Inference

Create a chat completion

OpenAI Chat Completions-compatible endpoint. The primary, multi-provider endpoint for generating AI responses: text, multi-turn conversation, tool use, vision (image input), and extended reasoning via reasoning_effort. Requests route to the government cloud provider that serves the requested model.

post/v1/chat/completions

Request

Base URL: https://api.consus.io
URL: https://api.consus.io/v1/chat/completions
Auth: API key in header x-api-key

Request body

modelstring required

Composite model ID. See GET /v1/models.

temperaturenumber

max_tokensinteger

top_pnumber

streamboolean

reasoning_effort'none' | 'low' | 'medium' | 'high' | 'xhigh'

Response

Chat completion (or, with stream: true, a text/event-stream of chat completion chunks terminated by data: [DONE]).

idstring

objectstring

createdinteger

modelstring

Example response

{
  "object": "chat.completion",
  "x_consus_governance": {
    "flags": [
      {
        "reason": "external_destination"
      }
    ]
  }
}

Changes

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