Qwen3.7 Max: API pricing, providers and specs
Qwen3.7 Max is a text model by Alibaba. 27 providers serve it, from $3.75 to $11.25 /1M; the lowest price is at ZenMux.
A newer version is out: Qwen3.8 Max
How Qwen3.7 Max compares
Against the 737 text models on the site priced the same way.
- Pricey for its class: at $3.75 /1M, its lowest price is above 74% of comparable models (median $1.10).
- Its 1M-token context window is larger than 67% of them (median 262K), about 1500 pages of text.
- On LMArena's WebDev board it ranks #44 of the 64 comparable models scored there.
- 27 providers serve it; 94% of comparable models have fewer.
Qwen3.7 Max prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| ZenMux | $1.25/1M | $3.75/1M | $0.125/1M | 1M |
 Novita AI | $1.25/1M | $3.75/1M | $0.25/1M | — |
 OrcaRouter | $1.25/1M | $3.75/1M | $0.25/1M | 1M |
| DevPass (LLM Gateway) | $1.25/1M | From$3.75/1M | $0.25/1M | — |
| APIMart | $1.37/1M | $4.11/1M | — | — |
| OpenRouter | $1.48/1M | From$4.42/1M | $0.295/1M | 1M |
 Together AI | $1.50/1M | $4.50/1M | $0.30/1M | — |
 AlibabaOfficial | $1.65/1M | $4.95/1M | — | — |
 AIHubMix | $1.69/1M | $5.07/1M | $0.169/1M | 1M |
 Ofox | $1.71/1M | $5.14/1M | $0.17/1M | 1.06M |
 APIYI | $1.71/1M | $5.14/1M | — | — |
 LaoZhang API | $1.71/1M | $5.14/1M | — | — |
 CrossModel | $1.88/1M | $5.63/1M | $0.375/1M | — |
 CometAPI | $2/1M | $6/1M | $0.20/1M | — |
| AI/ML API | $2/1M | $6/1M | $2/1M | — |
| AlibabaOfficial | $2.50/1M | From$7.50/1M | — | — |
 Requesty | $2.50/1M | From$7.50/1M | $0.25/1M | 1.05M |
 Charm Hyper | $2.50/1M | $7.50/1M | $0.50/1M | — |
| Vercel AI Gateway | $2.50/1M | $7.50/1M | $0.50/1M | 991K |
 NEAR AI Cloud | $2.80/1M | $7.50/1M | — | 1M |
 Deep Infra | $2.50/1M | $7.50/1M | $0.50/1M | — |
 Impossibl | $2.50/1M | $7.50/1M | $0.50/1M | — |
 EmpirioLabs AI | $2.50/1M | $7.50/1M | $2.50/1M | 1M |
| Atlas Cloud | $2.50/1M | $7.50/1M | $0.50/1M | — |
 Poe | $2.53/1M | $7.58/1M | — | 1M |
 Venice AI | $2.70/1M | $8.05/1M | $0.27/1M | — |
 Prime Inference | $3.75/1M | $11.25/1M | — | — |
- ZenMux$3.75
- Novita AI$3.75
- OrcaRouter$3.75
- DevPass (LLM Gateway)From$3.75
- APIMart$4.11
- OpenRouterFrom$4.42
- Together AI$4.50
- AlibabaOfficial$4.95
- AIHubMix$5.07
- Ofox$5.14
- APIYI$5.14
- LaoZhang API$5.14
Specs
- Type
- Text
- Maker
- Alibaba
- Inputs
- Text
- Outputs
- Text
- Context
- 1M≈ 1500 pages of text
- Max output
- 131K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling
- Released
- May 21, 2026
- License
- proprietary
- Open weights
- No, API only
- Arena score
- 1515WebDev
- Monthly searches
- 3K
Alternatives to Qwen3.7 Max
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Qwen3.7 Maxthis model | $3.75/1M | 1M | 1515 | 27 |
 Gemini 4 Argon | $8/1M | 1.05M | 1673 | 26 |
| Kimi K3 | $8.28/1M | 1.05M | 1655 | 47 |
| GPT-6.1 Sol | $8/1M | 1.05M | 1749 | 27 |
| GPT-6 Sol | $8/1M | 1.05M | 1682 | 28 |
| Grok 4.7 | $4.80/1M | 500K | 1637 | 28 |
| Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Muse Spark 1.3 | $4.25/1M | 1.05M | 1657 | 11 |
More from Alibaba
Qwen-Image-2.1Alibaba$0.02/imgQwen3.8 2.4T A95BAlibaba$4.11/1MWan3.0Alibaba$0.025/secQwen3.8 27BAlibaba$0.50/1MWan 2.2Alibaba$0.01/runQwen3.8 Flash NextAlibaba$0.376/1MQwen2-1.5B-InstructAlibaba$0.20/1MQwen3.5 FlashAlibaba$0.287/1MQwen3.7 Max FAQ
ZenMux, at $3.75 /1M. 27 providers serve Qwen3.7 Max; the table above lists every one with its price.
Qwen3.7 Max reads up to 1M tokens per request and writes up to 131K.
No. Qwen3.7 Max is only available through an API; Alibaba does not publish its weights.
27 API providers serve Qwen3.7 Max. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us