API reference

OpenAI-compatible gateway. Base URL: https://api.onelitellm.net/v1

Authentication

Send a virtual key in the Authorization header:

Authorization: Bearer sk-...

Endpoints

MethodPathDescription
POST/v1/chat/completionsChat completion (supports stream: true)
GET/v1/modelsModels available to the key
GET/health/livelinessProcess liveness
GET/health/readinessDependencies readiness
GET/openapi.jsonFull OpenAPI schema

Example

curl https://api.onelitellm.net/v1/chat/completions \
  -H "Authorization: Bearer $LITELLM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [{"role": "user", "content": "hello"}]
  }'

Models

deepseek-flash — fast, long context. deepseek-v4-pro — higher quality for complex tasks.

Limits

Per-key monthly budget and requests-per-minute are enforced by the gateway. Exceeding them returns 429; invalid keys return 401.