InferGate API documentation
Start with the InferGate API base URL, bearer authentication, exact model IDs and verified Responses API examples for Python, Node.js and streaming.
Base URL: https://api.useinfergate.com/v1. Requests authenticate with an InferGate API key in the Bearer authorization header. An OpenAI account key is not an InferGate credential.
Check access before sending requests
Use your own InferGate key to request the live catalog. Account permissions, key restrictions and available balance still apply. A model listed here is not a guarantee of uninterrupted upstream service.
curl --fail-with-body https://api.useinfergate.com/v1/models \
-H "Authorization: Bearer $INFERGATE_API_KEY"Retired model requests return model_not_available. InferGate does not silently substitute another model. Keep keys on your server and out of browser bundles.
First Responses request
curl --fail-with-body https://api.useinfergate.com/v1/responses \
-H "Authorization: Bearer $INFERGATE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.5","input":"Reply with one sentence about API design.","max_output_tokens":256}'Choose a guide
Errors and support
Check credentials for 401, account and key permissions for 403, and the exact published identifier for model_not_available. For upstream failures, record the request ID, model, timestamp and completion status. Never send a full key to support.