tokenstat
homepricingstatshelpsign in
tokenstat
Alibaba / Qwen

Qwen3.7 Flash

alibaba-cn/qwen3.7-flash · rates as of · Benchmarks · Plans · Calculator

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Cheapest input
$0.0296
$/MTok · models.dev
Cheapest output
$0.1185
$/MTok
Context
1M
tokens
Offers
4
1 source

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.devcheapestqwen3.7-flashAlibaba / Qwen$0.0296$0.1185$0.0031M
models.devqwen3-7-flashEmpirioLabs AI$0.03$0.13$0.0061M
models.devqwen3.7-flashLLM Gateway$0.03$0.13$0.0061M
models.devqwen3.7-flashCharm Hyper$0.2$0.8$0.041M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • Out: text
Released: 2026-07-15Family: 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