tokenstat
tokenstat

GLM 4.5 Air

z-ai/glm-4.5-air · rates as of · Benchmarks · Plans · Calculator

Efficient GLM model for fast reasoning, coding, and agent workflows

Cheapest input
$0.11
$/MTok · models.dev
Cheapest output
$0.56
$/MTok
Context
131K
tokens
Offers
4
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.devcheapestz-ai/glm-4.5-airZenMux$0.11$0.56$0.02128K
models.devz-ai/glm-4.5-airKilo Gateway$0.13$0.85$0.025131K
OpenRouterz-ai/glm-4.5-airOpenRouter$0.13$0.85$0.025131K
models.devz-ai/glm-4.5-airOrcaRouter$0.2$1.10$0.03131K

Capabilities

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

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