Chat Completions

Generate conversational responses using our AI models.

​

Endpoint Details

​

Request Format

​

Headers

​

Body Parameters

​

Example Request

{
  "model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}

​

Response Format

{
  "id": "cmpl-123abc",
  "object": "chat.completion",
  "created": 1677649420,
  "model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      }
    }
  ]
}

​

Model Parameters

• Maximum Output Tokens: 725
• Temperature: 0.7
• Top P: 0.9

​

Caching

• Responses are cached for 1 hour
• Cache key is based on model and messages content
• Cached responses are served instantly

​

Error Scenarios

• 400: Invalid request format or empty messages array
• 401: Missing API key
• 403: Invalid API key
• 429: Rate limit exceeded
• 500: Internal server error

​

Error Response Example

{
  "error": {
    "message": "Error description",
    "code": 400
  }
}