tokenstat
homepricingstatshelpsign in
tokenstat
Alibaba / Qwen

Qwen3 235B A22B Instruct 2507 FP8

Qwen/Qwen3-235B-A22B-Instruct-2507-tput · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.2
$/MTok · models.dev
Cheapest output
$0.6
$/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-tputTogether AI$0.2$0.6$0262K
LiteLLMQwen/Qwen3-235B-A22B-Instruct-2507-tput—$0.2$6$0.02—
LiteLLMQwen3-235B-A22B-Instruct-2507-tput—$0.2$6$0.02—
LiteLLMtogether_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput—$0.2$6$0.02—

Capabilities

  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-07Released: 2025-07-25Family: 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