Legacy Text Completions – Prompt-In, Completion-Out API

Use the legacy text completions endpoint for prompt-in, completion-out workflows — parameters, an example request, and when to prefer chat completions.

The /v1/completions endpoint accepts a text prompt and returns a completion. It is a legacy endpoint — for new projects, use /v1/chat/completions instead. It is included for compatibility with tools that depend on the completions interface, such as older SDKs or fine-tuned workflows built around raw prompt templates.

For new integrations, use /v1/chat/completions — it supports system prompts, tool calls, and structured output.

Endpoint

POST https://api.boole.dev/v1/completions

Request Body

model · string · required

Model slug to use for the request, e.g. llama-3.3-70b-instruct. See Models for all available slugs.

prompt · string · required

The text prompt to complete. The model continues generation from wherever the prompt ends.

max_tokens · integer

Maximum number of tokens to generate. Default: 16.

temperature · number

Sampling temperature between 0 and 2. Lower values produce more deterministic output. Default: 1.

stream · boolean

When true, streams the response as server-sent events. Default: false.

stop · string | array

One or more sequences at which generation stops. Generation halts as soon as any sequence in the list is encountered.

top_p · number

Nucleus sampling probability mass. Only tokens comprising the top top_p probability are considered. Default: 1.

Example Request

curl https://api.boole.dev/v1/completions \
  -H "Authorization: Bearer $BOOLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-instruct",
    "prompt": "The capital of France is",
    "max_tokens": 10
  }'

Example Response

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1720000000,
  "model": "llama-3.3-70b-instruct",
  "choices": [
    {
      "text": " Paris.",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 7,
    "completion_tokens": 2,
    "total_tokens": 9
  }
}

Response Fields

id · string

Unique identifier for the completion. Use this for logging and tracing.

choices[].text · string

The generated text continuation from the model for this choice.

choices[].finish_reason · string

Reason generation stopped. Common values: "stop" (natural end or stop sequence hit), "length" (max_tokens reached).

usage.prompt_tokens · integer

Number of tokens in the input prompt.

usage.completion_tokens · integer

Number of tokens generated in the response.