Skip to content

Connect clients

Complete a first request before configuring other clients. Use a user API key, separate from provider credentials and Admin integration keys.

ClientAddress or interfaceRequirements
OpenAI-compatible SDK, IDE or CLIBase URL: http://localhost:8787/v1User key, gateway model ID and an active Chat or Responses surface
Anthropic-compatible clientRequest URL: http://localhost:8787/v1/messagesA Messages surface; configure the SDK base according to its URL joining rules
Native Gemini clienthttp://localhost:8787/v1beta/models/model-id:generateContentA Gemini surface and native request body
MCP clienthttp://localhost:8787/mcp or /mcp/server-slugAn enabled MCP server and a user key or OAuth

Replace local addresses with your deployed Proxy URL. Some clients append /v1 themselves; inspect the final path to avoid repeating it.

Clients use the gateway’s model ID. The route maps it to the upstream model name. Specify a group as model-id:route-group, for example your-model:free. Available protocols depend on the group’s active surfaces.

Authenticated GET /v1/models returns LLMs by default. Use kind=image, kind=asr, kind=tts or kind=embedding for other types; kind=all includes all types. The compatible kind=audio filter includes ASR and TTS.

Terminal window
curl -sS http://localhost:8787/v1/responses \
-H 'Authorization: Bearer sk-your-api-key' \
-H 'Content-Type: application/json' \
-d '{"model":"your-route-model","input":"Hello"}'

A working Chat route does not automatically provide Responses, Messages or Gemini. Check the request surfaces, then inspect request logs.

See client examples for additional requests and fields.