 3 Medium Base audio-to-audio is the foundational 1.4 billion parameter checkpoint that transforms input audio into new stereo variations up to 6 minutes guided by text prompts.

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.96
P50
546
ms
Uptime
99.77%
F
@fal/stable-audio-3-medium-base-text-to-audioT1
General

Stable Audio 3 Medium Base is the foundational 1.4 billion parameter text-to-audio checkpoint generating stereo music up to 6 minutes, intended as the unmodified base for custom fine-tuning workflows.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.83
P50
529
ms
Uptime
99.96%
F
@fal/stable-audio-3-medium-text-to-audioT1
General

Stable Audio 3 Medium is a 1.4 billion parameter latent diffusion model that generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for safe commercial use.

Price
0.000
cr/req
Uses
674
est.
Rep
0.83
P50
129
ms
Uptime
99.73%
F
@fal/stable-audio-3-small-music-audio-inpaintingT1
General

Stable Audio 3 Small Music audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a music track guided by text prompts.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.84
P50
631
ms
Uptime
99.79%
F
@fal/stable-audio-3-small-music-audio-outpaintingT1
General

Stable Audio 3 Small Music audio outpainting is a 459 million parameter latent diffusion model that extends music compositions beyond their original endpoint via causal continuation.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.92
P50
338
ms
Uptime
99.89%
F
@fal/stable-audio-3-small-music-audio-to-audioT1
General

Stable Audio 3 Small Music audio-to-audio is a 459 million parameter latent diffusion model that transforms input music into new variations up to 2 minutes guided by text prompts.

Price
0.000
cr/req
Uses
440
est.
Rep
0.92
P50
393
ms
Uptime
99.87%
F
@fal/stable-audio-3-small-music-base-audio-inpaintingT1
General

Stable Audio 3 Small Music Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected music segments guided by text prompts.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.87
P50
543
ms
Uptime
99.88%
F
@fal/stable-audio-3-small-music-base-audio-outpaintingT1
General

Stable Audio 3 Small Music Base audio outpainting is the foundational 459 million parameter checkpoint that extends music tracks via causal continuation guided by text prompts.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.89
P50
253
ms
Uptime
99.85%
F
@fal/stable-audio-3-small-music-base-audio-to-audioT1
General

Stable Audio 3 Small Music Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input music into new variations up to 2 minutes guided by text prompts.

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.96
P50
187
ms
Uptime
99.86%
F
@fal/stable-audio-3-small-music-base-text-to-audioT1
General

Stable Audio 3 Small Music Base is the foundational 459 million parameter checkpoint generating full music compositions up to 2 minutes from text prompts, intended as the unmodified base for fine-tuning.

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.95
P50
466
ms
Uptime
99.95%
F
@fal/stable-audio-3-small-music-text-to-audioT1
General

Stable Audio 3 Small Music is a 459 million parameter latent diffusion model that generates full stereo music compositions up to 2 minutes from text prompts, lightweight enough for on-device deployment.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.90
P50
168
ms
Uptime
99.97%
F
@fal/stable-audio-3-small-sfx-audio-inpaintingT1
General

Stable Audio 3 Small SFX audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a sound-effect track guided by text prompts.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.84
P50
415
ms
Uptime
99.83%
F
@fal/stable-audio-3-small-sfx-audio-outpaintingT1
General

Stable Audio 3 Small SFX audio outpainting is a 459 million parameter latent diffusion model that extends sound-effect tracks beyond their original endpoint via causal continuation.

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.94
P50
533
ms
Uptime
99.71%
F
@fal/stable-audio-3-small-sfx-audio-to-audioT1
General

Stable Audio 3 Small SFX audio-to-audio is a 459 million parameter latent diffusion model that transforms input audio into new sound-effect variations guided by text prompts.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.86
P50
408
ms
Uptime
99.86%
F
@fal/stable-audio-3-small-sfx-base-audio-inpaintingT1
General

Stable Audio 3 Small SFX Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected sound-effect segments guided by text prompts.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.89
P50
434
ms
Uptime
99.91%
F
@fal/stable-audio-3-small-sfx-base-audio-outpaintingT1
General

Stable Audio 3 Small SFX Base audio outpainting is the foundational 459 million parameter checkpoint that extends sound-effect tracks via causal continuation guided by text prompts.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.97
P50
655
ms
Uptime
99.77%
F
@fal/stable-audio-3-small-sfx-base-audio-to-audioT1
General

Stable Audio 3 Small SFX Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input audio into new sound-effect variations guided by text prompts.

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.84
P50
648
ms
Uptime
99.80%
F
@fal/stable-audio-3-small-sfx-base-text-to-audioT1
General

Stable Audio 3 Small SFX Base is the foundational 459 million parameter checkpoint generating sound effects from text prompts, intended as the unmodified base for fine-tuning.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.82
P50
462
ms
Uptime
99.85%
F
@fal/stable-audio-3-small-sfx-text-to-audioT1
General

Stable Audio 3 Small SFX is a 459 million parameter latent diffusion model that generates high-quality sound effects from text prompts, designed for on-device deployment on mobile phones and consumer laptops.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.87
P50
172
ms
Uptime
99.74%
F
@fal/stable-audio-3-trainerT1
General

Stable Audio 3 LoRA Trainer fine-tunes Stable Audio 3 base models on paired audio-caption datasets, producing compact LoRA weights that adapt generation toward a custom music style, sound palette, or domain.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.89
P50
637
ms
Uptime
99.84%
F
@fal/stable-cascadeT1
General

Stable Cascade: Image generation on a smaller & cheaper latent space.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.91
P50
291
ms
Uptime
99.79%
F
@fal/stable-cascade-sote-diffusionT1
General

Anime finetune of Würstchen V3.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.86
P50
483
ms
Uptime
99.91%
F
@fal/stable-diffusion-v15T1
General

Stable Diffusion v1.5

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.93
P50
562
ms
Uptime
99.82%
F
@fal/stable-diffusion-v3-mediumT1
General

Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.86
P50
307
ms
Uptime
99.94%
F
@fal/stable-diffusion-v3-medium-image-to-imageT1
General

Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.83
P50
356
ms
Uptime
99.91%
F
@fal/stable-diffusion-v35-largeT1
General

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.94
P50
266
ms
Uptime
99.93%
F
@fal/stable-diffusion-v35-mediumT1
General

Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Price
0.000
cr/req
Uses
50
est.
Rep
0.96
P50
162
ms
Uptime
99.73%
F
@fal/stable-videoT1
General

Generate short video clips from your images using SVD v1.1

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.82
P50
605
ms
Uptime
99.81%
F
@fal/stepx-edit2T1
General

Image-to-image editing with Step1X-Edit v2 from StepFun. Reasoning-enhanced modifications through a thinking–editing–reflection loop with MLLM world knowledge for abstract instruction comprehension.

Price
0.000
cr/req
Uses
50
est.
Rep
0.85
P50
234
ms
Uptime
99.72%
F
@fal/sync-lipsyncT1
General

Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.89
P50
569
ms
Uptime
99.89%
F
@fal/sync-lipsync-react-1T1
General

Use React-1 from SyncLabs to refine human emotions and do realistic lip-sync without losing details!

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.91
P50
262
ms
Uptime
99.81%
F
@fal/sync-lipsync-v2T1
General

Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.89
P50
203
ms
Uptime
99.95%
F
@fal/sync-lipsync-v2-proT1
General

Generate high-quality realistic lipsync animations from audio while preserving unique details like natural teeth and unique facial features using the state-of-the-art Sync Lipsync 2 Pro model.

Price
0.000
cr/req
Uses
421
est.
Rep
0.94
P50
241
ms
Uptime
99.86%
F
@fal/sync-lipsync-v3T1
General

sync-3 most powerful lipsync model yet, featuring native visual intelligence for professional-quality video.

Price
0.000
cr/req
Uses
655
est.
Rep
0.92
P50
186
ms
Uptime
99.71%
F
@fal/sync-lipsync-v3-image-to-videoT1
General

sync-3 image to video turns a single still into a talking character, and works with any illustration or animated frame paired with a voice track

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.94
P50
477
ms
Uptime
99.86%
F
@fal/t2v-turboT1
General

Generate short video clips from your prompts

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.85
P50
226
ms
Uptime
99.79%
F
@fal/tada-1b-text-to-speechT1
General

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. Lighter 1B variant

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.95
P50
622
ms
Uptime
99.74%
F
@fal/tada-3b-text-to-speechT1
General

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.84
P50
500
ms
Uptime
99.77%
F
@fal/telestyle-v2T1
General

Restyle any image with TeleStyle v2 — provide an original image and a styling reference, and the model re-renders the original in the reference's visual style while preserving its content and composition.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.85
P50
568
ms
Uptime
99.99%
F
@fal/thinksoundT1
General

Generate realistic audio for a video with an optional text prompt and combine

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.82
P50
368
ms
Uptime
99.95%
F
@fal/thinksound-audioT1
General

Generate realistic audio from a video with an optional text prompt

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.95
P50
200
ms
Uptime
99.99%
F
@fal/topaz-upscale-imageT1
General

Use the powerful and accurate topaz image enhancer to enhance your images.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.89
P50
531
ms
Uptime
99.79%
F
@fal/topaz-upscale-videoT1
General

Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.94
P50
355
ms
Uptime
99.77%
F
@fal/trellisT1
General

Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.97
P50
390
ms
Uptime
99.96%
F
@fal/trellis-2T1
General

Generate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.95
P50
643
ms
Uptime
99.75%
F
@fal/trellis-2-loraT1
General

Run inference on LoRA adapters for TRELLIS.2 model

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.88
P50
488
ms
Uptime
99.95%
F
@fal/trellis-2-lora-trainerT1
General

Train LoRA adapters for TRELLIS.2 model

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.95
P50
162
ms
Uptime
99.84%
F
@fal/trellis-2-retextureT1
General

Generate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.90
P50
641
ms
Uptime
99.86%
F
@fal/trellis-multiT1
General

Generate 3D models from multiple images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.90
P50
143
ms
Uptime
99.98%
F
@fal/tripo3d-h3-1-image-to-3dT1
General

Generate high-quality 3D models from a single image using Tripo H3.1.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.92
P50
621
ms
Uptime
99.83%
F
@fal/tripo3d-h3-1-multiview-to-3dT1
General

Generate 3D models from multiple view images using Tripo H3.1.

Price
0.000
cr/req
Uses
450
est.
Rep
0.90
P50
553
ms
Uptime
99.89%
F
@fal/tripo3d-h3-1-text-to-3dT1
General

Generate 3D models from text descriptions using Tripo H3.1.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.88
P50
620
ms
Uptime
99.96%
F
@fal/tripo3d-p1-image-to-3dT1
General

Generate 3D models from a single image using Tripo P1.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.97
P50
584
ms
Uptime
99.93%
F
@fal/tripo3d-p1-text-to-3dT1
General

Generate 3D models from text descriptions using Tripo P1.

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.97
P50
128
ms
Uptime
99.84%
F
@fal/tripo3d-tripo-v2-5-image-to-3dT1
General

State of the art Image to 3D Object generation. Generate 3D model from a single image!

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.93
P50
372
ms
Uptime
99.77%
F
@fal/tripo3d-tripo-v2-5-multiview-to-3dT1
General

State of the art Multiview to 3D Object generation. Generate 3D models from multiple images!

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.90
P50
168
ms
Uptime
99.84%
F
@fal/tripo3d-triposplatT1
General

TripoSplat is an open-source model from TripoAI / VAST AI Research that converts a single 2D image into high-quality 3D Gaussians using a novel learned density-control approach

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.85
P50
610
ms
Uptime
99.95%
F
@fal/triposrT1
General

State of the art Image to 3D Object generation

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.84
P50
555
ms
Uptime
99.84%
F
@fal/turbo-flux-trainerT1
General

A blazing fast FLUX dev LoRA trainer for subjects and styles.

Price
0.000
cr/req
Uses
801
est.
Rep
0.89
P50
425
ms
Uptime
99.72%
F
@fal/unoT1
General

An AI model that transforms input images into new ones based on text prompts, blending reference visuals with your creative directions.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.90
P50
337
ms
Uptime
99.80%
F
@fal/usoT1
General

Use USO to perform subject driven generations using reference image.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.83
P50
222
ms
Uptime
99.79%
F
@fal/vecglypherT1
General

Vector font generation with VecGlypher. Create custom glyphs from text descriptions or reference images—outputs clean SVG paths directly without raster-to-vector conversion.

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.87
P50
539
ms
Uptime
99.94%
F
@fal/vecglypher-image-to-svgT1
General

Vector font generation with VecGlypher. Create custom glyphs from text descriptions or reference images—outputs clean SVG paths directly without raster-to-vector conversion.

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.90
P50
261
ms
Uptime
99.94%
F
@fal/veed-avatars-audio-to-videoT1
General

Generate high-quality videos with UGC-like avatars from audio

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.95
P50
465
ms
Uptime
99.84%
F
@fal/veed-avatars-text-to-videoT1
General

Generate high-quality videos with UGC-like avatars from text

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.93
P50
587
ms
Uptime
99.88%
F
@fal/veed-fabric-1-0T1
General

VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.87
P50
231
ms
Uptime
99.91%
F
@fal/veed-fabric-1-0-fastT1
General

VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.84
P50
450
ms
Uptime
99.71%
F
@fal/veed-fabric-1-0-textT1
General

VEED Fabric 1.0 text-to-video API

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.90
P50
645
ms
Uptime
99.77%
F
@fal/veed-lipsyncT1
General

Generate realistic lipsync from any audio using VEED's model.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.90
P50
392
ms
Uptime
99.79%
F
@fal/veed-lipsync-v2T1
General

Generate production-quality lipsync from any audio using VEED's most advanced model yet.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.92
P50
405
ms
Uptime
99.77%
F
@fal/veed-subtitlesT1
General

VEED’s Subtitles API transforms raw footage into polished, publish-ready content with professional burned-in subtitles starting at a base rate of $0.10 per minute.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.90
P50
215
ms
Uptime
99.75%
F
@fal/veed-video-background-removalT1
General

Remove background from any video with people and objects. No green screen needed.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.92
P50
604
ms
Uptime
99.82%
F
@fal/veed-video-background-removal-fastT1
General

Remove background from any video with people and objects. No green screen needed.

Price
0.000
cr/req
Uses
967
est.
Rep
0.89
P50
388
ms
Uptime
99.71%
F
@fal/veed-video-background-removal-green-screenT1
General

Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.89
P50
455
ms
Uptime
99.79%
F
@fal/veo3-1T1
General

Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on!

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.97
P50
255
ms
Uptime
99.92%
F
@fal/veo3-1-extend-videoT1
General

Extend Veo-Created Videos up to 30 seconds

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.93
P50
406
ms
Uptime
99.74%
F
@fal/veo3-1-fastT1
General

Faster and more cost effective version of Google's Veo 3.1!

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.91
P50
506
ms
Uptime
99.89%
F
@fal/veo3-1-fast-extend-videoT1
General

Extend Veo-Created Videos up to 30 seconds

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.86
P50
619
ms
Uptime
99.76%
F
@fal/veo3-1-fast-first-last-frame-to-videoT1
General

Generate videos from a first/last frame using Google's Veo 3.1 Fast

Price
0.000
cr/req
Uses
948
est.
Rep
0.83
P50
306
ms
Uptime
99.99%
F
@fal/veo3-1-fast-image-to-videoT1
General

Generate videos from your image prompts using Veo 3.1 fast.

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.92
P50
131
ms
Uptime
99.94%
F
@fal/veo3-1-fast-reference-to-videoT1
General

Generate videos from reference images using Google's Veo 3.1 Fast

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.95
P50
310
ms
Uptime
99.82%
F
@fal/veo3-1-first-last-frame-to-videoT1
General

Generate videos from a first and last framed using Google's Veo 3.1

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.94
P50
655
ms
Uptime
99.89%
F
@fal/veo3-1-image-to-videoT1
General

Veo 3.1 is the latest state-of-the art video generation model from Google DeepMind

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.87
P50
552
ms
Uptime
99.72%
F
@fal/veo3-1-liteT1
General

Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.98
P50
377
ms
Uptime
99.72%
F
@fal/veo3-1-lite-first-last-frame-to-videoT1
General

Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.88
P50
400
ms
Uptime
99.74%
F
@fal/veo3-1-lite-image-to-videoT1
General

Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.97
P50
436
ms
Uptime
99.92%
F
@fal/veo3-1-reference-to-videoT1
General

Generate Videos from images using Google's Veo 3.1

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.93
P50
305
ms
Uptime
99.97%
F
@fal/vibevoiceT1
General

Generate long, expressive multi-voice speech using Microsoft's powerful TTS

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.91
P50
561
ms
Uptime
99.70%
F
@fal/vibevoice-0-5bT1
General

Generate long speech snippets fast using Microsoft's powerful TTS.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.83
P50
142
ms
Uptime
99.99%
F
@fal/vibevoice-7bT1
General

Generate long, expressive multi-voice speech using Microsoft's powerful TTS

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.90
P50
333
ms
Uptime
99.86%
F
@fal/video-prompt-generatorT1
General

Generate video prompts using a variety of techniques including camera direction, style, pacing, special effects and more.

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.85
P50
416
ms
Uptime
99.77%
F
@fal/video-understandingT1
General

A video understanding model to analyze video content and answer questions about what's happening in the video based on user prompts.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.83
P50
558
ms
Uptime
99.81%
F
@fal/video-upscalerT1
General

The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.92
P50
182
ms
Uptime
99.93%
F
@fal/vidu-image-to-videoT1
General

Vidu Image to Video generates high-quality videos with exceptional visual quality and motion diversity from a single image

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.87
P50
623
ms
Uptime
99.84%
F
@fal/vidu-q1-image-to-videoT1
General

Vidu Q1 Image to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity from a single image

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.84
P50
133
ms
Uptime
99.96%
F
@fal/vidu-q1-reference-to-videoT1
General

Generate video clips from your multiple image references using Vidu Q1

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.82
P50
580
ms
Uptime
99.89%
F
@fal/vidu-q1-start-end-to-videoT1
General

Vidu Q1 Start-End to Video generates smooth transition 1080p videos between specified start and end images.

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.90
P50
165
ms
Uptime
99.79%
F
@fal/vidu-q1-text-to-videoT1
General

Vidu Q1 Text to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.90
P50
616
ms
Uptime
99.76%
F
@fal/vidu-q2-image-to-video-proT1
General

Use the latest Vidu Q2 models which much more better quality and control on your videos.

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.95
P50
440
ms
Uptime
99.97%
F
@fal/vidu-q2-image-to-video-turboT1
General

Use the latest Vidu Q2 models which much more better quality and control on your videos.

Price
0.000
cr/req
Uses
118
est.
Rep
0.88
P50
543
ms
Uptime
99.86%
F
@fal/vidu-q2-reference-to-imageT1
General

Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.83
P50
192
ms
Uptime
99.79%
F
@fal/vidu-q2-reference-to-video-proT1
General

Use the latest Vidu Q2 Pro models which much more better quality and control on your videos.

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.89
P50
189
ms
Uptime
99.97%
F
@fal/vidu-q2-text-to-imageT1
General

Use vidu Text-to-Image to turn your prompts into reality.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.86
P50
593
ms
Uptime
99.84%
F
@fal/vidu-q2-text-to-videoT1
General

Use the latest Vidu Q2 models which much more better quality and control on your videos.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.83
P50
310
ms
Uptime
99.76%
F
@fal/vidu-q2-video-extension-proT1
General

Use the latest Vidu Q2 models which much more better quality and control on your videos.

Price
0.000
cr/req
Uses
752
est.
Rep
0.91
P50
173
ms
Uptime
99.89%
F
@fal/vidu-q3-image-to-videoT1
General

Vidu's latest Q3 pro models.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.91
P50
443
ms
Uptime
99.83%
F
@fal/vidu-q3-image-to-video-turboT1
General

Vidu's Q3 Turbo Model

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.89
P50
253
ms
Uptime
99.98%
F
@fal/vidu-q3-reference-to-video-mixT1
General

Vidu's latest Q3 Reference to Video Mix model

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.92
P50
283
ms
Uptime
99.91%
F
@fal/vidu-q3-text-to-videoT1
General

Vidu's latest Q3 pro models

Price
0.000
cr/req
Uses
596
est.
Rep
0.84
P50
480
ms
Uptime
99.87%
F
@fal/vidu-q3-text-to-video-turboT1
General

Vidu's Q3 Turbo Model.

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.85
P50
429
ms
Uptime
99.93%
F
@fal/vidu-reference-to-imageT1
General

Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.94
P50
186
ms
Uptime
99.71%
F
@fal/vidu-reference-to-videoT1
General

Vidu Reference to Video creates videos by using a reference images and combining them with a prompt.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.95
P50
601
ms
Uptime
99.89%
F
@fal/vidu-start-end-to-videoT1
General

Vidu Start-End to Video generates smooth transition videos between specified start and end images.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.89
P50
244
ms
Uptime
99.81%
F
@fal/vidu-template-to-videoT1
General

Vidu Template to Video lets you create different effects by applying motion templates to your images.

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.89
P50
223
ms
Uptime
99.88%
F
@fal/void-video-inpaintingT1
General

VOID removes objects from videos along with all interactions they induce on the scene

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.94
P50
524
ms
Uptime
99.83%
F
@fal/wan-22-image-trainerT1
General

Wan 2.2 text to image LoRA trainer. Fine-tune Wan 2.2 for subjects and styles with unprecedented detail.

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.92
P50
608
ms
Uptime
99.77%
F
@fal/wan-22-trainer-i2v-a14bT1
General

Train custom LoRAs for Wan-2.2 T2V/I2V 480P

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.93
P50
372
ms
Uptime
99.74%
F
@fal/wan-22-trainer-t2v-a14bT1
General

Train custom LoRAs for Wan-2.2 T2V/I2V 480P

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.93
P50
553
ms
Uptime
99.98%
F
@fal/wan-22-vace-fun-a14b-depthT1
General

VACE Fun for Wan 2.2 A14B from Alibaba-PAI

Price
0.000
cr/req
Uses
596
est.
Rep
0.84
P50
335
ms
Uptime
99.91%
F
@fal/wan-22-vace-fun-a14b-inpaintingT1
General

VACE Fun for Wan 2.2 A14B from Alibaba-PAI

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.97
P50
243
ms
Uptime
99.75%
F
@fal/wan-22-vace-fun-a14b-outpaintingT1
General

VACE Fun for Wan 2.2 A14B from Alibaba-PAI

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.90
P50
459
ms
Uptime
99.73%
F
@fal/wan-22-vace-fun-a14b-reframeT1
General

VACE Fun for Wan 2.2 A14B from Alibaba-PAI

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.83
P50
134
ms
Uptime
99.82%
F
@fal/wan-25-preview-image-to-imageT1
General

Wan 2.5 image-to-image model.

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.84
P50
479
ms
Uptime
99.82%
F
@fal/wan-25-preview-image-to-videoT1
General

Wan 2.5 image-to-video model.

Price
0.000
cr/req
Uses
40
est.
Rep
0.92
P50
569
ms
Uptime
99.71%
F
@fal/wan-25-preview-text-to-imageT1
General

Wan 2.5 text-to-image model.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.91
P50
565
ms
Uptime
99.74%
F
@fal/wan-25-preview-text-to-videoT1
General

Wan 2.5 text-to-video model.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.89
P50
303
ms
Uptime
99.94%
F
@fal/wan-effectsT1
General

Wan Effects generates high-quality videos with popular effects from images

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.90
P50
637
ms
Uptime
99.96%
F
@fal/wan-flf2vT1
General

Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.92
P50
123
ms
Uptime
99.87%
F
@fal/wan-i2vT1
General

Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images

Price
0.000
cr/req
Uses
499
est.
Rep
0.83
P50
209
ms
Uptime
99.72%
F
@fal/wan-i2v-loraT1
General

Add custom LoRAs to Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.86
P50
247
ms
Uptime
99.83%
F
@fal/wan-motionT1
General

Wan Motion is a streamlined character animation model that transfers motion from a driving video onto a reference character image. Based on Wan-Animate which preserves the original character's proportions, Simple uses pose retargeting to adapt the driving video's skeleton to match the reference character's body shape, producing more natural results when the two have different builds. It outputs at 720p with optimized defaults for fast, high-quality generation — just provide a video, an image, and an optional prompt.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.93
P50
128
ms
Uptime
99.83%
F
@fal/wan-pro-image-to-videoT1
General

Wan-2.1 Pro is a premium image-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from images

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.95
P50
136
ms
Uptime
99.78%
F
@fal/wan-pro-text-to-videoT1
General

Wan-2.1 Pro is a premium text-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from text prompts

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.90
P50
261
ms
Uptime
99.90%
F
@fal/wan-t2vT1
General

Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.87
P50
387
ms
Uptime
99.96%
F
@fal/wan-t2v-loraT1
General

Add custom LoRAs to Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from images

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.84
P50
369
ms
Uptime
99.83%
F
@fal/wan-trainer-i2v-720pT1
General

Train custom LoRAs for Wan-2.1 I2V 720P

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.91
P50
603
ms
Uptime
99.81%
F
@fal/wan-trainer-t2vT1
General

Train custom LoRAs for Wan-2.1 T2V 1.3B

Price
0.000
cr/req
Uses
196
est.
Rep
0.93
P50
173
ms
Uptime
99.72%
F
@fal/wan-trainer-t2v-14bT1
General

Train custom LoRAs for Wan-2.1 T2V 14B

Price
0.000
cr/req
Uses
372
est.
Rep
0.92
P50
211
ms
Uptime
99.77%
F
@fal/wan-v2-2-14b-animate-moveT1
General

Wan-Animate is a video model that generates high-fidelity character videos by replicating the expressions and movements of characters from reference videos.

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.96
P50
415
ms
Uptime
99.84%
F
@fal/wan-v2-2-14b-animate-replaceT1
General

Wan-Animate Replace is a model that can integrate animated characters into reference videos, replacing the original character while preserving the scene’s lighting and color tone for seamless environmental integration.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.82
P50
588
ms
Uptime
99.73%
F
@fal/wan-v2-2-14b-speech-to-videoT1
General

Wan-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements, and professional camera work for film and television applications

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.91
P50
308
ms
Uptime
99.98%
F
@fal/wan-v2-2-5b-image-to-videoT1
General

Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.97
P50
571
ms
Uptime
99.74%
F
@fal/wan-v2-2-5b-text-to-imageT1
General

Wan 2.2's 5B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.98
P50
141
ms
Uptime
99.83%
F
@fal/wan-v2-2-5b-text-to-videoT1
General

Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.92
P50
160
ms
Uptime
99.88%
F
@fal/wan-v2-2-5b-text-to-video-distillT1
General

Wan 2.2's 5B distill model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.91
P50
224
ms
Uptime
99.98%
F
@fal/wan-v2-2-5b-text-to-video-fast-wanT1
General

Wan 2.2's 5B FastVideo model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.98
P50
648
ms
Uptime
99.88%
F
@fal/wan-v2-2-a14b-image-to-imageT1
General

Wan 2.2's 14B model edit high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.82
P50
454
ms
Uptime
99.75%
F
@fal/wan-v2-2-a14b-image-to-videoT1
General

fal-ai/wan/v2.2-A14B/image-to-video

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.87
P50
657
ms
Uptime
99.97%
F
@fal/wan-v2-2-a14b-image-to-video-loraT1
General

Wan-2.2 image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and images. This endpoint supports LoRAs made for Wan 2.2

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.94
P50
308
ms
Uptime
99.96%
F
@fal/wan-v2-2-a14b-image-to-video-turboT1
General

Wan-2.2 Turbo image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.96
P50
389
ms
Uptime
99.75%
F
@fal/wan-v2-2-a14b-text-to-imageT1
General

Wan 2.2's 14B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.82
P50
550
ms
Uptime
99.88%
F
@fal/wan-v2-2-a14b-text-to-image-loraT1
General

Wan 2.2's 14B model with LoRA support generates high-fidelity images with enhanced prompt alignment, style adaptability.

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.88
P50
223
ms
Uptime
99.71%
F
@fal/wan-v2-2-a14b-text-to-videoT1
General

Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.88
P50
400
ms
Uptime
99.92%
F
@fal/wan-v2-2-a14b-text-to-video-loraT1
General

Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. This endpoint supports LoRAs made for Wan 2.2.

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.98
P50
423
ms
Uptime
99.95%
F
@fal/wan-v2-2-a14b-text-to-video-turboT1
General

Wan-2.2 turbo text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

Price
0.000
cr/req
Uses
460
est.
Rep
0.83
P50
492
ms
Uptime
99.90%
F
@fal/wan-v2-2-a14b-video-to-videoT1
General

Wan-2.2 video-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and source videos.

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.85
P50
133
ms
Uptime
99.70%
F
@fal/wan-v2-6-image-to-imageT1
General

Wan 2.6 image-to-image model.

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.98
P50
369
ms
Uptime
99.86%
F
@fal/wan-v2-6-image-to-videoT1
General

Wan 2.6 image-to-video model.

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.96
P50
512
ms
Uptime
99.75%
F
@fal/wan-v2-6-image-to-video-flashT1
General

Wan 2.6 image-to-video flash model.

Price
0.000
cr/req
Uses
138
est.
Rep
0.85
P50
442
ms
Uptime
99.88%
F
@fal/wan-v2-6-reference-to-videoT1
General

Wan 2.6 reference-to-video model.

Price
0.000
cr/req
Uses
801
est.
Rep
0.85
P50
235
ms
Uptime
99.98%
F
@fal/wan-v2-6-reference-to-video-flashT1
General

Wan 2.6 reference-to-video flash model.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.83
P50
310
ms
Uptime
99.96%
F
@fal/wan-v2-6-text-to-imageT1
General

Wan 2.6 text-to-image model.

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.90
P50
514
ms
Uptime
99.71%
F
@fal/wan-v2-6-text-to-videoT1
General

Wan 2.6 text-to-video model.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.93
P50
503
ms
Uptime
99.79%
F
@fal/wan-v2-7-editT1
General

Transform and edit existing images with text-guided instructions using the WAN 2.7 model for creative image manipulation.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.85
P50
302
ms
Uptime
99.91%
F
@fal/wan-v2-7-edit-videoT1
General

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.98
P50
153
ms
Uptime
99.79%
F
@fal/wan-v2-7-image-to-videoT1
General

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.93
P50
435
ms
Uptime
99.82%
F
@fal/wan-v2-7-pro-editT1
General

Edit and transform images using text instructions with the WAN 2.7 Pro model for precise, professional-grade image modifications.

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.93
P50
186
ms
Uptime
99.71%
F
@fal/wan-v2-7-pro-text-to-imageT1
General

Generate premium-quality images from text prompts using the enhanced WAN 2.7 Pro model with superior detail and composition.

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.83
P50
513
ms
Uptime
99.96%
F
@fal/wan-v2-7-reference-to-videoT1
General

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.86
P50
315
ms
Uptime
99.88%
F
@fal/wan-v2-7-text-to-imageT1
General

Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.86
P50
332
ms
Uptime
99.82%
F
@fal/wan-v2-7-text-to-videoT1
General

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Price
0.000
cr/req
Uses
460
est.
Rep
0.98
P50
170
ms
Uptime
99.93%
F
@fal/wan-vace-14bT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.96
P50
512
ms
Uptime
99.78%
F
@fal/wan-vace-14b-depthT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.95
P50
326
ms
Uptime
99.84%
F
@fal/wan-vace-14b-inpaintingT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.93
P50
351
ms
Uptime
99.70%
F
@fal/wan-vace-14b-outpaintingT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.84
P50
428
ms
Uptime
99.73%
F
@fal/wan-vace-14b-poseT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.88
P50
337
ms
Uptime
99.80%
F
@fal/wan-vace-14b-reframeT1
General

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.96
P50
347
ms
Uptime
99.74%
F
@fal/wan-vace-apps-long-reframeT1
General

Reframe entire videos scene-by-scene using Wan VACE 2.1

Price
0.000
cr/req
Uses
801
est.
Rep
0.84
P50
252
ms
Uptime
99.98%
F
@fal/wan-vace-apps-video-editT1
General

Edit videos using plain language and Wan VACE

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.93
P50
562
ms
Uptime
99.87%
F
@fal/wizperT1
General

[Experimental] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.83
P50
606
ms
Uptime
99.86%
F
@fal/workflow-utilities-audio-compressorT1
General

FFMPEG Utility for Audio Compression

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.86
P50
454
ms
Uptime
99.87%
F
@fal/workflow-utilities-auto-subtitleT1
General

Add automatic subtitles to videos

Price
0.000
cr/req
Uses
469
est.
Rep
0.87
P50
282
ms
Uptime
99.92%
F
@fal/workflow-utilities-blend-videoT1
General

FFMPEG Utility for Blending Videos

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.97
P50
424
ms
Uptime
99.74%
F
@fal/workflow-utilities-extract-nth-frameT1
General

FFMPEG Untility for Extracting nth Frame

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.98
P50
453
ms
Uptime
99.83%
F
@fal/workflow-utilities-impulse-responseT1
General

FFMPEG Utility for Impulse Response

Price
0.000
cr/req
Uses
421
est.
Rep
0.98
P50
200
ms
Uptime
99.86%
F
@fal/workflow-utilities-interleave-videoT1
General

ffmpeg utility to interleave videos

Price
0.000
cr/req
Uses
186
est.
Rep
0.97
P50
204
ms
Uptime
99.97%
F
@fal/workflow-utilities-pick-image-by-indexT1
General

Choose the Nth image from an image URL list for workflows.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.88
P50
135
ms
Uptime
99.84%
F
@fal/workflow-utilities-reverse-videoT1
General

FFMPEG Utility to Reverse Videos

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.97
P50
487
ms
Uptime
99.99%
F
@fal/workflow-utilities-scale-videoT1
General

FFMPEG Utilities to Scale Videos

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.92
P50
414
ms
Uptime
99.73%
F
@fal/workflow-utilities-trim-videoT1
General

FFMPEG Utility for Trim Video

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.84
P50
445
ms
Uptime
99.73%
F
@fal/x-ailab-nsfwT1
General

Predict whether an image is NSFW or SFW.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.92
P50
165
ms
Uptime
99.78%
F
@fal/xai-grok-imagine-imageT1
General

Generate highly aesthetic images with xAI's Grok Imagine Image generation model.

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.86
P50
395
ms
Uptime
99.93%
F
@fal/xai-grok-imagine-image-editT1
General

Edit images precisely with xAI's Grok Imagine model

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.88
P50
658
ms
Uptime
99.72%
F
@fal/xai-grok-imagine-image-quality-editT1
General

Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.91
P50
253
ms
Uptime
99.93%
F
@fal/xai-grok-imagine-image-quality-text-to-imageT1
General

Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.84
P50
121
ms
Uptime
99.80%
F
@fal/xai-grok-imagine-video-edit-videoT1
General

Edit videos using xAI's Grok Imagine

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.86
P50
441
ms
Uptime
99.90%
F
@fal/xai-grok-imagine-video-extend-videoT1
General

Extend videos with xAI's Grok Imagine video model

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.83
P50
420
ms
Uptime
99.80%
F
@fal/xai-grok-imagine-video-image-to-videoT1
General

Generate videos from images with audio using xAI's Grok Imagine Video model.

Price
0.000
cr/req
Uses
782
est.
Rep
0.87
P50
370
ms
Uptime
99.96%
F
@fal/xai-grok-imagine-video-reference-to-videoT1
General

Generate videos using multiple reference images with xAI's Grok Imagine video model

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.84
P50
327
ms
Uptime
99.95%
F
@fal/xai-grok-imagine-video-text-to-videoT1
General

Generate videos with audio from text using Grok Imagine Video.

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.95
P50
487
ms
Uptime
99.95%
F
@fal/xai-grok-imagine-video-v1-5-image-to-videoT1
General

Generate videos from images with audio using xAI's Grok Imagine 1.5 Video model.

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.97
P50
495
ms
Uptime
99.73%
F
@fal/xai-tts-v1T1
General

Generate speech with expressive and realistic voices from xAI

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.84
P50
200
ms
Uptime
99.77%
F
@fal/z-image-baseT1
General

Z-Image is the foundation model of the Z- Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.92
P50
253
ms
Uptime
99.78%
F
@fal/z-image-base-loraT1
General

LoRA endpoint for Z-Image, the foundation model of the Z- Image family.

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.96
P50
546
ms
Uptime
99.76%
F
@fal/z-image-trainerT1
General

Train LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Price
0.000
cr/req
Uses
899
est.
Rep
0.90
P50
401
ms
Uptime
99.87%
F
@fal/z-image-turboT1
General

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.82
P50
571
ms
Uptime
99.87%
F
@fal/z-image-turbo-controlnetT1
General

Generate images from text and edge, depth or pose images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.95
P50
305
ms
Uptime
99.83%
F
@fal/z-image-turbo-controlnet-loraT1
General

Generate images from text and edge, depth or pose images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
186
est.
Rep
0.82
P50
204
ms
Uptime
99.70%
F
@fal/z-image-turbo-image-to-imageT1
General

Generate images from text and images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.94
P50
385
ms
Uptime
99.72%
F
@fal/z-image-turbo-image-to-image-loraT1
General

Generate images from text and images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
2.4k
est.
Rep
0.93
P50
211
ms
Uptime
99.86%
F
@fal/z-image-turbo-inpaintT1
General

Generate images from text, an image and a mask using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.90
P50
641
ms
Uptime
99.82%
F
@fal/z-image-turbo-inpaint-loraT1
General

Generate images from text, an image, a mask and custom LoRA using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.85
P50
555
ms
Uptime
99.92%
F
@fal/z-image-turbo-loraT1
General

Text-to-Image endpoint with LoRA support for Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.95
P50
207
ms
Uptime
99.90%
F
@fal/z-image-turbo-tilingT1
General

Generate seamlessly tiling photorealistic images from text using Z-Image Turbo

Price
0.000
cr/req
Uses
772
est.
Rep
0.88
P50
657
ms
Uptime
99.95%
F
@fal/z-image-turbo-tiling-loraT1
General

Generate seamlessly tiling photorealistic images from text using Z-Image Turbo and custom LoRA

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.83
P50
348
ms
Uptime
99.91%
F
@fal/z-image-turbo-trainer-v2T1
General

Fast LoRA trainer for Z-Image-Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.85
P50
391
ms
Uptime
99.93%
F
@fal/zonosT1
General

Clone voice of any person and speak anything in their voice using zonos' voice cloning.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.84
P50
391
ms
Uptime
99.89%
F
@fal/zonos2T1
General

Zonos2 is a text-to-speech model that clones a voice from a short sample and speaks naturally across many languages.

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.85
P50
513
ms
Uptime
99.78%
O
@openrouter/ai21-jamba-large-1-7T1
General

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.91
P50
409
ms
Uptime
99.85%
O
@openrouter/aion-labs-aion-2-0T1
General

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.83
P50
348
ms
Uptime
99.85%
O
@openrouter/aion-labs-aion-3-0T1
General

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.92
P50
334
ms
Uptime
99.72%
O
@openrouter/aion-labs-aion-3-0-miniT1
General

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.91
P50
329
ms
Uptime
99.78%
O
@openrouter/aion-labs-aion-rp-llama-3-1-8bT1
General

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

Price
0.000
cr/req
Uses
821
est.
Rep
0.85
P50
260
ms
Uptime
99.72%
O
@openrouter/allenai-olmo-3-32b-thinkT1
General

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.93
P50
380
ms
Uptime
99.98%
O
@openrouter/amazon-nova-2-lite-v1T1
General

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

Price
0.000
cr/req
Uses
294
est.
Rep
0.90
P50
206
ms
Uptime
99.90%
O
@openrouter/amazon-nova-lite-v1T1
General

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.85
P50
290
ms
Uptime
99.76%
O
@openrouter/amazon-nova-micro-v1T1
General

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.87
P50
319
ms
Uptime
99.78%
O
@openrouter/amazon-nova-premier-v1T1
General

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.98
P50
592
ms
Uptime
99.74%
O
@openrouter/amazon-nova-pro-v1T1
General

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.84
P50
403
ms
Uptime
99.71%
O
@openrouter/anthracite-org-magnum-v4-72bT1
General

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.87
P50
138
ms
Uptime
99.95%
O
@openrouter/anthropic-claude-3-haikuT1
General

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.93
P50
258
ms
Uptime
99.91%
O
@openrouter/anthropic-claude-fable-5T1
General

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.98
P50
347
ms
Uptime
99.75%
O
@openrouter/anthropic-claude-fable-latestT1
General

This model always redirects to the latest model in the Claude Fable family.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.91
P50
219
ms
Uptime
99.73%
O
@openrouter/anthropic-claude-haiku-4-5T1
General

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Price
0.000
cr/req
Uses
14
lifetime
Rep
0.90
P50
388
ms
Uptime
99.88%
O
@openrouter/anthropic-claude-haiku-latestT1
General

This model always redirects to the latest model in the Anthropic Claude Haiku family.

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.87
P50
459
ms
Uptime
99.78%
O
@openrouter/anthropic-claude-opus-4T1
General

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.85
P50
421
ms
Uptime
99.72%
O
@openrouter/anthropic-claude-opus-4-1T1
General

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.98
P50
247
ms
Uptime
99.93%
O
@openrouter/anthropic-claude-opus-4-5T1
General

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

Price
0.000
cr/req
Uses
69
est.
Rep
0.87
P50
480
ms
Uptime
99.74%
O
@openrouter/anthropic-claude-opus-4-6T1
General

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.92
P50
544
ms
Uptime
99.79%
O
@openrouter/anthropic-claude-opus-4-7T1
General

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

Price
0.000
cr/req
Uses
6.1k
est.
Rep
0.95
P50
339
ms
Uptime
99.94%
O
@openrouter/anthropic-claude-opus-4-7-fastT1
General

Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.90
P50
156
ms
Uptime
99.87%
O
@openrouter/anthropic-claude-opus-4-8T1
General

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.87
P50
227
ms
Uptime
99.86%
O
@openrouter/anthropic-claude-opus-4-8-fastT1
General

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.93
P50
388
ms
Uptime
99.93%
O
@openrouter/anthropic-claude-opus-latestT1
General

This model always redirects to the latest model in the Claude Opus family.

Price
0.000
cr/req
Uses
957
est.
Rep
0.92
P50
469
ms
Uptime
99.98%
O
@openrouter/anthropic-claude-sonnet-4T1
General

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.90
P50
435
ms
Uptime
99.74%
O
@openrouter/anthropic-claude-sonnet-4-5T1
General

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Price
0.000
cr/req
Uses
645
est.
Rep
0.95
P50
326
ms
Uptime
99.99%
O
@openrouter/anthropic-claude-sonnet-4-6T1
General

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.83
P50
348
ms
Uptime
99.78%
O
@openrouter/anthropic-claude-sonnet-5T1
General

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.95
P50
634
ms
Uptime
99.94%
O
@openrouter/anthropic-claude-sonnet-latestT1
General

This model always redirects to the latest model in the Anthropic Claude Sonnet family.

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.84
P50
269
ms
Uptime
99.84%
O
@openrouter/arcee-ai-trinity-large-thinkingT1
General

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.87
P50
311
ms
Uptime
99.92%
O
@openrouter/arcee-ai-virtuoso-largeT1
General

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.90
P50
611
ms
Uptime
99.91%
O
@openrouter/baidu-ernie-4-5-vl-424b-a47bT1
General

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.89
P50
164
ms
Uptime
99.80%
O
@openrouter/bytedance-seed-seed-1-6T1
General

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.

Price
0.000
cr/req
Uses
948
est.
Rep
0.83
P50
175
ms
Uptime
99.99%
O
@openrouter/bytedance-seed-seed-1-6-flashT1
General

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...

Price
0.000
cr/req
Uses
3.7k
est.
Rep
0.93
P50
367
ms
Uptime
99.73%
O
@openrouter/bytedance-seed-seed-2-0-liteT1
General

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.86
P50
404
ms
Uptime
99.84%
O
@openrouter/bytedance-seed-seed-2-0-miniT1
General

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.87
P50
543
ms
Uptime
99.72%
O
@openrouter/bytedance-ui-tars-1-5-7bT1
General

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.86
P50
644
ms
Uptime
99.71%
O
@openrouter/cognitivecomputations-dolphin-mistral-24b-venice-editionT1
General

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.90
P50
557
ms
Uptime
99.94%
O
@openrouter/cohere-command-aT1
General

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.89
P50
654
ms
Uptime
99.70%
O
@openrouter/cohere-command-r-08-2024T1
General

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.87
P50
180
ms
Uptime
99.96%
O
@openrouter/cohere-command-r-plus-08-2024T1
General

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.87
P50
156
ms
Uptime
99.82%
O
@openrouter/cohere-command-r7b-12-2024T1
General

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.94
P50
381
ms
Uptime
99.77%
O
@openrouter/cohere-north-mini-code-freeT1
General

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.88
P50
277
ms
Uptime
99.81%
O
@openrouter/deepcogito-cogito-v2-1-671bT1
General

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.89
P50
624
ms
Uptime
99.97%
O
@openrouter/deepseek-deepseek-chatT1
General

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.96
P50
617
ms
Uptime
99.86%
O
@openrouter/deepseek-deepseek-chat-v3-0324T1
General

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.90
P50
363
ms
Uptime
99.87%
O
@openrouter/deepseek-deepseek-chat-v3-1T1
General

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.87
P50
151
ms
Uptime
99.90%
O
@openrouter/deepseek-deepseek-r1T1
General

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.96
P50
398
ms
Uptime
99.71%
O
@openrouter/deepseek-deepseek-r1-0528T1
General

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.96
P50
482
ms
Uptime
99.89%
O
@openrouter/deepseek-deepseek-r1-distill-llama-70bT1
General

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.83
P50
247
ms
Uptime
99.85%
O
@openrouter/deepseek-deepseek-v3-1-terminusT1
General

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

Price
0.000
cr/req
Uses
694
est.
Rep
0.92
P50
616
ms
Uptime
99.79%
O
@openrouter/deepseek-deepseek-v3-2T1
General

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.92
P50
574
ms
Uptime
99.90%
O
@openrouter/deepseek-deepseek-v3-2-expT1
General

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.97
P50
310
ms
Uptime
99.73%
O
@openrouter/deepseek-deepseek-v4-flashT1
General

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.91
P50
354
ms
Uptime
99.91%
O
@openrouter/deepseek-deepseek-v4-proT1
General

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.95
P50
478
ms
Uptime
99.80%
O
@openrouter/google-gemini-2-5-flashT1
General

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.96
P50
634
ms
Uptime
99.73%
O
@openrouter/google-gemini-2-5-flash-imageT1
General

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.82
P50
200
ms
Uptime
99.95%
O
@openrouter/google-gemini-2-5-flash-liteT1
General

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.83
P50
344
ms
Uptime
99.71%
O
@openrouter/google-gemini-2-5-proT1
General

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.94
P50
381
ms
Uptime
99.95%
O
@openrouter/google-gemini-2-5-pro-previewT1
General

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.86
P50
138
ms
Uptime
99.84%
O
@openrouter/google-gemini-2-5-pro-preview-05-06T1
General

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Price
0.000
cr/req
Uses
5.0k
est.
Rep
0.96
P50
322
ms
Uptime
99.76%
O
@openrouter/google-gemini-3-1-flash-imageT1
General

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.91
P50
283
ms
Uptime
99.87%
O
@openrouter/google-gemini-3-1-flash-image-previewT1
General

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.85
P50
496
ms
Uptime
99.91%
O
@openrouter/google-gemini-3-1-flash-liteT1
General

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.86
P50
243
ms
Uptime
99.77%
O
@openrouter/google-gemini-3-1-flash-lite-imageT1
General

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.93
P50
245
ms
Uptime
99.91%
O
@openrouter/google-gemini-3-1-flash-lite-previewT1
General

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.85
P50
226
ms
Uptime
99.84%
O
@openrouter/google-gemini-3-1-pro-previewT1
General

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

Price
0.000
cr/req
Uses
1
lifetime
Rep
0.97
P50
263
ms
Uptime
99.78%
O
@openrouter/google-gemini-3-1-pro-preview-customtoolsT1
General

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.83
P50
462
ms
Uptime
99.97%
O
@openrouter/google-gemini-3-5-flashT1
General

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

Price
0.000
cr/req
Uses
206
est.
Rep
0.83
P50
373
ms
Uptime
99.73%
O
@openrouter/google-gemini-3-flash-previewT1
General

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

Price
0.000
cr/req
Uses
6.6k
est.
Rep
0.95
P50
638
ms
Uptime
99.96%
O
@openrouter/google-gemini-3-pro-imageT1
General

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.85
P50
176
ms
Uptime
99.83%
O
@openrouter/google-gemini-3-pro-image-previewT1
General

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.94
P50
418
ms
Uptime
99.98%
O
@openrouter/google-gemini-flash-latestT1
General

This model always redirects to the latest model in the Google Gemini Flash family.

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.87
P50
215
ms
Uptime
99.81%
O
@openrouter/google-gemini-pro-latestT1
General

This model always redirects to the latest model in the Google Gemini Pro family.

Price
0.000
cr/req
Uses
596
est.
Rep
0.85
P50
290
ms
Uptime
99.88%
O
@openrouter/google-gemma-2-27b-itT1
General

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.87
P50
480
ms
Uptime
99.89%
O
@openrouter/google-gemma-3-12b-itT1
General

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Price
0.000
cr/req
Uses
343
est.
Rep
0.85
P50
176
ms
Uptime
99.70%
O
@openrouter/google-gemma-3-27b-itT1
General

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.93
P50
431
ms
Uptime
99.90%
O
@openrouter/google-gemma-3-4b-itT1
General

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.84
P50
550
ms
Uptime
99.97%
O
@openrouter/google-gemma-3n-e4b-itT1
General

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.89
P50
531
ms
Uptime
99.82%
O
@openrouter/google-gemma-4-26b-a4b-itT1
General

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.92
P50
499
ms
Uptime
99.81%
O
@openrouter/google-gemma-4-26b-a4b-it-freeT1
General

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.83
P50
197
ms
Uptime
99.89%
O
@openrouter/google-gemma-4-31b-itT1
General

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.86
P50
176
ms
Uptime
99.94%
O
@openrouter/google-gemma-4-31b-it-freeT1
General

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Price
0.000
cr/req
Uses
362
est.
Rep
0.90
P50
594
ms
Uptime
99.75%
O
@openrouter/google-lyria-3-clip-previewT1
General

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.90
P50
599
ms
Uptime
99.72%
O
@openrouter/google-lyria-3-pro-previewT1
General

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.89
P50
375
ms
Uptime
99.76%
O
@openrouter/gryphe-mythomax-l2-13bT1
General

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.84
P50
470
ms
Uptime
99.71%
O
@openrouter/ibm-granite-granite-4-0-h-microT1
General

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.96
P50
355
ms
Uptime
99.78%
O
@openrouter/ibm-granite-granite-4-1-8bT1
General

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.91
P50
452
ms
Uptime
99.91%
O
@openrouter/inception-mercury-2T1
General

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.98
P50
285
ms
Uptime
99.78%
O
@openrouter/inclusionai-ling-2-6-1tT1
General

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.82
P50
373
ms
Uptime
99.87%
O
@openrouter/inclusionai-ling-2-6-flashT1
General

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.89
P50
450
ms
Uptime
99.78%
O
@openrouter/inclusionai-ring-2-6-1tT1
General

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.94
P50
422
ms
Uptime
99.97%
O
@openrouter/inflection-inflection-3-piT1
General

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.97
P50
639
ms
Uptime
99.71%
O
@openrouter/inflection-inflection-3-productivityT1
General

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional...

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.82
P50
551
ms
Uptime
99.87%
O
@openrouter/kwaipilot-kat-coder-air-v2-5T1
General

KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.95
P50
381
ms
Uptime
99.73%
O
@openrouter/kwaipilot-kat-coder-pro-v2T1
General

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.96
P50
520
ms
Uptime
99.72%
O
@openrouter/kwaipilot-kat-coder-pro-v2-5T1
General

KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...

Price
0.000
cr/req
Uses
792
est.
Rep
0.91
P50
266
ms
Uptime
99.96%
O
@openrouter/mancer-weaverT1
General

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.82
P50
495
ms
Uptime
99.99%
O
@openrouter/meta-llama-llama-3-1-70b-instructT1
General

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.83
P50
276
ms
Uptime
99.97%
O
@openrouter/meta-llama-llama-3-1-8b-instructT1
General

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.92
P50
392
ms
Uptime
99.86%
O
@openrouter/meta-llama-llama-3-2-1b-instructT1
General

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.96
P50
423
ms
Uptime
99.71%
O
@openrouter/meta-llama-llama-3-2-3b-instructT1
General

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.96
P50
318
ms
Uptime
99.77%
O
@openrouter/meta-llama-llama-3-3-70b-instructT1
General

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.96
P50
166
ms
Uptime
99.93%
O
@openrouter/meta-llama-llama-4-maverickT1
General

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Price
0.000
cr/req
Uses
508
est.
Rep
0.93
P50
650
ms
Uptime
99.70%
O
@openrouter/meta-llama-llama-4-scoutT1
General

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.82
P50
521
ms
Uptime
99.88%
O
@openrouter/meta-llama-llama-guard-4-12bT1
General

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.96
P50
461
ms
Uptime
99.81%
O
@openrouter/meta-muse-spark-1-1T1
General

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.92
P50
367
ms
Uptime
99.77%
O
@openrouter/microsoft-phi-4T1
General

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.85
P50
547
ms
Uptime
99.78%
O
@openrouter/microsoft-wizardlm-2-8x22bT1
General

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.91
P50
346
ms
Uptime
99.86%
O
@openrouter/minimax-minimax-01T1
General

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.94
P50
359
ms
Uptime
99.96%
O
@openrouter/minimax-minimax-m1T1
General

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.90
P50
582
ms
Uptime
99.79%
O
@openrouter/minimax-minimax-m2T1
General

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Price
0.000
cr/req
Uses
8.0k
est.
Rep
0.91
P50
569
ms
Uptime
99.79%
O
@openrouter/minimax-minimax-m2-1T1
General

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.87
P50
358
ms
Uptime
99.83%
O
@openrouter/minimax-minimax-m2-5T1
General

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.98
P50
170
ms
Uptime
99.98%
O
@openrouter/minimax-minimax-m2-7T1
General

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.82
P50
530
ms
Uptime
99.83%
O
@openrouter/minimax-minimax-m2-herT1
General

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.84
P50
441
ms
Uptime
99.89%
O
@openrouter/minimax-minimax-m3T1
General

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.89
P50
138
ms
Uptime
99.94%
O
@openrouter/mistralai-codestral-2508T1
General

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Price
0.000
cr/req
Uses
6.0k
est.
Rep
0.93
P50
604
ms
Uptime
99.93%
O
@openrouter/mistralai-devstral-2512T1
General

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.86
P50
610
ms
Uptime
99.92%
O
@openrouter/mistralai-ministral-14b-2512T1
General

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.85
P50
403
ms
Uptime
99.74%
O
@openrouter/mistralai-ministral-3b-2512T1
General

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Price
0.000
cr/req
Uses
7.8k
est.
Rep
0.92
P50
283
ms
Uptime
99.76%
O
@openrouter/mistralai-ministral-8b-2512T1
General

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.89
P50
476
ms
Uptime
99.73%
O
@openrouter/mistralai-mistral-largeT1
General

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.92
P50
595
ms
Uptime
99.72%
O
@openrouter/mistralai-mistral-large-2407T1
General

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

Price
0.000
cr/req
Uses
801
est.
Rep
0.86
P50
463
ms
Uptime
99.98%
O
@openrouter/mistralai-mistral-large-2512T1
General

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.89
P50
135
ms
Uptime
99.78%
O
@openrouter/mistralai-mistral-medium-3T1
General

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.83
P50
382
ms
Uptime
99.98%
O
@openrouter/mistralai-mistral-medium-3-1T1
General

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.92
P50
283
ms
Uptime
99.91%
O
@openrouter/mistralai-mistral-medium-3-5T1
General

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.89
P50
333
ms
Uptime
99.84%
O
@openrouter/mistralai-mistral-nemoT1
General

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.85
P50
239
ms
Uptime
99.91%
O
@openrouter/mistralai-mistral-sabaT1
General

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

Price
0.000
cr/req
Uses
909
est.
Rep
0.86
P50
243
ms
Uptime
99.91%
O
@openrouter/mistralai-mistral-small-24b-instruct-2501T1
General

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.86
P50
594
ms
Uptime
99.83%
O
@openrouter/mistralai-mistral-small-2603T1
General

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

Price
0.000
cr/req
Uses
7.4k
est.
Rep
0.83
P50
348
ms
Uptime
99.87%
O
@openrouter/mistralai-mistral-small-3-1-24b-instructT1
General

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.95
P50
263
ms
Uptime
99.94%
O
@openrouter/mistralai-mistral-small-3-2-24b-instructT1
General

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.93
P50
220
ms
Uptime
99.95%
O
@openrouter/mistralai-mixtral-8x22b-instructT1
General

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.96
P50
149
ms
Uptime
99.85%
O
@openrouter/mistralai-voxtral-small-24b-2507T1
General

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.85
P50
463
ms
Uptime
99.94%
O
@openrouter/moonshotai-kimi-k2T1
General

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.89
P50
274
ms
Uptime
99.81%
O
@openrouter/moonshotai-kimi-k2-0905T1
General

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.97
P50
377
ms
Uptime
99.91%
O
@openrouter/moonshotai-kimi-k2-5T1
General

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.92
P50
460
ms
Uptime
99.92%
O
@openrouter/moonshotai-kimi-k2-6T1
General

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.94
P50
377
ms
Uptime
99.88%
O
@openrouter/moonshotai-kimi-k2-7-codeT1
General

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Price
0.000
cr/req
Uses
6.9k
est.
Rep
0.83
P50
352
ms
Uptime
99.73%
O
@openrouter/moonshotai-kimi-k2-thinkingT1
General

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.82
P50
399
ms
Uptime
99.81%
O
@openrouter/moonshotai-kimi-k3T1
General

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.93
P50
465
ms
Uptime
99.84%
O
@openrouter/moonshotai-kimi-latestT1
General

This model always redirects to the latest model in the MoonshotAI Kimi family.

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.92
P50
418
ms
Uptime
99.97%
O
@openrouter/morph-morph-v3-fastT1
General

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

Price
0.000
cr/req
Uses
206
est.
Rep
0.89
P50
565
ms
Uptime
99.72%
O
@openrouter/morph-morph-v3-largeT1
General

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.92
P50
418
ms
Uptime
99.70%
O
@openrouter/nex-agi-nex-n2-miniT1
General

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.90
P50
312
ms
Uptime
99.76%
O
@openrouter/nex-agi-nex-n2-proT1
General

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.93
P50
562
ms
Uptime
99.96%
O
@openrouter/nousresearch-hermes-3-llama-3-1-405bT1
General

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Price
0.000
cr/req
Uses
9.0k
est.
Rep
0.87
P50
265
ms
Uptime
99.86%
O
@openrouter/nousresearch-hermes-3-llama-3-1-70bT1
General

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.87
P50
286
ms
Uptime
99.85%
O
@openrouter/nousresearch-hermes-4-405bT1
General

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.86
P50
530
ms
Uptime
99.87%
O
@openrouter/nousresearch-hermes-4-70bT1
General

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

Price
0.000
cr/req
Uses
606
est.
Rep
0.97
P50
503
ms
Uptime
99.92%
O
@openrouter/nvidia-nemotron-3-5-content-safety-freeT1
General

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.97
P50
352
ms
Uptime
99.77%
O
@openrouter/nvidia-nemotron-3-nano-30b-a3bT1
General

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Price
0.000
cr/req
Uses
6.3k
est.
Rep
0.87
P50
657
ms
Uptime
99.78%
O
@openrouter/nvidia-nemotron-3-nano-30b-a3b-freeT1
General

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.96
P50
208
ms
Uptime
99.76%
O
@openrouter/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-freeT1
General

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.85
P50
400
ms
Uptime
99.85%
O
@openrouter/nvidia-nemotron-3-super-120b-a12bT1
General

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.90
P50
211
ms
Uptime
99.85%
O
@openrouter/nvidia-nemotron-3-super-120b-a12b-freeT1
General

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.97
P50
478
ms
Uptime
99.83%
O
@openrouter/nvidia-nemotron-3-ultra-550b-a55bT1
General

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.87
P50
357
ms
Uptime
99.91%
O
@openrouter/nvidia-nemotron-3-ultra-550b-a55b-freeT1
General

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.96
P50
242
ms
Uptime
99.95%
O
@openrouter/nvidia-nemotron-nano-12b-v2-vl-freeT1
General

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

Price
0.000
cr/req
Uses
5.3k
est.
Rep
0.88
P50
312
ms
Uptime
99.84%
O
@openrouter/nvidia-nemotron-nano-9b-v2-freeT1
General

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.86
P50
551
ms
Uptime
99.93%
O
@openrouter/openai-gpt-3-5-turboT1
General

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Price
0.000
cr/req
Uses
7.3k
est.
Rep
0.88
P50
252
ms
Uptime
99.81%
O
@openrouter/openai-gpt-3-5-turbo-0613T1
General

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.83
P50
217
ms
Uptime
99.95%
O
@openrouter/openai-gpt-3-5-turbo-16kT1
General

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

Price
0.000
cr/req
Uses
4.4k
est.
Rep
0.87
P50
202
ms
Uptime
99.90%
O
@openrouter/openai-gpt-3-5-turbo-instructT1
General

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Price
0.000
cr/req
Uses
4.6k
est.
Rep
0.95
P50
659
ms
Uptime
99.91%
O
@openrouter/openai-gpt-4T1
General

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

Price
0.000
cr/req
Uses
196
est.
Rep
0.82
P50
542
ms
Uptime
99.72%
O
@openrouter/openai-gpt-4-1T1
General

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.82
P50
301
ms
Uptime
99.86%
O
@openrouter/openai-gpt-4-1-miniT1
General

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.88
P50
636
ms
Uptime
99.87%
O
@openrouter/openai-gpt-4-1-nanoT1
General

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Price
0.000
cr/req
Uses
2.3k
est.
Rep
0.97
P50
208
ms
Uptime
99.86%
O
@openrouter/openai-gpt-4-turboT1
General

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Price
0.000
cr/req
Uses
9.4k
est.
Rep
0.85
P50
163
ms
Uptime
99.92%
O
@openrouter/openai-gpt-4-turbo-previewT1
General

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...

Price
0.000
cr/req
Uses
128
est.
Rep
0.87
P50
640
ms
Uptime
99.87%
O
@openrouter/openai-gpt-4oT1
General

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

Price
0.000
cr/req
Uses
499
est.
Rep
0.96
P50
305
ms
Uptime
99.71%
O
@openrouter/openai-gpt-4o-2024-05-13T1
General

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.97
P50
352
ms
Uptime
99.77%
O
@openrouter/openai-gpt-4o-2024-08-06T1
General

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.88
P50
598
ms
Uptime
99.73%
O
@openrouter/openai-gpt-4o-2024-11-20T1
General

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...

Price
0.000
cr/req
Uses
9.7k
est.
Rep
0.98
P50
297
ms
Uptime
99.85%
O
@openrouter/openai-gpt-4o-miniT1
General

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.95
P50
212
ms
Uptime
99.79%
O
@openrouter/openai-gpt-4o-mini-2024-07-18T1
General

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.84
P50
483
ms
Uptime
99.80%
O
@openrouter/openai-gpt-4o-mini-search-previewT1
General

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.88
P50
143
ms
Uptime
99.89%
O
@openrouter/openai-gpt-4o-search-previewT1
General

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.84
P50
301
ms
Uptime
99.87%
O
@openrouter/openai-gpt-5T1
General

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.82
P50
137
ms
Uptime
99.78%
O
@openrouter/openai-gpt-5-1T1
General

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

Price
0.000
cr/req
Uses
3.2k
est.
Rep
0.97
P50
462
ms
Uptime
99.93%
O
@openrouter/openai-gpt-5-1-chatT1
General

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.94
P50
393
ms
Uptime
99.98%
O
@openrouter/openai-gpt-5-1-codexT1
General

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Price
0.000
cr/req
Uses
2.7k
est.
Rep
0.83
P50
411
ms
Uptime
99.78%
O
@openrouter/openai-gpt-5-1-codex-maxT1
General

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.84
P50
277
ms
Uptime
99.80%
O
@openrouter/openai-gpt-5-1-codex-miniT1
General

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.93
P50
591
ms
Uptime
99.80%
O
@openrouter/openai-gpt-5-2T1
General

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

Price
0.000
cr/req
Uses
1.0k
est.
Rep
0.91
P50
355
ms
Uptime
99.78%
O
@openrouter/openai-gpt-5-2-chatT1
General

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.88
P50
257
ms
Uptime
99.82%
O
@openrouter/openai-gpt-5-2-codexT1
General

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Price
0.000
cr/req
Uses
89
est.
Rep
0.84
P50
644
ms
Uptime
99.78%
O
@openrouter/openai-gpt-5-2-proT1
General

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

Price
0.000
cr/req
Uses
684
est.
Rep
0.96
P50
263
ms
Uptime
99.77%
O
@openrouter/openai-gpt-5-3-chatT1
General

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...

Price
0.000
cr/req
Uses
8.6k
est.
Rep
0.82
P50
635
ms
Uptime
99.98%
O
@openrouter/openai-gpt-5-3-codexT1
General

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

Price
0.000
cr/req
Uses
2.6k
est.
Rep
0.96
P50
407
ms
Uptime
99.93%
O
@openrouter/openai-gpt-5-4T1
General

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.84
P50
357
ms
Uptime
99.83%
O
@openrouter/openai-gpt-5-4-image-2T1
General

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.97
P50
449
ms
Uptime
99.89%
O
@openrouter/openai-gpt-5-4-miniT1
General

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

Price
0.000
cr/req
Uses
2.9k
est.
Rep
0.83
P50
627
ms
Uptime
99.71%
O
@openrouter/openai-gpt-5-4-nanoT1
General

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

Price
0.000
cr/req
Uses
645
est.
Rep
0.87
P50
303
ms
Uptime
99.97%
O
@openrouter/openai-gpt-5-4-proT1
General

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.89
P50
202
ms
Uptime
99.75%
O
@openrouter/openai-gpt-5-5T1
General

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

Price
0.000
cr/req
Uses
6.4k
est.
Rep
0.92
P50
338
ms
Uptime
99.71%
O
@openrouter/openai-gpt-5-5-proT1
General

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

Price
0.000
cr/req
Uses
8.9k
est.
Rep
0.86
P50
260
ms
Uptime
99.81%
O
@openrouter/openai-gpt-5-6-lunaT1
General

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.86
P50
577
ms
Uptime
99.98%
O
@openrouter/openai-gpt-5-6-luna-proT1
General

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Price
0.000
cr/req
Uses
9.1k
est.
Rep
0.83
P50
310
ms
Uptime
99.77%
O
@openrouter/openai-gpt-5-6-solT1
General

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.90
P50
587
ms
Uptime
99.83%
O
@openrouter/openai-gpt-5-6-sol-proT1
General

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.97
P50
128
ms
Uptime
99.77%
O
@openrouter/openai-gpt-5-6-terraT1
General

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.84
P50
555
ms
Uptime
99.87%
O
@openrouter/openai-gpt-5-6-terra-proT1
General

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Price
0.000
cr/req
Uses
977
est.
Rep
0.90
P50
388
ms
Uptime
99.73%
O
@openrouter/openai-gpt-5-chatT1
General

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

Price
0.000
cr/req
Uses
577
est.
Rep
0.84
P50
474
ms
Uptime
99.85%
O
@openrouter/openai-gpt-5-codexT1
General

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Price
0.000
cr/req
Uses
616
est.
Rep
0.89
P50
459
ms
Uptime
99.93%
O
@openrouter/openai-gpt-5-imageT1
General

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

Price
0.000
cr/req
Uses
79
est.
Rep
0.94
P50
562
ms
Uptime
99.76%
O
@openrouter/openai-gpt-5-image-miniT1
General

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.93
P50
216
ms
Uptime
99.92%
O
@openrouter/openai-gpt-5-miniT1
General

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.93
P50
304
ms
Uptime
99.78%
O
@openrouter/openai-gpt-5-nanoT1
General

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Price
0.000
cr/req
Uses
7.6k
est.
Rep
0.82
P50
153
ms
Uptime
99.80%
O
@openrouter/openai-gpt-5-proT1
General

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...

Price
0.000
cr/req
Uses
3.9k
est.
Rep
0.83
P50
504
ms
Uptime
99.79%
O
@openrouter/openai-gpt-audioT1
General

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.84
P50
353
ms
Uptime
99.74%
O
@openrouter/openai-gpt-audio-miniT1
General

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

Price
0.000
cr/req
Uses
323
est.
Rep
0.96
P50
314
ms
Uptime
99.95%
O
@openrouter/openai-gpt-chat-latestT1
General

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...

Price
0.000
cr/req
Uses
3.4k
est.
Rep
0.94
P50
339
ms
Uptime
99.71%
O
@openrouter/openai-gpt-latestT1
General

This model always redirects to the latest model in the OpenAI GPT family.

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.89
P50
320
ms
Uptime
99.93%
O
@openrouter/openai-gpt-mini-latestT1
General

This model always redirects to the latest model in the OpenAI GPT Mini family.

Price
0.000
cr/req
Uses
1.1k
est.
Rep
0.86
P50
315
ms
Uptime
99.76%
O
@openrouter/openai-gpt-oss-120bT1
General

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Price
0.000
cr/req
Uses
294
est.
Rep
0.96
P50
444
ms
Uptime
99.91%
O
@openrouter/openai-gpt-oss-20bT1
General

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Price
0.000
cr/req
Uses
518
est.
Rep
0.85
P50
218
ms
Uptime
99.75%
O
@openrouter/openai-gpt-oss-20b-freeT1
General

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.90
P50
460
ms
Uptime
99.89%
O
@openrouter/openai-gpt-oss-safeguard-20bT1
General

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.83
P50
264
ms
Uptime
99.76%
O
@openrouter/openai-o1T1
General

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.97
P50
601
ms
Uptime
99.79%
O
@openrouter/openai-o1-proT1
General

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.86
P50
636
ms
Uptime
99.93%
O
@openrouter/openai-o3T1
General

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

Price
0.000
cr/req
Uses
3.8k
est.
Rep
0.94
P50
515
ms
Uptime
99.99%
O
@openrouter/openai-o3-deep-researchT1
General

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Price
0.000
cr/req
Uses
3.6k
est.
Rep
0.96
P50
609
ms
Uptime
99.73%
O
@openrouter/openai-o3-miniT1
General

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.87
P50
459
ms
Uptime
99.90%
O
@openrouter/openai-o3-mini-highT1
General

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.96
P50
178
ms
Uptime
99.80%
O
@openrouter/openai-o3-proT1
General

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

Price
0.000
cr/req
Uses
4.8k
est.
Rep
0.84
P50
138
ms
Uptime
99.76%
O
@openrouter/openai-o4-miniT1
General

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Price
0.000
cr/req
Uses
616
est.
Rep
0.96
P50
157
ms
Uptime
99.93%
O
@openrouter/openai-o4-mini-deep-researchT1
General

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.96
P50
647
ms
Uptime
99.92%
O
@openrouter/openai-o4-mini-highT1
General

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.86
P50
585
ms
Uptime
99.85%
O
@openrouter/openrouter-autoT1
General

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.93
P50
330
ms
Uptime
99.73%
O
@openrouter/openrouter-auto-betaT1
General

Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...

Price
0.000
cr/req
Uses
6.2k
est.
Rep
0.88
P50
282
ms
Uptime
99.90%
O
@openrouter/openrouter-bodybuilderT1
General

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

Price
0.000
cr/req
Uses
5.1k
est.
Rep
0.97
P50
166
ms
Uptime
99.74%
O
@openrouter/openrouter-freeT1
General

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.87
P50
543
ms
Uptime
99.87%
O
@openrouter/openrouter-fusionT1
General

Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...

Price
0.000
cr/req
Uses
9.3k
est.
Rep
0.96
P50
225
ms
Uptime
99.86%
O
@openrouter/openrouter-pareto-codeT1
General

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...

Price
0.000
cr/req
Uses
8.7k
est.
Rep
0.84
P50
179
ms
Uptime
99.91%
O
@openrouter/perceptron-perceptron-mk1T1
General

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.86
P50
273
ms
Uptime
99.86%
O
@openrouter/perplexity-sonarT1
General

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

Price
0.000
cr/req
Uses
13
lifetime
Rep
0.96
P50
183
ms
Uptime
99.77%
O
@openrouter/perplexity-sonar-deep-researchT1
General

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.97
P50
365
ms
Uptime
99.97%
O
@openrouter/perplexity-sonar-proT1
General

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

Price
0.000
cr/req
Uses
430
est.
Rep
0.91
P50
507
ms
Uptime
99.85%
O
@openrouter/perplexity-sonar-pro-searchT1
General

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...

Price
0.000
cr/req
Uses
2
lifetime
Rep
0.84
P50
196
ms
Uptime
99.73%
O
@openrouter/perplexity-sonar-reasoning-proT1
General

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.92
P50
186
ms
Uptime
99.99%
O
@openrouter/poolside-laguna-m-1T1
General

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.97
P50
221
ms
Uptime
99.80%
O
@openrouter/poolside-laguna-m-1-freeT1
General

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...

Price
0.000
cr/req
Uses
8.2k
est.
Rep
0.97
P50
394
ms
Uptime
99.92%
O
@openrouter/poolside-laguna-xs-2-1T1
General

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.83
P50
192
ms
Uptime
99.93%
O
@openrouter/poolside-laguna-xs-2-1-freeT1
General

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.84
P50
353
ms
Uptime
99.84%
O
@openrouter/qwen-qwen-2-5-72b-instructT1
General

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Price
0.000
cr/req
Uses
1.4k
est.
Rep
0.89
P50
173
ms
Uptime
99.94%
O
@openrouter/qwen-qwen-2-5-7b-instructT1
General

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.83
P50
428
ms
Uptime
99.98%
O
@openrouter/qwen-qwen-2-5-coder-32b-instructT1
General

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.88
P50
577
ms
Uptime
99.84%
O
@openrouter/qwen-qwen-plusT1
General

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

Price
0.000
cr/req
Uses
7.9k
est.
Rep
0.98
P50
212
ms
Uptime
99.78%
O
@openrouter/qwen-qwen-plus-2025-07-28T1
General

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Price
0.000
cr/req
Uses
421
est.
Rep
0.83
P50
554
ms
Uptime
99.86%
O
@openrouter/qwen-qwen-plus-2025-07-28-thinkingT1
General

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Price
0.000
cr/req
Uses
909
est.
Rep
0.91
P50
405
ms
Uptime
99.90%
O
@openrouter/qwen-qwen2-5-vl-72b-instructT1
General

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

Price
0.000
cr/req
Uses
2.2k
est.
Rep
0.86
P50
299
ms
Uptime
99.81%
O
@openrouter/qwen-qwen3-14bT1
General

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.94
P50
571
ms
Uptime
99.91%
O
@openrouter/qwen-qwen3-235b-a22bT1
General

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.98
P50
462
ms
Uptime
99.98%
O
@openrouter/qwen-qwen3-235b-a22b-2507T1
General

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.88
P50
375
ms
Uptime
99.91%
O
@openrouter/qwen-qwen3-235b-a22b-thinking-2507T1
General

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Price
0.000
cr/req
Uses
7.5k
est.
Rep
0.84
P50
280
ms
Uptime
99.97%
O
@openrouter/qwen-qwen3-30b-a3bT1
General

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.82
P50
597
ms
Uptime
99.91%
O
@openrouter/qwen-qwen3-30b-a3b-instruct-2507T1
General

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.84
P50
327
ms
Uptime
99.75%
O
@openrouter/qwen-qwen3-30b-a3b-thinking-2507T1
General

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Price
0.000
cr/req
Uses
674
est.
Rep
0.90
P50
173
ms
Uptime
99.74%
O
@openrouter/qwen-qwen3-32bT1
General

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Price
0.000
cr/req
Uses
977
est.
Rep
0.82
P50
483
ms
Uptime
99.73%
O
@openrouter/qwen-qwen3-5-122b-a10bT1
General

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

Price
0.000
cr/req
Uses
3.5k
est.
Rep
0.86
P50
564
ms
Uptime
99.84%
O
@openrouter/qwen-qwen3-5-27bT1
General

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...

Price
0.000
cr/req
Uses
4.1k
est.
Rep
0.90
P50
459
ms
Uptime
99.95%
O
@openrouter/qwen-qwen3-5-35b-a3bT1
General

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

Price
0.000
cr/req
Uses
138
est.
Rep
0.98
P50
120
ms
Uptime
99.87%
O
@openrouter/qwen-qwen3-5-397b-a17bT1
General

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.93
P50
625
ms
Uptime
99.73%
O
@openrouter/qwen-qwen3-5-9bT1
General

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.85
P50
450
ms
Uptime
99.93%
O
@openrouter/qwen-qwen3-5-flash-02-23T1
General

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

Price
0.000
cr/req
Uses
8.3k
est.
Rep
0.89
P50
502
ms
Uptime
99.78%
O
@openrouter/qwen-qwen3-5-plus-02-15T1
General

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.86
P50
522
ms
Uptime
99.98%
O
@openrouter/qwen-qwen3-5-plus-20260420T1
General

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.84
P50
357
ms
Uptime
99.83%
O
@openrouter/qwen-qwen3-6-27bT1
General

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

Price
0.000
cr/req
Uses
1.9k
est.
Rep
0.82
P50
121
ms
Uptime
99.75%
O
@openrouter/qwen-qwen3-6-35b-a3bT1
General

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Price
0.000
cr/req
Uses
9.8k
est.
Rep
0.95
P50
276
ms
Uptime
99.95%
O
@openrouter/qwen-qwen3-6-flashT1
General

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...

Price
0.000
cr/req
Uses
5.9k
est.
Rep
0.88
P50
211
ms
Uptime
99.90%
O
@openrouter/qwen-qwen3-6-max-previewT1
General

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.90
P50
498
ms
Uptime
99.89%
O
@openrouter/qwen-qwen3-6-plusT1
General

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

Price
0.000
cr/req
Uses
1.7k
est.
Rep
0.84
P50
259
ms
Uptime
99.93%
O
@openrouter/qwen-qwen3-7-maxT1
General

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

Price
0.000
cr/req
Uses
440
est.
Rep
0.83
P50
145
ms
Uptime
99.88%
O
@openrouter/qwen-qwen3-7-plusT1
General

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

Price
0.000
cr/req
Uses
3.1k
est.
Rep
0.94
P50
170
ms
Uptime
99.99%
O
@openrouter/qwen-qwen3-8bT1
General

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.85
P50
222
ms
Uptime
99.95%
O
@openrouter/qwen-qwen3-coderT1
General

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

Price
0.000
cr/req
Uses
5.6k
est.
Rep
0.98
P50
276
ms
Uptime
99.74%
O
@openrouter/qwen-qwen3-coder-30b-a3b-instructT1
General

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.85
P50
290
ms
Uptime
99.74%
O
@openrouter/qwen-qwen3-coder-flashT1
General

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

Price
0.000
cr/req
Uses
5.2k
est.
Rep
0.83
P50
479
ms
Uptime
99.71%
O
@openrouter/qwen-qwen3-coder-nextT1
General

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Price
0.000
cr/req
Uses
5.7k
est.
Rep
0.87
P50
463
ms
Uptime
99.75%
O
@openrouter/qwen-qwen3-coder-plusT1
General

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.93
P50
292
ms
Uptime
99.92%
O
@openrouter/qwen-qwen3-maxT1
General

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.91
P50
270
ms
Uptime
99.72%
O
@openrouter/qwen-qwen3-max-thinkingT1
General

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.90
P50
156
ms
Uptime
99.96%
O
@openrouter/qwen-qwen3-next-80b-a3b-instructT1
General

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Price
0.000
cr/req
Uses
8.4k
est.
Rep
0.93
P50
503
ms
Uptime
99.71%
O
@openrouter/qwen-qwen3-next-80b-a3b-thinkingT1
General

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.89
P50
155
ms
Uptime
99.77%
O
@openrouter/qwen-qwen3-vl-235b-a22b-instructT1
General

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Price
0.000
cr/req
Uses
7.7k
est.
Rep
0.90
P50
489
ms
Uptime
99.80%
O
@openrouter/qwen-qwen3-vl-235b-a22b-thinkingT1
General

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

Price
0.000
cr/req
Uses
8.5k
est.
Rep
0.96
P50
651
ms
Uptime
99.82%
O
@openrouter/qwen-qwen3-vl-30b-a3b-instructT1
General

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.87
P50
551
ms
Uptime
99.84%
O
@openrouter/qwen-qwen3-vl-30b-a3b-thinkingT1
General

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

Price
0.000
cr/req
Uses
9.2k
est.
Rep
0.90
P50
283
ms
Uptime
99.97%
O
@openrouter/qwen-qwen3-vl-32b-instructT1
General

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...

Price
0.000
cr/req
Uses
3.3k
est.
Rep
0.87
P50
627
ms
Uptime
99.85%
O
@openrouter/qwen-qwen3-vl-8b-instructT1
General

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

Price
0.000
cr/req
Uses
7.2k
est.
Rep
0.91
P50
511
ms
Uptime
99.72%
O
@openrouter/qwen-qwen3-vl-8b-thinkingT1
General

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

Price
0.000
cr/req
Uses
587
est.
Rep
0.96
P50
140
ms
Uptime
99.89%
O
@openrouter/rekaai-reka-edgeT1
General

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

Price
0.000
cr/req
Uses
1.6k
est.
Rep
0.89
P50
240
ms
Uptime
99.97%
O
@openrouter/rekaai-reka-flash-3T1
General

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.84
P50
298
ms
Uptime
99.99%
O
@openrouter/relace-relace-apply-3T1
General

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

Price
0.000
cr/req
Uses
1.5k
est.
Rep
0.83
P50
517
ms
Uptime
99.87%
O
@openrouter/relace-relace-searchT1
General

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.88
P50
240
ms
Uptime
99.80%
O
@openrouter/sakana-fugu-ultraT1
General

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

Price
0.000
cr/req
Uses
8.1k
est.
Rep
0.93
P50
317
ms
Uptime
99.97%
O
@openrouter/sao10k-l3-1-euryale-70bT1
General

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).

Price
0.000
cr/req
Uses
5.4k
est.
Rep
0.94
P50
562
ms
Uptime
99.84%
O
@openrouter/sao10k-l3-3-euryale-70bT1
General

Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).

Price
0.000
cr/req
Uses
460
est.
Rep
0.94
P50
537
ms
Uptime
99.91%
O
@openrouter/sao10k-l3-lunaris-8bT1
General

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

Price
0.000
cr/req
Uses
6.5k
est.
Rep
0.94
P50
427
ms
Uptime
99.87%
O
@openrouter/stepfun-step-3-5-flashT1
General

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Price
0.000
cr/req
Uses
3.0k
est.
Rep
0.97
P50
406
ms
Uptime
99.75%
O
@openrouter/stepfun-step-3-7-flashT1
General

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

Price
0.000
cr/req
Uses
1.8k
est.
Rep
0.91
P50
346
ms
Uptime
99.80%
O
@openrouter/tencent-hunyuan-a13b-instructT1
General

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.87
P50
561
ms
Uptime
99.72%
O
@openrouter/tencent-hy3T1
General

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

Price
0.000
cr/req
Uses
5.5k
est.
Rep
0.89
P50
374
ms
Uptime
99.74%
O
@openrouter/tencent-hy3-freeT1
General

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.84
P50
446
ms
Uptime
99.89%
O
@openrouter/tencent-hy3-previewT1
General

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

Price
0.000
cr/req
Uses
372
est.
Rep
0.82
P50
508
ms
Uptime
99.76%
O
@openrouter/thedrummer-cydonia-24b-v4-1T1
General

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

Price
0.000
cr/req
Uses
9.5k
est.
Rep
0.95
P50
364
ms
Uptime
99.76%
O
@openrouter/thedrummer-rocinante-12bT1
General

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...

Price
0.000
cr/req
Uses
6.7k
est.
Rep
0.96
P50
500
ms
Uptime
99.96%
O
@openrouter/thedrummer-skyfall-36b-v2T1
General

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

Price
0.000
cr/req
Uses
7.1k
est.
Rep
0.84
P50
500
ms
Uptime
99.83%
O
@openrouter/thedrummer-unslopnemo-12bT1
General

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

Price
0.000
cr/req
Uses
616
est.
Rep
0.92
P50
650
ms
Uptime
99.91%
O
@openrouter/thinkingmachines-inklingT1
General

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Price
0.000
cr/req
Uses
2.1k
est.
Rep
0.96
P50
368
ms
Uptime
99.93%
O
@openrouter/undi95-remm-slerp-l2-13bT1
General

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

Price
0.000
cr/req
Uses
9.6k
est.
Rep
0.91
P50
489
ms
Uptime
99.88%
O
@openrouter/upstage-solar-pro-3T1
General

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...

Price
0.000
cr/req
Uses
7.0k
est.
Rep
0.94
P50
562
ms
Uptime
99.86%
O
@openrouter/writer-palmyra-x5T1
General

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...

Price
0.000
cr/req
Uses
1.3k
est.
Rep
0.91
P50
629
ms
Uptime
99.72%
O
@openrouter/x-ai-grok-4-20T1
General

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.92
P50
207
ms
Uptime
99.87%
O
@openrouter/x-ai-grok-4-20-multi-agentT1
General

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...

Price
0.000
cr/req
Uses
264
est.
Rep
0.83
P50
184
ms
Uptime
99.82%
O
@openrouter/x-ai-grok-4-3T1
General

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

Price
0.000
cr/req
Uses
2.8k
est.
Rep
0.97
P50
601
ms
Uptime
99.79%
O
@openrouter/x-ai-grok-4-5T1
General

Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Price
0.000
cr/req
Uses
4.2k
est.
Rep
0.83
P50
571
ms
Uptime
99.79%
O
@openrouter/x-ai-grok-build-0-1T1
General

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

Price
0.000
cr/req
Uses
4.7k
est.
Rep
0.89
P50
227
ms
Uptime
99.96%
O
@openrouter/x-ai-grok-latestT1
General

This model always redirects to the latest Grok model from xAI.

Price
0.000
cr/req
Uses
4.0k
est.
Rep
0.86
P50
442
ms
Uptime
99.96%
O
@openrouter/xiaomi-mimo-v2-5T1
General

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

Price
0.000
cr/req
Uses
343
est.
Rep
0.90
P50
249
ms
Uptime
99.97%
O
@openrouter/xiaomi-mimo-v2-5-proT1
General

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.86
P50
303
ms
Uptime
99.86%
O
@openrouter/z-ai-glm-4-5T1
General

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Price
0.000
cr/req
Uses
2.5k
est.
Rep
0.96
P50
259
ms
Uptime
99.79%
O
@openrouter/z-ai-glm-4-5-airT1
General

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

Price
0.000
cr/req
Uses
479
est.
Rep
0.85
P50
244
ms
Uptime
99.94%
O
@openrouter/z-ai-glm-4-5vT1
General

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

Price
0.000
cr/req
Uses
5.8k
est.
Rep
0.98
P50
563
ms
Uptime
99.86%
O
@openrouter/z-ai-glm-4-6T1
General

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

Price
0.000
cr/req
Uses
6.8k
est.
Rep
0.84
P50
563
ms
Uptime
99.76%
O
@openrouter/z-ai-glm-4-6vT1
General

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

Price
0.000
cr/req
Uses
704
est.
Rep
0.85
P50
247
ms
Uptime
99.80%
O
@openrouter/z-ai-glm-4-7T1
General

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

Price
0.000
cr/req
Uses
4.5k
est.
Rep
0.97
P50
242
ms
Uptime
99.85%
O
@openrouter/z-ai-glm-4-7-flashT1
General

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

Price
0.000
cr/req
Uses
4.3k
est.
Rep
0.82
P50
293
ms
Uptime
99.95%
O
@openrouter/z-ai-glm-5T1
General

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Price
0.000
cr/req
Uses
2.0k
est.
Rep
0.91
P50
642
ms
Uptime
99.70%
O
@openrouter/z-ai-glm-5-1T1
General

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

Price
0.000
cr/req
Uses
538
est.
Rep
0.84
P50
373
ms
Uptime
99.78%
O
@openrouter/z-ai-glm-5-2T1
General

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Price
0.000
cr/req
Uses
4.9k
est.
Rep
0.88
P50
315
ms
Uptime
99.73%
O
@openrouter/z-ai-glm-5-turboT1
General

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

Price
0.000
cr/req
Uses
8.8k
est.
Rep
0.85
P50
483
ms
Uptime
99.87%
O
@openrouter/z-ai-glm-5v-turboT1
General

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

Price
0.000
cr/req
Uses
1.2k
est.
Rep
0.83
P50
539
ms
Uptime
99.80%