How I get usage credit without juggling a dedicated Token Pass key
Using a scoped Token Pass key means requests stop entirely once its credit runs out for the billing period. Vercel now applies Token Pass credit automatically to included AI Gateway usage regardless of auth method, so a standard API key or OIDC token gets the credit and falls back to team credits instead of failing.
What it is
Token Pass credit now applies automatically across AI Gateway for included model usage, whether a request authenticates with an API key, OIDC token, or fx login. When credit runs out for the billing period, standard keys and OIDC tokens fall back to your team's AI Gateway credits, while Token Pass keys stop until the next period.
Applied case
A developer on a Pro team who created a Token Pass key during setup can switch to a standard API key or OIDC token and still consume Token Pass credit on included models. If the credit runs dry mid-period, their standard-key requests keep working by drawing on team AI Gateway credits instead of failing outright. Requests through the Token Pass provider remain Zero Data Retention, and fallback requests follow the team setting: with team-wide ZDR enabled, they route only to ZDR providers.
- Swap a Token Pass key for a standard key or OIDC token to gain fallback behavior
When to use it
Use when you are a Token Pass subscriber on a Pro team and want automatic credit plus fallback to team credits. Skip when you need keys scoped only to featured models and providers, where a dedicated Token Pass key still applies.
Read more
Recommended for you
- WorkflowVercel
When to use a vision coding agent instead of a plain LLM?
Text-only models miss detail in screenshots and charts, and drift on long-running agent tasks across a large codebase.
- WorkflowOpencode
How do you keep coding agents on task without babysitting every step?
Agent sessions drift from the objective, forcing you to watch every turn; opencode's /goal lets a session run until a reviewer confirms the goal is met.
- WorkflowHerdr
How do you supervise coding agents without watching every window?
I run Claude and opencode side by side in one terminal. Three herdr habits replaced window-polling with state-waiting: persistent sessions, the agent loop, a setup script.
- WorkflowSuperpowersClaude Code
Why does your multi-agent workflow keep colliding?
Two agents in two threads share files but not context. Both decide on stale state. Fix: one fresh agent per task, with isolated context.
Enjoyed this article?
Subscribe for new articles. No spam. Unsubscribe anytime.