LLM

OpenAI-compatible chat completion. Set `stream: true` for server-sent events.

post/api/v1/chat/completions

Request

  • Base URL: https://api.api-stock.com
  • URL: https://api.api-stock.com/api/v1/chat/completions
  • Auth: HTTP bearer

Request body

modelstring required

Model id

streamboolean

Stream partial deltas as server-sent events

temperaturenumber

Sampling temperature (0-2)

top_pnumber

Nucleus sampling probability

max_tokensnumber

Maximum tokens to generate

max_completion_tokensnumber

Alias for max_tokens; capped by API Stock

nnumber

Number of completions. API Stock currently supports one.

Example request

{
  "model": "gemini-3.5-flash",
  "messages": [
    {
      "role": "user"
    }
  ]
}

Response

Chat completion. When stream is true the response is a text/event-stream of deltas.

idstring required
objectstring required
creatednumber required
modelstring required

Example response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gemini-3.5-flash",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hi there!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 34,
    "total_tokens": 46
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.