Skip to Content
Getting started

Getting started

Under maintenance. The managed Vinci API and Platform are under maintenance. These service-specific instructions are retained as reference for existing integrations when service is available. They do not promise current access or a return date. Downloadable models and direct/BYOK use of Vinci Code CLI are separate paths.

Choose the path that matches your task.

  • Run model weights: follow Models and evidence. Start with a model card, its licence and its evaluation limitations; use the card’s runtime instructions.
  • Use a terminal coding agent: follow Vinci Code CLI. Provider credentials and model support follow the installed CLI’s documentation.
  • Inspect research: visit the technical record .
  • Continue a hosted API integration: use the service-specific setup below.

Hosted API setup

The following examples document the hosted Vinci API. They are retained for existing integrations and do not imply that the downloadable MLE or Cyber artifacts are served under these routing names. Account access, model availability and billing follow the hosted service; check the API reference and your account before use.

1. Get an API key

  1. Sign in to the Vinci Platform — the developer console for keys and usage. Same account as the Vinci app (same email and password).
  2. Go to API keys.
  3. Issue a key. It looks like vinci_live_… and is shown once — copy it now. (We only store a hash; if you lose it, revoke and issue a new one.)

Keep keys secret. Treat them like a password; never commit them to source control.

2. Make a request

Vinci’s API is OpenAI-compatible, so most OpenAI SDKs and tools work by changing two things: the base URL and the API key.

curl https://vinci.getsimpledirect.com/api/v1/chat/completions \
  -H "Authorization: Bearer $VINCI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "forte",
    "messages": [{ "role": "user", "content": "Explain async/await in one sentence." }]
  }'

What you’ll see — a standard OpenAI-shaped response, with Vinci doing the talking:

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "forte",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "async/await lets you write asynchronous code that reads like synchronous code — await pauses at a promise until it settles." },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 74, "completion_tokens": 28, "total_tokens": 102 }
}

A response confirms this request succeeded. Check the supported API surface before adapting additional endpoints or features.

3. Use it from an SDK

Python (the official openai package):

from openai import OpenAI
 
client = OpenAI(
    base_url="https://vinci.getsimpledirect.com/api/v1",
    api_key="vinci_live_...",  # or os.environ["VINCI_API_KEY"]
)
 
resp = client.chat.completions.create(
    model="forte",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

JavaScript / TypeScript:

import OpenAI from 'openai';
 
const client = new OpenAI({
  baseURL: 'https://vinci.getsimpledirect.com/api/v1',
  apiKey: process.env.VINCI_API_KEY,
});
 
const resp = await client.chat.completions.create({
  model: 'forte',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(resp.choices[0].message.content);

If something’s off

  • 401 Unauthorized — the key is wrong, revoked, or has a typo. Issue a fresh one on the Platform ↗  (keys are shown once, so copy carefully).
  • 402 — your Vinci Platform credit balance is exhausted.
  • 429 — we’re momentarily busy; wait a few seconds and retry.

Next

Last updated on
IntroductionModels and evidence