Chat Completions

Use Chat Completions when your application already sends messages with role and content fields.

Request

Field	Value
Method	POST
Endpoint	/chat/completions
Full URL	https://supado.com/v1/chat/completions
Auth	Authorization: Bearer <SUPADO_API_KEY>

Common request fields:

Field	Type	Notes
model	string	Use a model available in your Supado account.
messages	array	OpenAI-style chat messages.
temperature	number	Optional. Support can depend on the model.
stream	boolean	Optional. Use true for SSE streaming if supported.

Example

Non-streaming curl

curl https://supado.com/v1/chat/completions \
  -H "Authorization: Bearer $SUPADO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "Answer in one short paragraph." },
      { "role": "user", "content": "What should I verify after changing API gateways?" }
    ]
  }'

TypeScript SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SUPADO_API_KEY,
  baseURL: "https://supado.com/v1",
});

const completion = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "Answer in one short paragraph." },
    { role: "user", content: "What should I verify after changing API gateways?" },
  ],
});

console.log(completion.choices[0]?.message?.content);

Response

For a successful non-streaming request, read the assistant message from:

completion.choices[0]?.message?.content

For streaming requests, set stream: true and consume Server-Sent Events incrementally. See Streaming Responses for client behavior and proxy considerations.

Errors

Requests must use a messages array, a model available in Supado, and a JSON body. Preserve non-2xx response bodies in server-side logs without logging secrets.

Use the Errors page when a request reaches Supado but does not complete successfully.