chat/completions request as a minimal example. Image and video generation use different endpoints; after completing this chat request, follow the links at the end of the page to integrate them.
1. Prepare an API key
Create a Bearer key in the console and save it as an environment variable. Send every request from your server; never place the key in browser code or a client application bundle.2. Start a Claude chat through the OpenAI-compatible endpoint
model to gpt-5.5, gpt-5.6-terra, qwen3.7-max, or another available text model to call it with the same key.
3. Use the native Anthropic protocol (recommended for the Claude SDK / Claude Code)
If you use the official Anthropic SDK or Claude Code, use the dedicated base URLhttps://api-direct.dimilinks.com/:
4. Enable streaming
data: {...} events as text/event-stream, ending with data: [DONE]. See Chat completions for details.
5. Next steps
- List currently available models and select a recent model: Model selection and updates
- Connect Claude Code to Claude: Claude Code
- Connect Codex CLI to GPT: Codex CLI
- Configure Cursor, Continue, Zed, Cherry Studio, and other IDEs: VS Code and other IDEs
- Import directly from the console into CC Switch or Cherry Studio: One-click CC Switch / Cherry Studio import
- Submit an image task: Create image generation
- Submit a video task: Create video generation
- Retrieve task progress: Retrieve image task