Gateway API

OpenAI-compatible Gateway endpoints for chat, embeddings, and images.

Chat Completions

Base: POST /v1/chat/completions · Auth: API Key

json

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain quantum computing briefly."}
  ],
  "max_tokens": 500,
  "temperature": 0.7
}

Streaming

Set stream: true for Server-Sent Events response:

bash

curl -N -X POST "https://<BASE_URL>/v1/chat/completions" \
  -H "Authorization: Bearer <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o", "messages": [{"role":"user","content":"Hi"}], "stream": true}'

Models

Available models depend on your tenant configuration. Common models include gpt-4o, claude-3-5-sonnet, gemini-pro, deepseek-chat.

Rate Limits

Rate limits are enforced per API key and plan tier. 429 responses include a Retry-After header.