Completions

Given a prompt, the model will return one or more predicted completions.

Create Completion

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

Creates a completion for the provided prompt and parameters.

Request Body

Name	Type	Description
model	string	Required. The name of the model to use.
prompt	string	Required. The prompt(s) to generate completions for.
max_tokens	integer	The maximum number of tokens to generate in the completion.
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/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SYBIL_API_KEY" \
  -d '{
    "model": "DeepSeek-R3",
    "prompt": "Say this is a test",
    "max_tokens": 7,
    "temperature": 0
  }'

Response Format

{
  "model": "DeepSeek-R3",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}