Intel / article

Introducing Token Pass

Source: vercel.com
Author: Jas Garcha
Date: Published Oct 15, 2026

Context

Pass is a fixed monthly subscription for using two models through Vercel's AI Gateway, rather than paying per request. In early access for Pro teams, it costs $30 a month and gives the team $80 of monthly credit to spend on Z.ai's GLM 5.3 and Moonshot AI's Kimi K3, with more models promised. The credit is shared across the team, and members can switch between the included models from coding agents such as fx, Command Code and Pi, or from agents they build with the AI SDK, using a dedicated Token Pass API key (vercel.com).

The billing rules make spending predictable in both directions. The subscription renews monthly unless canceled, unused credit does not carry over to the next month, and when the credit is used up, Token Pass requests simply stop until the next billing period instead of incurring automatic overage charges. A team that runs out mid-month therefore loses access through the pass rather than receiving a larger bill.

The privacy settings are also fixed rather than left to configuration. Zero Data Retention is on by default: requests go through selected providers with in the US and EU, and both AI Gateway and the provider delete prompts and responses after each request, with prompts not used for training. That differs from ordinary gateway access to Kimi K3, where earlier coverage noted that zero data retention has to be switched on in gateway settings or per request (vercel.com).

Key takeaways · AI-distilled

Vercel names fx, Command Code, and Pi as coding agents that work with Token Pass, and says teams can also build their own with the AI SDK and switch between the included models on the shared team credit.
Zero Data Retention is on by default: requests run on selected providers with inference in the US and EU, prompts and responses are deleted after each request, and prompts are not used to train models, per the post.
The subscription renews monthly unless canceled, and any unused credit does not roll over into the next billing period.
Setup runs through the Token Pass page in the team's AI Gateway dashboard: activate the subscription, create a dedicated Token Pass API key, connect the agent, then select GLM 5.3 or Kimi K3.

Terms in this piece · Glossary

token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

Read the source vercel.com