OpenAI · Chat Completions

POST /v1/chat/completions

Auth: auth page. Base: protocol checklist. Probe commands: curl verification.

http

Authorization: Bearer sk-xxxx
Content-Type: application/json

bash

curl https://api.daoxe.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "copy from /v1/models",
    "messages": [{"role":"user","content":"ping"}],
    "max_tokens": 64
  }'

Success response (structure)

json

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Stream fragments (sample)

text

data: {"choices":[{"delta":{"content":"Hi"}}]}
data: [DONE]

Error samples

json

{"error":{"message":"Invalid token","code":401}}
{"error":{"message":"Insufficient quota"}}
{"error":{"message":"Rate limit exceeded"}}

More errors: error codes. Models: recommended models table.