tokenstat
tokenstat

Qwen3 VL 235B A22B Instruct

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

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

Cheapest input
$0.21
$/MTok · OpenRouter
Cheapest output
$1.90
$/MTok
Context
262K
tokens
Offers
8
3 sources

Price changes

Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ riseOutput $0.88 → $1.90
  • ↑ riseInput $0.2 → $0.21

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
OpenRoutercheapestqwen/qwen3-vl-235b-a22b-instructOpenRouter$0.21$1.90$0.1262K
models.devqwen/qwen3-vl-235b-a22b-instructTensorX$0.21$1.90$0.0525131K
models.devqwen/qwen3-vl-235b-a22b-instructKilo Gateway$0.26$1.04$0131K
models.devqwen/Qwen3-VL-235B-A22B-InstructNanoGPT$0.3$1.20$0128K
models.devqwen/qwen3-vl-235b-a22b-instructNovita AI$0.3$1.50$0131K
models.devQwen/Qwen3-VL-235B-A22B-InstructSiliconFlow (China)$0.3$1.50$0262K
models.devQwen/Qwen3-VL-235B-A22B-InstructSiliconFlow$0.3$1.50$0262K
LiteLLMqwen/qwen3-vl-235b-a22b-instruct$0.3$1.50$0.03

Capabilities

  • 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