Chat

Generate a chat completion

post

Create a chat completion based on a list of messages. Requires authorization.

Authorizations

Body

modelstringRequired

Model ID to use for the completion

Example: copilot-zero

temperaturenumberOptional

Sampling temperature between 0 and 1.

Default: 0.7

max_tokensintegerOptional

Maximum tokens to generate (max 4096).

Default: 1024

streambooleanOptional

Whether to stream partial responses.

Default: false

instructionsstring | nullableOptional

Optional instructions for the model.

Responses

200

Chat completion response

application/json

400

Invalid request (missing or invalid parameters)

application/json

401

Unauthorized - Invalid or missing API key

application/json

429

Too many requests - rate limit exceeded

application/json

500

Internal server error

application/json

post

HTTPcURLJavaScriptPython

POST /v1/chat/completions HTTP/1.1
Host: api.secton.org
Authorization: Bearer JWT
Content-Type: application/json
Accept: */*
Content-Length: 165

{
  "model": "copilot-zero",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how can I help you?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false,
  "instructions": "text"
}

{
  "object": "chat.completion",
  "model": "copilot-zero",
  "organization_id": "org_1234",
  "messages": [
    {
      "role": "user",
      "content": "Hello! How can I assist you today?"
    }
  ],
  "usage": {
    "prompt_tokens": 50,
    "completion_tokens": 100,
    "total_tokens": 150
  }
}