Alibaba (Qwen) › Qwen3.7 Max › Pricing
Qwen3.7 Max pricing
API list price by Alibaba (Qwen) · checked Oct 23, 2026
$1.48 / $4.43per 1M tokens in / out
$0.29cache read · −80%
$1.15per task at thinking?
#206on OpenRouter by tokens · 9B / week
Price sheetper 1M tokens
| Input | $1.48 | list |
| Output | $4.43 | |
| Cache read | $0.29 | −80% vs input |
| Cache write | $1.84 | +25% vs input |
| Context · max output | 1M · 131K | tokens |
Where to buy5 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Novita | $1.25 | $3.75 | — |
| Alibaba | $1.48 | $4.43 | 1M |
| together | $1.50 | $4.50 | — |
| DeepInfra | $2.50 | $7.50 | — |
| qwen | $2.50 | $7.50 | — |
In Alibaba (Qwen)'s line-upper 1M in / out
| Qwen3.5 397B A17B | $0.60 / $3.60 | −39% |
| Qwen3 Next 80B A3B Thinking | $0.50 / $6 | −15% |
| Qwen 3.5 Omni Plus 2026-03-15 | $0.96 / $5.50 | −5% |
| Qwen3.7 Max | $1.48 / $4.43 | this model |
| Qwen3.8 2.4T A95B | $2 / $6 | +36% |
| Qwen3.8 Max (0902) | $2 / $6 | +36% |
| Qwen 2 VL 72B Instruct | $2.29 / $6.88 | +56% |
Cheaper for the same workvs Qwen3.7 Max
| GPT-6.1 Sol max | -37% | score +76% | $0.72 |
| GPT-6 Sol max | -9% | score +62% | $1.04 |
| Claude Sonnet 5.5 high | -23% | score +59% | $0.88 |
| MiMo v2.6 Pro thinkingOpen | -88% | score +57% | $0.13 |
| GPT-6 Astra low | -29% | score +55% | $0.82 |
Pricing questions
How much does Qwen3.7 Max cost?›
$1.48 per 1M input tokens and $4.43 per 1M output tokens. Cached input is $0.29. One Intelligence Index task costs about $1.15 at the default effort.
Is Qwen3.7 Max free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.29 per 1M, 80% below the input price. Writing to the cache costs $1.84 per 1M.
Is Qwen3.7 Max cheaper than Qwen3.6 Max Preview?›
Yes: $1.48 / $4.43 against $1.30 / $7.80, 24% less per token.
What is a cheaper alternative to Qwen3.7 Max?›
GPT-6.1 Sol at max effort costs -37% per task with a score +76% on Humanity's Last Exam.