model field. Use its model page to check supported inputs, controls, and the endpoint to call.
Browse the catalog
Browse model pages for exact IDs, supported modes, media requirements, and output formats.Video models
Video generation, animation, and enhancement models.
Image models
Synchronous and asynchronous image generation and editing.
LLM
Chat completions, multimodal reasoning, and video understanding.
OpenAI
GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna support reasoning, structured output, images, tools, and SSE. Use Responses and tools for agent workflows and Chat Completions for compatible text clients. GPT Image 2.6 Flare, GPT Image 2.6 Sunburst, GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, and GPT Image 2 support synchronous generation and reference-image editing through the OpenAI Image API. Flare emphasizes speed for everyday generation; Sunburst emphasizes editing precision. All three use GENGEN’s normalized request fields and return image URLs retained for 24 hours. GPT Image 2.5 addsxhigh and max quality; streaming is not exposed by this endpoint.
Google images
Nano Banana 2.1 supports 1K, 2K, and 4K image generation and editing with up to 14 reference images. Use the Google Image API with modelgemini-nano-banana-2.1. Generated image URLs are retained for 24 hours.
LLM and video understanding
Gemini 4 Neon and Gemini 4 Hydrogen support coding, document understanding, multimodal input, and tools through Chat Completions and Responses with SSE. Both default to 65,536 output tokens and support automatic continuation within a shared 1,048,576-token window, with high reasoning by default and an optional xhigh level. Gemini 4 Carbon supports complex reasoning, coding, structured output, and multimodal input through Chat Completions and Responses, including SSE and tools. Larger explicit output budgets enable automatic continuation within its shared 1,048,576-token window. Gemini 4 Argon supports complex reasoning, coding, structured output, and multimodal input through Chat Completions and Responses, including SSE and tools. Larger explicit output budgets enable automatic continuation within its shared 1,048,576-token window. Gemini 3.8 Flash supports text generation and multimodal understanding. Use Chat Completions for synchronous or streaming text and Responses for video analysis.Google Veo
Veo 3.1, Veo 3.1 Fast, and Veo 3.1 Lite (Preview) generate videos with optional audio. The Veo API guide covers HTTPS/GCS inputs, first and last frames, subject references and API-only extension.Wan Spicy
The Wan 3.0 Spicy family supports text, keyframes and multimodal references. Base and Prime support 480p through 1080p. Pro and Prime Pro support 1080p, 2K and 4K. For image-driven Wan 2.7, see Wan 2.7 Spicy.Video providers
Kling 3.0 Turbo
Fast Kling video generation for text-to-video and first-frame image-to-video workflows.
Kling 4.0
Text, keyframe and Omni workflows. See the model page for live availability.
Kling 3.0
Kuaishou video generation with native audio, multi-shot control, and output up to 4K.
MiniMax H3
Text, first-and-last-frame, and multimodal reference video generation up to 2K.
MiniMax H3 Max
Fast text-to-video and image-to-video generation at 480P or 768P.
Capabilities, availability, and final customer prices can differ by model. Check the Models section in the Dashboard before production use.
Model selection
- Use the exact public ID shown by GENGEN.
- Use aliases only when a compatibility page explicitly documents them.
- Keep advanced model settings under
providerOptions. - Keep media under
assetsand provider-neutral settings undercontrols.