completions

Inference: Completion

Compatible with OpenAI's Completions API.

post/completions

Request

Base URL
https://inference-api.nousresearch.com/v1
Auth
HTTP bearer
TypeScript
https://skmtc.dev/nousresearch/apis/nous-research-inference-api/docs/completions/post.ts
A function with typed inputs. Its response is checked against the schema.

modelstring required

The model to use for the request.

promptstring required

The input prompt to generate completions for.

max_tokensinteger

The maximum number of tokens to generate. Must be between 1 and 32000.

temperaturenumber

Sampling temperature to use. Must be between 0.0 and 2.0.

streamboolean

Whether to stream responses incrementally.

{
  "model": "Hermes-4.3-36B",
  "prompt": "Once upon a time",
  "max_tokens": 60,
  "temperature": 0.8,
  "stream": true
}

Successful Response

idstring

Unique identifier for the response.

objectstring

createdinteger

Timestamp of response creation.

modelstring

The model used.

{
  "object": "text_completion"
}

No recorded changes to this operation across all 1 revision of this API.