chat completions

Inference: Chat Completion

Compatible with the OpenAI Chat API.

post/chat/completions

Request

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

Request body

modelstring required

The model to use for the request.

temperaturenumber

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

max_tokensinteger

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

streamboolean

Whether to stream responses incrementally.

Example request

{
  "model": "Hermes-4.3-36B",
  "messages": [
    {
      "role": "user",
      "content": "What is the capital of France?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 50,
  "stream": true
}

Response

Successful Response

idstring

Unique identifier for the response.

objectstring

createdinteger

Timestamp of response creation.

modelstring

The model used.

Example response

{
  "object": "chat.completion"
}

Changes

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