What AI models are available on ModelsLab?

ModelsLab offers 10,000+ AI models including text-to-image (Stable Diffusion, FLUX, SDXL), text-to-video, text-to-audio, 3D generation, voice cloning, and LLM APIs from providers like Alibaba, Google, Meta, and more.

How do I get started with ModelsLab APIs?

Create an account, choose a plan from $21/month, then get your API key from the dashboard and start making API calls. We provide SDKs for Python, JavaScript, and cURL examples for every model.

What are the pricing options for ModelsLab?

ModelsLab plans start at $21/month (Basic), with the $149/month Open Source plan covering unlimited generation on open-source models. Enterprise plans with custom pricing and dedicated support are also available.

What programming languages are supported?

ModelsLab APIs work with any language that can make HTTP requests — Python, JavaScript, PHP, Ruby, Go, Rust, Java, and more. We provide official SDKs, CLI tools, and MCP server integrations.

Do you offer API documentation?

Yes, every model on ModelsLab has comprehensive API documentation with code examples, parameter descriptions, and integration guides available at docs.modelslab.com and on each model's API Documentation tab.

Generative AI Platform | AI APIs for Image, Video, Audio & LLMs

GPT Image 2.5 transforms how images get edited. Upload any photo — a product shot, portrait, marketing asset, or personal image — and simply describe what you want changed. Swap the background, adjust lighting, remove objects, add readable text.

Closed SourceNew AddedBest for Filmmakers+1

GPT Image 2.5 is OpenAI's most advanced text-to-image model. Describe any scene, concept, poster, product visual, or creative idea in plain language — and the model thinks through your brief, plans the layout.

Closed SourceNew AddedBest for Creators+1

GPT Image 2.5 transforms how images get edited. Upload any photo — a product shot, portrait, marketing asset, or personal image — and simply describe what you want changed. Swap the background, adjust lighting, remove objects, add readable text.

Closed SourceNew AddedBest for Creators+1

GPT Image 2.5 is OpenAI's most advanced text-to-image model. Describe any scene, concept, poster, product visual, or creative idea in plain language — and the model thinks through your brief, plans the layout.

Closed SourceNew AddedBest for Creators+1

Feed Wan 3.0 one or more reference images and generate video that keeps faces, characters, and objects consistent shot after shot — ideal for branded content, avatars, and multi-scene storytelling via the ModelsLab API.

Closed SourceAnimate Your ImageBest for Filmmakers+1

Bring any photo to life with Wan 3.0's image-to-video model. Upload a source image, describe the motion, and get a smooth, physically consistent AI video — built for product, portrait, and creative animation via the ModelsLab API.

Closed SourceAnimate Your ImageBest for Filmmakers+1

Turn any text prompt into a cinematic AI video with Wan 3.0 — Alibaba's next-gen video model. Sharper motion, longer clips, and stronger prompt adherence than Wan 2.5, available now via the ModelsLab API.

Closed SourceAnimate Your ImageBest for Filmmakers+1

MiniMax H3 is an open-weight multimodal AI video generation model capable of creating up to 15-second videos with native stereo audio from text, images, video, and audio inputs. It supports text-to-video, image-to-video, video editing, and video-to-video

Open Source

MiniMax H3 is an open-weight multimodal AI video generation model capable of creating up to 15-second videos with native stereo audio from text, images, video, and audio inputs. It supports text-to-video, image-to-video, video editing, and video-to-video

Open Source

LTX 2.5 Pro turns text prompts into cinematic video with native synchronized audio — dialogue, ambience, and sound effects generated alongside the frames. Output at 720p or 1080p, 25 or 50 fps, up to 10 seconds, from a single ModelsLab API call.

Closed SourceFilmmaker GradeCinematic+2

LTX 2.5 Pro Image to Video animates a single still into a cinematic clip, using a text prompt to direct motion, camera movement, and atmosphere. Native synchronized audio, 720p or 1080p output, 25 or 50 fps, and 6 to 10 second durations — all from one end

Closed SourceFilmmaker GradeCinematic+2

MiniMax H3 is an open-weight multimodal AI video generation model capable of creating up to 15-second videos with native stereo audio from text, images, video, and audio inputs. It supports text-to-video, image-to-video, video editing, and video-to-video

Open Source

Grok Imagine Image 2.0 Image Editing modifies existing images from plain text instructions — add, remove, restyle, or merge subjects while preserving the original look. Handles up to 14 input images in a single generation across seven aspect ratios.

Closed SourceNew Added2K Output+2

Grok Imagine Image 2.0 turns text prompts into 2K images with stronger prompt adherence, cleaner in-image text, and sharper detail than the original Grok Imagine. Five aspect ratios, 1K or 2K output, one ModelsLab endpoint.

Closed SourceNew Added2K Output+2

Seedance 2.5 writes a full scene from one text prompt — up to 30 seconds of continuous video with synced dialogue, ambience and score, no stitching required. Prompt in 11 languages, pick any aspect ratio from 21:9 to 9:16, and render at 480p or 720p

Closed SourceNew AddedNative Sync Audio+2

Seedance 2.5 animates a single still into a video up to 30 seconds long, with native sound and dialogue in 11 languages. Set a first frame, or pin both first and last frames to control exactly where the shot starts and ends. Outputs 480p or 720p.

Closed SourceNew AddedNative Sync Audio+2

AI APIs for Developers

Popular Models

AI Model APIs