Chat Completions

Chat Completions

POST /v1/chat/completions — the base OpenAI chat format.

POST /v1/chat/completions is the OpenAI Chat Completions format. Most SDKs and tools speak it, and providers support it more often than any other.

Request

curl https://ai-seller.vibe-codes.ru/v1/chat/completions \
  -H "Authorization: Bearer $AISELLER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [
      {"role": "system", "content": "Answer briefly."},
      {"role": "user", "content": "How many planets are in the Solar System?"}
    ],
    "max_tokens": 200
  }'

Response

json
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1790000000,
  "model": "gpt-5.6-sol",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Eight."},
      "finish_reason": "stop"
    }
  ],
  "usage": {"prompt_tokens": 24, "completion_tokens": 2, "total_tokens": 26}
}

Specifics

  • Streaming — "stream": true. Usage arrives in the last chunk only when requested: "stream_options": {"include_usage": true}. See Streaming.
  • Image input — via image_url message parts (a link or a data: URL). The request body limit is 25 MiB.
  • Tools — only your own functions (function, custom); the provider's built-in tools are stripped.
  • Not supported: audio input and output and files by file_id — such a request gets 400 unsupported_parameter.

The full parameter list is in Request parameters.

Updated September 29, 2026