tokenstat
tokenstat

GLM-4.5

zai-org/GLM-4.5 · rates as of · Benchmarks · Plans · Calculator

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Cheapest input
$0.3
$/MTok · models.dev
Cheapest output
$1.30
$/MTok
Context
131K
tokens
Offers
7
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.

SourceProviderInputOutputCache readContext
models.devcheapestzai-org/glm-4.5NanoGPT$0.3$1.30$0128K
LiteLLMzai-org/GLM-4.5$0.4$1.60$0.04
models.devzai-org/GLM-4.5Abacus$0.6$2.20$0131K
models.devzai-org/GLM-4.5Hugging Face$0.6$2.20$0131K
models.devzai-org/glm-4.5Jiekou.AI$0.6$2.20$0131K
models.devzai-org/glm-4.5Novita AI$0.6$2.20$0.11131K
LiteLLMzai-org/glm-4.5$0.6$2.20$0.11

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-07-28Family: 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