GLM 5.2 now available on AI Gateway
1M context window. GLM 5.2 just shipped on Vercel's AI Gateway with 5x the token capacity of its predecessor.
Why it matters
Vercel expands model availability on AI Gateway with GLM 5.2, positioning itself as a neutral API aggregator for developers. The 1M token context and improved task reliability signal competitive pressure in the inference API layer.
The key facts
11 to knowGLM 5.2 context window: 1M tokens (up from 200K in GLM 5.1)
5x increase in context capacity
Built for long-horizon tasks with project-level engineering context
AI Gateway offers unified API, usage tracking, cost management, retries, failover, performance optimization
No platform fee on inference; reflects provider pricing with zero markup
Zero Data Retention support available
Available via Vercel AI SDK (model: zai/glm-5.2)
Includes custom reporting, budgets for API keys, Bring Your Own Key (BYOK) support
Available via Vercel AI Gateway
AI Gateway features: unified API, usage/cost tracking, retries, failover, performance optimization, Zero Data Retention support, BYOK (Bring Your Own Key) capability
No platform fee on inference; reflects provider pricing with no markup
Go to the source
Vercel Blogvercel.com
Publisher excerpt: GLM 5.2 is now available on .AI Gateway Built for long-horizon tasks, GLM 5.2 carries project-level engineering context across a single task, runs long-running tasks more reliably, and follows engineering standards more consistently. The context window for this model has been upgraded to 1M tokens,…