Quick Start on CobabaAi

This guide uses the hosted platform at cobabaai.com. For private deployment, see Installation.

1. Create an account

1. Open https://cobabaai.com/register
2. Complete sign-up and sign in to the Console

2. Create an API token

1. Go to Console → Tokens
2. Create a token and copy it (shown once)

3. Configure your client

Use CobabaAi as an OpenAI-compatible endpoint:

Base URL: https://cobabaai.com/v1
API Key:  <your CobabaAi token>

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://cobabaai.com/v1",
    api_key="YOUR_COBABAAI_TOKEN",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello from CobabaAi"}],
)
print(response.choices[0].message.content)

curl

curl https://cobabaai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_COBABAAI_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

4. Try the playground

Open Console → Playground on cobabaai.com to test models in the browser before integrating.

5. View usage

Check Console → Logs for token usage, latency, and errors per request.

Next steps

• Features — routing, pricing, and quotas
• Channels — how CobabaAi selects upstream providers (admin)
• Installation — run CobabaAi on your own server