qwen
Qwen: Qwen3.7 Max
qwen/qwen3.7-max
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3.7-max is described in the OpenRouter catalog as the flagship model of Alibaba's Qwen3.7 series, aimed at agent-centric workloads with emphasis on coding and office productivity. It is text-in, text-out, exposes a very large context window, and supports tool calling, structured outputs, and optional reasoning. An independent model card was not available in this source pack, so capabilities are catalog-reported rather than verified; benchmark figures live in the structured catalog data and should be validated on your own workloads.[1]
Strengths
- Very large context window of one million tokens according to the catalog, suited to long documents and extended agent sessions.[1]
- Catalog description positions it for agent-centric work, with tool calling, tool choice, and structured output parameters listed as supported.[1]
- Reasoning is supported but optional rather than mandatory, alongside common controls such as seed, temperature, logprobs, and response formatting.[1]
Limitations
- Evidence is limited to the OpenRouter catalog; no independent model card was available in this source pack, so claims are unverified and need validation on your workloads.[1]
- Only text input and text output are listed; no other modalities are documented.[1]
- License terms, knowledge cutoff, and deployment or hardware requirements are not documented in the supplied evidence.[1]
Where to use it
- Worth prototyping for agentic coding and automation that benefit from tool calling and long context; not a proven fit without testing.[1]
- Candidate for office and productivity workflows over large text inputs, consistent with the catalog's stated design focus.[1]
- Consider for applications needing structured outputs or controllable reasoning, pending evaluation against your accuracy and latency requirements.[1]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3.7 MaxSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
Specifications
- Model ID
- qwen/qwen3.7-max
- Canonical ID
- qwen/qwen3.7-max-20260520
- Creator
- qwen
- Added to OpenRouter
- 21.05.2026
- Context length
- 1,000,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1.48 / out $4.43
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | AA — next 20% of the cohort | — |
| Agents | BB — next 30% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 66 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 22.5 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · agenticgamedevwin rate 45.6% · rank 20 | 1,107Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 47.8% · rank 29 | 1,147Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · blender3dwin rate 32.9% · rank 23 | 980Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 47.6% · rank 22 | 1,172Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 55.6% · rank 16 | 1,169Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 43.4% · rank 17 | 1,055Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 44.6% · rank 31 | 1,152Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · pdfwin rate 46.1% · rank 24 | 1,143Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 46.1% · rank 21 | 1,148Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 43.8% · rank 24 | 1,099Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · webappswin rate 48.4% · rank 23 | 1,190Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 53.8% · rank 32 | 1,248Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 53% · rank 24 | 1,205Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 53.8% · rank 32 | 1,266Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 53% · rank 25 | 1,274Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 52.3% · rank 33 | 1,256Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 54.9% · rank 26 | 1,207Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 53.5% · rank 37 | 1,264Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 54.6% · rank 30 | 1,268Elo | AA — next 20% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Alibaba | 1,000,000 | $1.48 | $4.43 | — | — | 100% |
| Alibaba | 1,000,000 | $2 | $6 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.