Chat Completions

Create a model response for a conversation. This endpoint is compatible with the OpenAI Chat Completions API.

POST https://api.setu.dwet.ai/v1/chat/completions

Request body

Field	Type	Description
`model`	string	ID of the model to use, e.g. sutra-v2-pro.
`messages`	array	The conversation so far. Each item has a role (system, user, assistant) and content.
`stream`	boolean	If true, partial deltas are sent as SSE. Default false.
`temperature`	number	Sampling temperature between 0 and 2. Default 0.7.
`max_tokens`	integer	Maximum tokens to generate in the response.

Example request

bash

curl https://api.setu.dwet.ai/v1/chat/completions \
  -H "Authorization: Bearer $SETU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sutra-v2-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain UPI in one line"}
    ],
    "temperature": 0.7
  }'

Example response

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1782033025,
  "model": "sutra-v2-pro",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "UPI is..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 97,
    "total_tokens": 107
  }
}

Streaming response

With stream: true, the server emits chat.completion.chunk events terminated by a data: [DONE] line.

text

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"UPI "},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

See Models for available model IDs and SDKs for client examples.