Router DeskHomeQwen3 Max
Qwen3 Max
“Qwen3 Max” now points at more than one card. Qwen3.7 Max is the flagship with a million-token window. The older qwen3-max slug is cheaper and shorter.
Updated 2026-09-27
| Slug | Input / M | Output / M | Context |
|---|---|---|---|
| qwen/qwen3.7-max | $1.475 | $4.425 | 1,000,000 |
| qwen/qwen3-max | $0.78 | $3.90 | 262,144 |
OpenRouter describes Qwen3.7 Max as the flagship of the Qwen3.7 series, aimed at agents, coding, and office tasks. Cache reads were $0.295 per million and cache writes $1.844 per million on that row. The older Qwen3 Max card is the one to keep if a prompt was tuned on the 262K model.
Set the id explicitly. A client that only says “qwen3-max” can land on either generation depending on how the app maps names. Qwen3.7 Max is still far below Claude Sonnet 5 ($2 / $10) and GPT-5.1 output ($10), and far above Qwen3 32B.
Questions
How much is Qwen3 Max?
qwen/qwen3.7-max was $1.475 / $4.425 per million tokens on 27 Sep 2026. qwen/qwen3-max was $0.78 / $3.90.
Which slug is the current Max?
qwen/qwen3.7-max. It has the 1,000,000-token window.
Is there a free Qwen3 Max?
Not these two slugs. A free Qwen in the catalog that day was qwen/qwen3.8-27b:free, which is a different model.
Related
- Qwen3 32B
Qwen3 32B is a dense 32.8B model. On 27 Sep 2026 OpenRouter priced qwen/qwen3-32b at $0.08 input and $0.28 output per million tokens.
- Qwen3 235B
Qwen3 235B A22B activates 22B of 235B parameters. On 27 Sep 2026 it was $0.455 input and $1.82 output per million tokens.
- GLM 5.2 API
GLM 5.2 on OpenRouter was $0.650 input and $2.042 output per million tokens on 27 Sep 2026. The slug is z-ai/glm-5.2, with a 1M context.
- Coding models
Coding-model choice on OpenRouter is price, context, and tool-call reliability. DeepSeek V4, Qwen3.7 Max, GLM 5.2, and Sonnet 5 are the slugs to price first.