Skip to content
SETU by SUPREME AI
Beta

Models API

OpenAI-compatible chat completions with streaming and tool calls. Point your OpenAI client at Setu and keep your code.

How it works

  1. 1

    Create a key

    In the Setu console, create a key with the chat:write scope.

  2. 2

    Change the base URL

    Point your OpenAI client at Setu and use your Setu key.

  3. 3

    Pick a model

    List the models with GET /v1/models and send the id with each request.

Try it

Replace $SETU_API_KEY with a key from the Setu console.

Send a chat request

curl https://setu.supremeai.services/api/setu/v1/chat/completions \
  -H "Authorization: Bearer $SETU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "quantum-lite",
    "messages": [{ "role": "user", "content": "Say hello in Nepali." }]
  }'

List the models

curl https://setu.supremeai.services/api/setu/v1/models \
  -H "Authorization: Bearer $SETU_API_KEY"

What it does

  • OpenAI-compatible chat completions with streaming and tool calls.
  • A model list endpoint.
  • Move an existing OpenAI integration to Setu by changing two lines.
  • Add a chat box to a support tool.
  • Give an agent a model and Setu tools on the same key.

Limits and status

Beta
  • Needs the chat:write scope on the key.
  • Each call uses credits from your SUPREME AI account.
  • Not yet: Models beyond DeepSeek and Gemini. Other providers are not served.

Status last checked 2026-10-21.

Questions

Which OpenAI features work?

Chat completions, including streaming and tool calls, in the stock OpenAI format. The models Setu serves are listed at /v1/models.

Can I choose any provider?

No. Setu serves its own model list, based on DeepSeek and Gemini today. Other providers are not offered.

Start building with Setu

No Setu fee during beta. Create a key and make your first call.