Skip to Content
API/chat/completions

/chat/completions

Creates a chat completion for the given conversation messages. This endpoint is compatible with the OpenAI Chat API .

Endpoint

POST /v1/chat/completions

Headers

NameTypeDescription
AuthorizationstringRequired. Your API key prefixed with “Bearer “

Request Body

{
  // ID of the model to use. Required.
  "model": string,
 
  // The messages to generate chat completions for. Required.
  "messages": [
    {
      "role": string,     // The role of the message sender. Can be "system", "user", or "assistant"
      "content": string   // The content of the message
    }
  ],
 
  // Whether to stream the response. Optional.
  "stream": boolean,
 
  // The maximum number of tokens to generate. Optional.
  "max_tokens": number,
 
  // Sampling temperature between 0 and 2. Optional.
  "temperature": number,
 
  // Alternative to temperature. Optional.
  "top_p": number
}

Response

Returns a chat completion object with the model’s response:

{
  "id": string,
  "object": "chat.completion",
  "created": number,
  "model": string,
  "choices": [
    {
      "index": number,
      "message": {
        "role": "assistant",
        "content": string
      },
      "finish_reason": string
    }
  ],
  "usage": {
    "prompt_tokens": number,
    "completion_tokens": number,
    "total_tokens": number
  }
}

When stream is true, the response is sent as server-sent events in the same format.

Error Codes

  • 400 - Invalid request (missing required fields or invalid model)
  • 401 - Invalid API key
  • 429 - Rate limit exceeded or insufficient credit
  • 500 - Server error

Example

curl -X POST https://api.octora.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ]
  }'
API/completions