tokenstat
tokenstat
Alibaba / Qwen

Qwen3.8 Max

Qwen/Qwen3.8-Max · rates as of · Benchmarks · AI plans · Calculator

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
1.0M
tokens
Sources
3
46 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 listings. Hide them.

SourceProviderInputOutputCache readContext
tokenstatqwen/qwen3.8-maxAlibaba / Qwen$2$6$0.251M
models.devcheapestqwen3.8-maxAlibaba Token Plan (China)$0$0$01M
models.devqwen3.8-maxAlibaba Token Plan$0$0$01M
models.devqwen3-8-maxKenari$0$0$01M
models.devQwen3.8-MaxSCNet Token Plan$0$0$01M
models.devqwen3.8-maxVancine$1.60$4.80$0.21M
models.devQwen/Qwen3.8-MaxDeepInfra$1.65$4.95$0.206256K
LiteLLMQwen/Qwen3.8-MaxN/A$1.65$4.95$0.206N/A
LiteLLMQwen3.8-MaxN/A$1.65$4.99$0.21N/A
LiteLLMscx-ai/Qwen3.8-MaxN/A$1.65$4.99$0.21N/A
models.devqwen3.8-maxAIHubMix$1.69$5.07$0.169991K
models.devqwen/qwen3.8-maxOfox$1.71$5.14$0.171M
models.devqwen3.8-maxAlibaba / Qwen$1.78$5.33$0.22221M
models.devQwen3.8-MaxSCX.Ai$1.81$5.45$0.171M
models.devqwen/qwen3.8-maxCrossModel$1.88$5.63$0.231M
models.devqwen/qwen3.8-maxEden AI$2$6$0.251M
models.devqwen/qwen3.8-maxMerge Gateway$2$6$0.251M
models.devqwen/qwen3.8-maxNanoGPT$2$6$0.25991K
models.devqwen/qwen3.8-maxOrcaRouter$2$6$0.251M
models.devqwen3.8-maxAbacus$2$6$01M
models.devqwen3.8-maxAlibaba / Qwen$2$6$0.251M
models.devalibaba/qwen3.8-maxCloudflare$2$6$0.251M
models.devqwen3.8-maxDigitalOcean$2$6$0.21M
models.devqwen3-8-maxEmpirioLabs AI$2$6$21M
models.devqwen3.8-maxCharm Hyper$2$6$0.251M
models.devscx-ai-gp/qwen3.8-maxLLM Gateway$2$6$0.251M
models.devqwen3.8-maxDevPass (LLM Gateway)$2$6$0.251M
models.devqwen3.8-maxOpenCode Go$2$6$0.251M
models.devqwen3.8-maxOpper$2$6$0.25984K
models.devqwen3.8-maxRequesty$2$6$0.251.0M
models.devalibaba/qwen3.8-maxVercel AI Gateway$2$6$0.25262K
models.devcline-pass/qwen3.8-maxClinePass$2$6$0.251M
models.devaccounts/fireworks/models/qwen3p8-maxFireworks AI$2$6$0.25262K
models.devqwen/qwen3.8-max:thinkingNanoGPT$2$6$0.25991K
models.devbailian/qwen3.8-maxOfox$2$6$0.251M
LiteLLMqwen/qwen3.8-maxN/A$2$6$0.25N/A
LiteLLMqwen3.8-maxN/A$2$6$0.25N/A
LiteLLMaccounts/fireworks/models/qwen3p8-maxN/A$2$6$0.25N/A
LiteLLMdashscope/qwen3.8-maxN/A$2$6$0.25N/A
LiteLLMnovita/qwen/qwen3.8-maxN/A$2$6$0.25N/A
LiteLLMopenrouter/qwen/qwen3.8-maxN/A$2$6$0.25N/A
LiteLLMqwen3p8-maxN/A$2$6$0.25N/A
LiteLLMqwen_ai_platform/qwen3.8-maxN/A$2$6$0.25N/A
LiteLLMqwencloud/qwen3.8-maxN/A$2$6$0.25N/A
models.devqwen3.8-max302.AI$2.16$6.36$01M
models.devqwen3.8-maxAbove.Dev$2.20$6.60$0.2751M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • In: pdf
  • 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. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayIn review

Data and list-price estimates may contain mistakes. Not investment advice.