Qwen3.7 Max
Qwen3.7 Max is a large language model made by Qwen, added to the catalog on 21 May 2026. It has a context window of 1,000,000 tokens and costs $1.475 per 1M input tokens and $4.425 per 1M output tokens. It accepts text and produces text. Typical uses: coding assistance, office and productivity workflows and text-based tasks involving tools.
Price checked · source: OpenRouter
What Qwen3.7 Max is
Qwen3.7 Max is Alibaba’s flagship model in the Qwen3.7 series. It accepts text and produces text, and is described as designed for agent-centric workloads. Its stated areas of strength include coding, office work, and productivity tasks. The model supports reasoning and tool use, alongside structured outputs and response-format options. These capabilities suit workflows that combine text-based requests with tools or require output in a specified structure, without implying any particular tool setup or result.
It has a context length of 1,000,000 tokens and a maximum output length of 131,072 tokens. The context limit can accommodate extended text inputs or substantial material in one request, while the output limit allows for lengthy generated responses when needed. The context figure describes how much input context it can accommodate; it is distinct from the maximum length of a single generated output. The facts do not specify particular file types, programming languages, tools, or response schemas, so those details depend on the implementation using the model. Qwen3.7 Max may suit coding assistance, text-based office and productivity workflows, and tasks involving reasoning or structured text. Its listed input and output modalities are text; image and audio processing are not listed. Practical use depends on the surrounding application and how it configures tools, response formats, and structured output.
Key features
- Accepts text input and produces text output
- Has a context length of 1,000,000 tokens
- Supports a maximum output of 131,072 tokens
- Supports tools, reasoning, and structured outputs
- Includes response-format support
Typical uses
- Coding assistance
- Office and productivity workflows
- Text-based tasks involving tools
- Generating structured text
- Reasoning over extended text
Qwen3.7 Max pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.475 |
| Output, per 1M tokens | $4.425 |
| Cached input read, per 1M tokens | $0.295 |
| Cache write, per 1M tokens | $1.844 |
No price change since it was added on 21 May 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0021 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.040 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.053 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.228 |
Qwen3.7 Max specifications
| Model id | qwen/qwen3.7-max |
|---|---|
| Version | qwen3.7-max-20260520 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 May 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| 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 Qwen3.7 Max yet.
Compare Qwen3.7 Max
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.