tokenstat
tokenstat
302ai

glm-4.7

302ai/glm-4.7 · 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
15
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-4.7Alibaba Coding Plan (China)$0$0$0203K
models.devglm-4.7Alibaba Coding Plan$0$0$0203K
models.devGLM-4.7KUAE Cloud Coding Plan$0$0$0205K
models.devglm-4.7Z.AI Coding Plan$0$0$0205K
models.devglm-4.7Zhipu AI Coding Plan$0$0$0205K
models.devglm-4.7CrofAI$0.25$1.10$0.05203K
models.devglm-4.7302.AI$0.286$1.14$0205K
models.devglm-4.7LLM Gateway$0.38$1.98$0.19205K
LiteLLMglm-4.7$0.4$1.50$0
models.devglm-4.7DInference$0.45$1.65$0200K
models.devglm-4.7Cortecs$0.45$2.23$0198K
models.devglm-4.7OpenCode Zen$0.6$2.20$0.1205K
models.devglm-4.7Zhipu / Z.ai$0.6$2.20$0.11205K
LiteLLMGLM-4.7$0.6$2.20$0.06
models.devGLM-4.7Moark$3.50$14$0205K

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-12-22Family: glm

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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