tokenstat
tokenstat

Qwen3.6 Flash

qwen/qwen3.6-flash · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.165
$/MTok · models.dev
Cheapest output
$0.99
$/MTok
Context
1M
tokens
Offers
15
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. Free/$0 listings are hidden by default (2 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
models.devcheapestqwen/qwen3.6-flashMerge Gateway$0.165$0.99$0.0331M
models.devqwen3.6-flashAIHubMix$0.17$1.01$0.0169991K
models.devqwen/qwen3.6-flashKilo Gateway$0.1875$1.13$01M
OpenRouterqwen/qwen3.6-flashOpenRouter$0.1875$1.13$01M
models.devqwen3.6-flashAlibaba / Qwen$0.1875$1.13$01M
models.devqwen3.6-flashAlibaba Coding Plan (China)$0.1875$1.13$01M
models.devqwen3.6-flashAlibaba Coding Plan$0.1875$1.13$01M
models.devqwen3.6-flashAlibaba / Qwen$0.1875$1.13$01M
models.devqwen3.6-flashPioneer$0.1875$1.13$0.03751M
models.devqwen/qwen3.6-flashCrossModel$0.19$1.13$0.0191M
models.devalibaba/qwen3.6-flashNanoGPT$0.19$1.16$0992K
models.devqwen/qwen3.6-flashImpossibl$0.25$1.50$0.051M
models.devqwen3-6-flashEmpirioLabs AI$0.25$1.50$0.251M
models.devqwen3.6-flashLLM Gateway$0.25$1.50$0.051M
models.devqwen3.6-flashCharm Hyper$1$4$0.11M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • Out: text
Knowledge cutoff: 2025-04Released: 2026-04-27Family: qwen3.6

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