Authentication

API keys

Create and manage keys on the API keys page. Keys start with tnsa_ and are shown only once, when you create them. Each key can carry its own spend limit. Treat keys like passwords.

• Store keys in environment variables, never in code or the browser.
• Use separate keys per environment (development, staging, production).
• Set a usage limit on a key to cap how much it can spend.
• Rotate or revoke a key immediately if it may have leaked.

The x-api-key header

Pass your key in the x-api-key header on every request:

curl https://api.tnsaai.com/v1/chat/completions \
  -H "x-api-key: $TNSA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "NGen-4.3-Pro", "messages": [{ "role": "user", "content": "Hello" }] }'

Using an OpenAI client

The OpenAI-compatible endpoint at https://api.tnsaai.com/v1 works with OpenAI SDKs: change the base URL and send your key in the x-api-key header. See Libraries & SDKs.

import os
from openai import OpenAI

key = os.environ["TNSA_API_KEY"]
client = OpenAI(
    base_url="https://api.tnsaai.com/v1",
    api_key=key,
    default_headers={"x-api-key": key},
)

Credits

All of your keys spend from one prepaid credit balance, the same one the Playground uses. Add credits on the Billing page. A per-key spend limit caps what a single key can use, on top of the shared balance.

Authentication errors

• 401: no x-api-key header was sent.
• 402 insufficient_credits: your credit balance is used up. Top up on Billing.
• 403: the key is unknown, revoked, or over its spend limit.

See Error handling for the full list of status codes.