tokenstat
tokenstat

Qwen3 235B A22B Instruct

qwen/qwen3-235b-a22b-instruct-2507-maas · rates as of · Benchmarks · Plans · Calculator

Qwen instruction model for multilingual chat, reasoning, and tool use

Cheapest input
$0.22
$/MTok · models.dev
Cheapest output
$0.88
$/MTok
Context
262K
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.devcheapestqwen/qwen3-235b-a22b-instruct-2507-maasGoogle Vertex AI$0.22$0.88$0262K
LiteLLMqwen/qwen3-235b-a22b-instruct-2507-maas$0.25$1$0.025
LiteLLMqwen3-235b-a22b-instruct-2507-maas$0.25$1$0.025
LiteLLMvertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas$0.25$1$0.025

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2025-08-13Family: qwen

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