Alibaba (Qwen)

Qwen3.8 Max 0902

Generally availableProprietary991K contextReasoning

Summary

Qwen3.8 Max 0902 is a proprietary language model from Alibaba (Qwen), released on 2 Sept 2026. It accepts text, images and PDFs and generates text, with a 991K-token context window and up to 128K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $2 per million input tokens and $6 per million output tokens (OpenRouter), across 2 providers we track.

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

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperAlibaba (Qwen)
Release date2 Sept 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window991K (991,000 tokens) [models.dev]
Max output128K tokens [models.dev]
InputText, images and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]

Qwen3.8 Max 0902 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
qwen/qwen3.8-max-0902
$2$6$0.251MOpenRouter, 18 Nov 2026
Vercel AI Gateway
alibaba/qwen3.8-max-0902
$2$6$0.25991Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Qwen3.8 Max 0902?

Qwen3.8 Max 0902 has a context window of 991,000 tokens (991K) and can generate up to 128,000 tokens in a single response, according to models.dev.

How much does the Qwen3.8 Max 0902 API cost?

Qwen3.8 Max 0902 is listed from $2 per million input tokens and $6 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Qwen3.8 Max 0902 open source?

No. Qwen3.8 Max 0902 is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including OpenRouter, Vercel AI Gateway.

When was Qwen3.8 Max 0902 released?

Alibaba (Qwen) released Qwen3.8 Max 0902 on 2 Sept 2026, according to models.dev.

Which providers offer Qwen3.8 Max 0902?

We track Qwen3.8 Max 0902 on 2 providers: OpenRouter, Vercel AI Gateway.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Fugu MaxSakana11 Sept 20261M$2$6Closed
GLM 5.3 PrimeZhipu AI (Z.ai)23 Sept 20261M$1.68$5.28–
Muse Spark 1.3 ContributorMeta2 Sept 20261M$1.25$4.25Closed
Claude Sonnet 5.5Anthropic28 Sept 20261M$2$10Closed
GPT-6 SolOpenAI22 Sept 20261.1M$2$10Closed
GPT-6 Sol ProOpenAI22 Sept 20261.1M$2$10–

Change history

  • Input modalities changed from text, image, video to text, image, pdf
  • Max output changed from 131K to 128K
  • Context window changed from 1M to 991K
  • Context window changed from 991K to 1M
  • Input modalities changed from text, image, pdf to text, image, video
  • Max output changed from 128K to 131K
  • Context window changed from 1M to 991K
  • Input modalities changed from text, image, video to text, image, pdf
  • Max output changed from 131K to 128K
  • Input modalities changed from text, image, pdf to text, image, video
  • Max output changed from 128K to 131K
  • Context window changed from 991K to 1M
  • Context window changed from 1M to 991K
  • Input modalities changed from text, image, video to text, image, pdf
  • Max output changed from 131K to 128K
  • Max output changed from 128K to 131K
  • Input modalities changed from text, image, pdf to text, image, video
  • Context window changed from 991K to 1M
  • Max output changed from 131K to 128K
  • Context window changed from 1M to 991K
  • Input modalities changed from text, image, video to text, image, pdf
  • Input modalities changed from text, image, pdf to text, image, video
  • Max output changed from 128K to 131K
  • Context window changed from 991K to 1M
  • Context window changed from 1M to 991K

Sources