Responses

Given a list of input prompts, the model will return one or more predicted completions for each. This endpoint is optimized for processing multiple independent inputs in a single request.

Create Responses

POST https://api.sybil.com/v1/responses

Creates completions for the provided list of input prompts.

Request Body

Name	Type	Description
model	string	Required. The name of the model to use.
input	array	Required. the prompt(s) sent to the model.
max_tokens	integer	The maximum number of tokens to generate per response.
temperature	number	What sampling temperature to use, between 0 and 2.
top_p	number	An alternative to sampling with temperature, called nucleus sampling.
stream	boolean	Whether to stream back partial progress.

Example Request

curl https://api.sybil.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SYBIL_API_KEY" \
  -d '{
    "model": "DeepSeek-R3",
    "input": [
      "What is the capital of France?",
      "What is the capital of Spain?"
    ],
    "max_tokens": 50,
    "temperature": 0.7
  }'

Response Format

{
  "model": "DeepSeek-R3",
  "choices": [
    {
      "index": 0,
      "text": "The capital of France is Paris.",
      "finish_reason": "stop"
    },
    {
      "index": 1,
      "text": "The capital of Spain is Madrid.",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "input_tokens": 14,
    "output_tokens": 16,
    "total_tokens": 30
  }
}