Quickstart

Planned requests use a bearer token in the Authorization header.

Authorization: Bearer $TFF_API_KEY

Keys are not being issued in the current release.

https://api.tokenforfree.com/v1

This hostname is reserved for the planned API. It may not accept requests yet.

Chat Completions

The planned interface follows the familiar OpenAI Chat Completions request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokenforfree.com/v1",
    api_key="YOUR_TFF_API_KEY",
)

response = client.chat.completions.create(
    model="tff/free",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

Models

Routing profiles keep application code stable while the underlying eligible free source can change.

Errors

The planned API will use standard HTTP status codes and a compact JSON error body.

Error semantics may change before API launch.

Rate Limits

Limits will depend on available free supply and may vary by route. Exact policies will be published with the backend launch.