POST
/
api
/
v2
/
log
/
inference
{
    // required fields
    "language_model_id": "gpt-4",
    "prompt": [
        {
            "role": "user",
            "content": "Which spaceship was first to land on the moon?"
        }
    ],
    "response": "The Apollo 11 was the first spaceship to land on the moon.",
}
Using OpenAI with Python? Just follow our quick start guide to get started in just a few lines of code.
Using LiteLLM? Follow this guide to get set up in just a few lines of code.
You can log your inference calls to Athina via a simple API request. The logging request should be made just after you receive a response from the LLM.
  • Method: POST
  • Endpoint: https://log.athina.ai/api/v2/log/inference
  • Headers:
    • athina-api-key: YOUR_ATHINA_API_KEY
    • Content-Type: application/json
Tip: To avoid adding any latency to your application, log your inference as a fire-and-forget request.
{
    // required fields
    "language_model_id": "gpt-4",
    "prompt": [
        {
            "role": "user",
            "content": "Which spaceship was first to land on the moon?"
        }
    ],
    "response": "The Apollo 11 was the first spaceship to land on the moon.",
}
​
language_model_id
string
required
Identifier for the language model used for inference. This is just a string label, all models are supported.
​
prompt
string | {role: string, content: string}[]
The prompt sent for inference. This can be either a string or the messages array sent to OpenAI. Note that in case of Tool message content can be either string or array.
​
response
string
required
The response from the LLM. This should be a string.

​
Logging Attributes

See the full list of available fields for logging here.