AI APIs for Developers
Filter by use case
AI Model APIs
222 resultsNano Banana 2.1 - Image Edit
Edit and transform images with plain-language instructions using Google's Nano Banana 2.1. Precise changes while keeping the rest of your image intact.
Nano Banana 2.1 Text To Image
Generate high-quality images from text prompts with Google's Nano Banana 2.1. Fast, prompt-faithful results through a single ModelsLab API.
Ideogram
Ideogram 4.5 Text to Image
Generate images with Ideogram 4.5 from a natural-language or structured JSON prompt. Add optional source images to guide or edit the result, with magic prompt control for prompt expansion.
Ideogram
Ideogram 4.5 Precise Image Edit
Edit any image with Ideogram 4.5 using a simple text instruction. Add an optional mask or reference images, and get the result back at the original image's exact width and height.
Black Forest Labs
Flux 3 Text To Image
Generate images from text with FLUX 3 by Black Forest Labs. Output up to 4K in 15 aspect ratios, bounding box layout control, and web grounding for accurate real-world subjects. Available through the ModelsLab API and Playground.
Black Forest Labs
Flux 3 Image Edit
Edit images with FLUX 3 by Black Forest Labs. Describe the change, combine up to 10 reference images, and target exact regions with bounding boxes while the rest stays unchanged. Output up to 4K via the ModelsLab API and Playground.
ModelsLab
PopularQwen 2.1 Image to Image
Transform existing images with Qwen 2.1 Image-to-Image. Upload an image and describe your desired changes in a natural-language prompt to generate an updated result.
ModelsLab
Qwen Image 2.1 Text to Image
Generate high-quality images from natural-language prompts with Qwen Image 2.1. Describe the scene, subject, style, composition, lighting, or visual details you want, and the model turns your instructions into a detailed image.
ModelsLab
Minimax H3 Fast Reference To Video
Minimax H3 Fast is an open-weight multimodal AI video model that creates up to 15-second videos with native stereo audio. Generate and transform videos using text, images, video, or audio with support for image-to-video, video-to-video.
Open Ai
GPT-Image-2.5 Flare - Image Edit
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.
Open Ai
GPT-Image-2.5 Flare - Text To Image
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.
Open Ai
GPT-Image-2.5 Sunburst - Image Edit
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.
Open Ai
GPT-Image-2.5 Sunburst - Text To Image
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.
Alibaba
Wan 3.0 Reference To Video
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.
Alibaba
Wan 3.0 Image To Video
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.
Alibaba
Wan 3.0 Text To Video
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.