Chat Completions (OpenAI format)

curl {base_url}/r/{router}/v1/chat/completions \
  -H "Authorization: Bearer sk-dodo-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default",
    "stream": false,
    "messages": [{"role": "user", "content": "Reply with exactly the word: pong"}]
  }'

Verified live response:

{
  "choices": [{"finish_reason": "stop", "index": 0,
               "message": {"content": "pong", "role": "assistant"}}],
  "model": "gpt-5.5",
  "usage": {"completion_tokens": 5, "prompt_tokens": 13, "total_tokens": 18,
            "prompt_tokens_details": {"cached_tokens": 0}}
}

# Streaming

With "stream": true, the response is a standard OpenAI-style SSE stream of chat.completion.chunk deltas terminated by data: [DONE] — verified working, including tool-call streaming.