tokenstat
tokenstat

Qwen3 VL 235B A22B Thinking

qwen/qwen3-vl-235b-a22b-thinking · rates as of · Benchmarks · Plans · Calculator

Qwen vision-language model for visual reasoning, documents, and agent tasks

Cheapest input
$0.22
$/MTok · LiteLLM
Cheapest output
$0.88
$/MTok
Context
262K
tokens
Offers
14
3 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
LiteLLMcheapestaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking$0.22$0.88$0.022
LiteLLMcheapestfireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking$0.22$0.88$0.022
models.devqwen/qwen3-vl-235b-a22b-thinkingKilo Gateway$0.4$4$0131K
models.devqwen/qwen3-vl-235b-a22b-thinkingOpenRouter$0.4$4$0131K
LiteLLMqwen3-vl-235b-a22b-thinking$0.4$4$0.04
LiteLLMdashscope/qwen3-vl-235b-a22b-thinking$0.4$4$0.04
models.devQwen/Qwen3-VL-235B-A22B-ThinkingSiliconFlow (China)$0.45$3.50$0262K
models.devQwen/Qwen3-VL-235B-A22B-ThinkingSiliconFlow$0.45$3.50$0262K
models.devqwen3-vl-235b-a22b-thinkingNanoGPT$0.5$6$033K
models.devqwen/qwen3-vl-235b-a22b-thinkingNovita AI$0.98$3.95$0131K
OpenRouterqwen/qwen3-vl-235b-a22b-thinkingOpenRouter$0.98$3.95$0131K
models.devqwen3-vl-235b-a22b-thinkingLLM Gateway$0.98$3.95$0131K
LiteLLMqwen/qwen3-vl-235b-a22b-thinking$0.98$3.95$0.098
LiteLLMnovita/qwen/qwen3-vl-235b-a22b-thinking$0.98$3.95$0.098

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • Out: text
Knowledge cutoff: 2025-03-31Released: 2025-09-23Family: 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