Diterbitkan pada 2026-08-16 · 赵予安
Jawaban langsung
Zhipu GLM 5.1 CN is listed at 0.83 / 3.31 per million tokens. Context window and CacheSafety for this exact id stay unpublished. Panduan ini ditulis untuk tim produk dan platform yang membandingkan kualitas model, biaya, kebijakan routing, dan risiko peluncuran.
What shipped
GLM 5.1 CN is now live in the NextModel gateway catalog. The model id is z-ai/glm-5.1-cn, and the public slug is z-ai--glm-5.1-cn. The provider is Z Ai. The model has streaming support. The catalog assigns it to the quality use case. Its latency band is 1000 to 3000 ms.
Pricing
Input price is $0.83 per 1M tokens. Output price is $3.31 per 1M tokens. The context window is unpublished in the catalog snapshot. Related catalog entries include GLM 5 CN at $0.58 per 1M tokens in and $2.58 per 1M tokens out. GLM 5.2 CN is listed at $1.18 per 1M tokens in and $4.12 per 1M tokens out.
Who this is for
This is for teams that need a quality-focused model at a price point between GLM 5 CN and GLM 5.2 CN. The latency band fits interactive workloads. Streaming output is available for real-time use.
What is still unverified
The release date is unpublished in this catalog snapshot. Independent third-party quality scores are not in these notes. The context window is unpublished when the catalog value is zero. No first-party CacheSafety Bench row exists for this exact model. Safe Hit, Bad Hit, and trap rates are not reported.