{"slug": "glm-5-2-fast-via-wafer-now-available-on-ai-gateway", "title": "GLM 5.2 Fast via Wafer now available on AI Gateway", "summary": "Vercel's AI Gateway now offers GLM 5.2 Fast via Wafer, delivering 2x higher throughput than other providers in benchmarking tests. The model achieves over 170 tok/s for small contexts and over 200 tok/s for large contexts, with no markup or platform fees.", "body_md": "GLM 5.2 Fast via Wafer is now available on [AI Gateway](https://vercel.com/ai-gateway).\n\nBased on our own benchmarking across small-context, large-context, and tool-call scenarios, Wafer delivers a 2x higher throughput than other providers serving GLM-5.2 on serverless, leading on decode and end-to-end speed for sustained generation in the small- and large-context cases.\n\nIn our testing, GLM 5.2 Fast on Wafer measured:\n\nSmall context: 170+ tok/s\n\nLarge context: 200+ tok/s\n\nTo use GLM 5.2 Fast, set `model`\n\nto `zai/glm-5.2-fast`\n\nin the [AI SDK](https://ai-sdk.dev/):\n\nAI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in [custom reporting](https://vercel.com/changelog/custom-reporting-ai-gateway), [Zero Data Retention support](https://vercel.com/blog/zdr-on-ai-gateway), [budgets for API keys](https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys), and more.\n\nAI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on [Bring Your Own Key](https://vercel.com/docs/ai-gateway/authentication-and-byok/byok) (BYOK) requests.\n\nTry GLM 5.2 Fast in the [model playground](https://vercel.com/ai-gateway/models/glm-5.2-fast).", "url": "https://wpnews.pro/news/glm-5-2-fast-via-wafer-now-available-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/glm-5-2-fast-via-wafer-now-available-on-ai-gateway", "published_at": "2026-06-24 00:00:00+00:00", "updated_at": "2026-06-24 19:10:48.417643+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "ai-infrastructure", "ai-tools"], "entities": ["Vercel", "AI Gateway", "GLM 5.2 Fast", "Wafer", "AI SDK"], "alternates": {"html": "https://wpnews.pro/news/glm-5-2-fast-via-wafer-now-available-on-ai-gateway", "markdown": "https://wpnews.pro/news/glm-5-2-fast-via-wafer-now-available-on-ai-gateway.md", "text": "https://wpnews.pro/news/glm-5-2-fast-via-wafer-now-available-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/glm-5-2-fast-via-wafer-now-available-on-ai-gateway.jsonld"}}