tokenstat
tokenstat
302ai

glm-5

302ai/glm-5 · rates as of · Benchmarks · Plans · Calculator

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
205K
tokens
Offers
18
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 offers. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestglm-5Alibaba Coding Plan (China)$0$0$0203K
models.devglm-5Alibaba Coding Plan$0$0$0203K
models.devglm-5Alibaba Token Plan (China)$0$0$0203K
models.devglm-5Alibaba Token Plan$0$0$0203K
models.devglm-5Tencent Coding Plan (China)$0$0$0203K
models.devglm-5CrofAI$0.48$1.90$0.1203K
models.devglm-5302.AI$0.6$2.60$0205K
models.devglm-5LLM Gateway$0.72$2.30$0.144203K
models.devglm-5DInference$0.75$2.40$0200K
LiteLLMglm-5$0.8$2.56$0.08
models.devglm-5Charm Hyper$0.85$2.62$0203K
models.devglm-5Alibaba / Qwen$0.86$3.15$0203K
LiteLLMGLM-5$0.95$3.15$0.095
models.devglm-5DigitalOcean$1$3.20$0203K
models.devglm-5OpenCode Go$1$3.20$0.2203K
models.devglm-5OpenCode Zen$1$3.20$0.2205K
models.devglm-5Zhipu / Z.ai$1$3.20$0.2205K
models.devglm-5Cortecs$1.08$3.44$0203K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2026-02-12Family: glm

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash