GLM 5.3 Flash is now available in Token Pass

Vercel added GLM 5.3 Flash to Token Pass, its monthly subscription for open-weight models through AI Gateway. It joins Kimi K3, GLM 5.3, and DeepSeek V4.1 Flash, with more models planned.

GLM 5.3 Flash is Z.ai's native multimodal coding model with a 1M-token context window. You can add it from the Token Pass page in your team's AI Gateway dashboard. The model ID is zai/glm-5.3-flash. Vercel lists it at $0.15 per million input tokens and $0.50 per million output tokens, which is what each request deducts from your credit.

Token Pass costs $30 a month per team and gives you $80 in credit. It works with any coding agent that connects to AI Gateway, such as fx, Pi, Cline, or Command Code, or with agents you build on the AI SDK. Requests use zero data retention.

It's in Early Access and only on Pro teams, so Enterprise teams can't subscribe, and when spots run out the tab shows a waitlist. Credit is shared across the team and expires at the end of each billing period. If it runs out, standard API keys fall back to your regular AI Gateway credits, while keys restricted to Token Pass stop working until the next period.