apimodels.app is a multi-model API gateway: one API key and OpenAI- and Anthropic-compatible endpoints for about 150 image, video, audio and language models, including Claude Opus 5.5, Claude Sonnet 5.5, GPT Image 2, Seedance 2.5, MiniMax H3, Kling V3, Wan 3.0 and Nano Banana. Billing is pay per use, and failed calls are not charged.
curl https://api.apimodels.app/v1/chat/completions \
-H "Authorization: Bearer $APIMODELS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-opus-5-5", "messages": [{"role": "user", "content": "Hello"}]}'Each library credits the people who wrote the prompts and links to the original posts. The same collections, with the images and videos playing inline, are on apimodels.app.
| Repository | What's inside |
|---|---|
| claude-opus-5-5-video-prompts | 60 real videos made with Claude Opus 5.5, six workflows with templates, and our own reproducible run |
| awesome-seedance2.5-prompts | Seedance 2.5 video prompts, each shown next to the clip it produced |
| stunning-minimax-h3-prompts | MiniMax H3 (Hailuo 3) video prompts, each with a clip you can watch |
| gpt-image-2-prompts | Bilingual GPT Image 2 prompts with the images they generated, as CSV and JSON |
| gpt-image-2-5-prompts | GPT Image 2.5 (Flare and Sunburst) prompts, each with the image it produced |
- apimodels-api-demo: curl, Node.js and Python examples for image, video, chat and audio models.
- apimodels-apidocs: base URL per SDK and the native endpoints.
- apimodels-mcp: MCP server (npm
apimodels-mcp), listed in the official MCP Registry. - apimodels-skill: Agent Skills for Claude Code and other coding agents.