Qwen3.8 Max (0902)
Qwen3.8 Max (0902) is a large language model made by Qwen, added to the catalog on 3 Sep 2026. It has a context window of 1,000,000 tokens and costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: summarising lengthy documents, working with prompts combining text and images and reviewing video alongside written material.
Price checked ยท source: OpenRouter
What Qwen3.8 Max (0902) is
Qwen3.8 Max (0902) is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a mixture-of-experts model with 2.4 trillion parameters. It accepts text, image, and video inputs and returns text. This makes it suited to prompts that combine written material with visual or video content, as well as text-only requests. Its listed context capacity is 1,000,000 tokens, with a maximum output of 131,072 tokens.
The model supports reasoning, tools, structured outputs, and response-format settings. These capabilities provide options for workflows that need the model to reason through a prompt, use tools when provided, or return information in a specified structure. The catalog does not specify particular tools, output schemas, or details about how image and video inputs are represented, so those depend on the surrounding interface and request.
With its large context window, the model can take in substantial amounts of supplied material within a request, subject to the context limit. This can suit tasks such as reviewing lengthy documents alongside images or video, extracting and organizing information into structured text, and drafting responses based on mixed-media prompts. Its text output also fits summarization, explanation, and other generation tasks. The listed modalities do not include audio, and the model is described as returning text rather than generated images or video.
Key features
- Accepts text, image, and video inputs and produces text
- Has a context length of 1,000,000 tokens
- Supports reasoning and tools
- Supports structured outputs and response-format settings
- Maximum output length is 131,072 tokens
Typical uses
- Summarising lengthy documents
- Working with prompts combining text and images
- Reviewing video alongside written material
- Producing structured text from supplied information
- Drafting responses to mixed-media prompts
Qwen3.8 Max (0902) pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $2.00 | $1.15 |
| Output, per 1M tokens | $6.00 | $3.45 |
| Cached input read, per 1M tokens | $0.25 | n/a |
| Variant | Model id |
|---|---|
| Batch | qwen/qwen3.8-max-0902:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 3 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0028 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.055 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.072 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.309 |
Qwen3.8 Max (0902) specifications
| Model id | qwen/qwen3.8-max-0902 |
|---|---|
| Version | qwen3.8-max-20260902 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 3 Sep 2026 |
| Input types | text, image, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Qwen3.8 Max (0902) yet.
Compare Qwen3.8 Max (0902)
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.