Qwen3.7 Max
Summary
Qwen3.7 Max is a proprietary language model from Alibaba (Qwen), released on 21 May 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $1.25 per million input tokens and $3.75 per million output tokens (Novita AI), across 6 providers we track.
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 21 May 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 1M (1,000,000 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
Qwen3.7 Max API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Novita AI qwen/qwen3.7-max | $1.25 | $3.75 | $0.25 | 1M | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3.7-max | $1.48 | $4.42 | $0.29 | 1M | OpenRouter, 18 Nov 2026 |
| Alibaba Cloud Model Studio qwen3.7-max | $2.50 | $7.50 | $0.50 | 1M | models.dev, 18 Nov 2026 |
| DeepInfra Qwen/Qwen3.7-Max | $2.50 | $7.50 | $0.50 | 256K | models.dev, 18 Nov 2026 |
| Together AI Qwen/Qwen3.7-Max | $2.50 | $7.50 | $0.50 | 1M | models.dev, 18 Nov 2026 |
| Vercel AI Gateway alibaba/qwen3.7-max | $2.50 | $7.50 | $0.50 | 991K | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Qwen3.7 Max?
Qwen3.7 Max has a context window of 1,000,000 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the Qwen3.7 Max API cost?
Through Alibaba Cloud Model Studio, Qwen3.7 Max costs $2.50 per million input tokens and $7.50 per million output tokens. The lowest listed price is $1.25 input / $3.75 output through Novita AI. Prices last verified 18 Nov 2026.
Is Qwen3.7 Max open source?
No. Qwen3.7 Max is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including Novita AI, OpenRouter, Alibaba Cloud Model Studio, DeepInfra.
When was Qwen3.7 Max released?
Alibaba (Qwen) released Qwen3.7 Max on 21 May 2026, according to models.dev.
Which providers offer Qwen3.7 Max?
We track Qwen3.7 Max on 6 providers: Novita AI, OpenRouter, Alibaba Cloud Model Studio, DeepInfra, Together AI, 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Muse Spark 1.1 | Meta | 8 Apr 2026 | 1M | $1.25 | $4.25 | Closed |
| Grok 4.3 | xAI | 17 Apr 2026 | 1M | $1.25 | $2.50 | Closed |
| Gemini 3.6 Flash | Google DeepMind | 21 Jul 2026 | 1M | $0.75 | $3.75 | Closed |
| Muse Spark 1.2 Contributor | Meta | 5 Aug 2026 | 1M | $1.25 | $4.25 | Closed |
| Gemini 3.7 Flash | Google DeepMind | 13 Aug 2026 | 1M | $0.75 | $3.75 | Closed |
| Grok 4.20 (Non-Reasoning) | xAI | 9 Mar 2026 | 1M | $1.25 | $2.50 | Closed |
Change history
- Together AI price changed: input $1.25 → $2.50, output $3.75 → $7.50 per 1M tokens
- Structured output changed from none to yes
Sources
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.7-max.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3.7-max.toml
- https://openrouter.ai/qwen/qwen3.7-max
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.7-Max.toml
- https://github.com/sst/models.dev/blob/dev/providers/togetherai/models/Qwen/Qwen3.7-Max.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/alibaba/qwen3.7-max.toml