Quickstart

This guide walks through one full path: signing in, connecting a provider, minting a proxy key, and making your first chat-completions request.

1. Sign in

Open ada.ai, enter your email, and click Send magic link. Click the link in your inbox. First-time emails create an account automatically — there's no separate signup step.

You can also sign in with a password if you've set one.

2. Add an upstream

An upstream is a provider endpoint paired with your own API key. The proxy routes your traffic across whichever upstreams you've enabled, in priority order.

In the dashboard, go to Upstreams → Add upstream and pick from the preset list, or define a custom one. You'll need:

3. Mint a proxy key

Go to Keys → New key, name it, and click Create. You'll see the full key once — it looks like sk-rc-<random>.

The key is personal by default. To scope it to an organization instead, pick the org from the Owner field when minting — see Organizations and API keys.

4. Send your first request

curl https://api.ada.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-rc-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.7",
    "messages": [{"role": "user", "content": "Say hello in one word."}]
  }'

You'll get a standard OpenAI chat-completion response:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "glm-4.7",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "\n\nHello" }, "finish_reason": "stop" }
  ],
  "usage": { "prompt_tokens": 16, "completion_tokens": 2, "total_tokens": 18 }
}

5. Point your SDK at Ada AI

Because the API is OpenAI-compatible, existing SDKs work unchanged — just change the base URL and use your proxy key as the API key.

from openai import OpenAI

client = OpenAI(
    api_key="sk-rc-...",
    base_url="https://api.ada.ai/v1",
)

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Next steps