tokenstat
tokenstat

Qwen3.8 Max

qwen/qwen3.8-max · rates as of · Benchmarks · Plans · Calculator

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...

Cheapest input
$2
$/MTok · OpenRouter
Cheapest output
$6
$/MTok
Context
1M
tokens
Offers
5
4 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
OpenRoutercheapestqwen/qwen3.8-maxOpenRouter$2$6$0.251M
seedqwen/qwen3.8-maxAlibaba / Qwen$2$6$0.251M
models.devqwen3.8-maxOpenCode Go$2$6$0.251M
LiteLLMqwen3.8-max$2$6$0.25
LiteLLMdashscope/qwen3.8-max$2$6$0.25

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • Out: text
Released: 2026-08-03Family: qwen

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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