Alibaba (Qwen) › Qwen3.8 Max › Pricing
Qwen3.8 Max pricing
API list price by Alibaba (Qwen) · checked Oct 23, 2026
$2 / $6per 1M tokens in / out
$0.25cache read · −87%
$2.67per task at thinking?
#65on OpenRouter by tokens · 204.3B / week
Price sheetper 1M tokens
| Input | $2 | list |
| Output | $6 | |
| Cache read | $0.25 | −87% vs input |
| Cache write | $2.50 | +25% vs input |
| Context · max output | 1M · 131K | tokens |
Where to buy4 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $1.65 | $4.95 | — |
| Alibaba | $2 | $6 | 1M |
| fireworks | $2 | $6 | — |
| Novita | $2 | $6 | — |
In Alibaba (Qwen)'s line-upper 1M in / out
| Qwen 2 VL 7B Instruct | $0 / $0 | −100% |
| Decision Model Preview | $0 / $0 | −100% |
| Qwen3.5 0.8B | $0.01 / $0.05 | −99% |
| Qwen3.5 2B | $0.02 / $0.10 | −99% |
| Qwen3Guard Gen 0.6B | $0.04 / $0.08 | −98% |
| Qwen VL OCR | $0.043 / $0.072 | −98% |
| Qwen VL OCR 2025-11-20 | $0.043 / $0.072 | −98% |
Cheaper for the same workvs Qwen Max
| Claude Opus 5.5 high | -32% | score +33% | $1.82 |
| Gemini 4 Argon high | -25% | score +31% | $1.99 |
| GPT-6 Astra xhigh | -14% | score +30% | $2.31 |
| Claude Sonnet 5.5 xhigh | -25% | score +29% | $2.01 |
| GPT-6.1 Sol max | -73% | score +29% | $0.72 |
Pricing questions
How much does Qwen3.8 Max cost?›
$2 per 1M input tokens and $6 per 1M output tokens. Cached input is $0.25. One Intelligence Index task costs about $2.67 at the default effort.
Is Qwen3.8 Max free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.25 per 1M, 87% below the input price. Writing to the cache costs $2.50 per 1M.
Is Qwen3.8 Max cheaper than Qwen3.7 Max?›
No: $2 / $6 against $1.48 / $4.43, 36% more per token.
What is a cheaper alternative to Qwen3.8 Max?›
Claude Opus 5.5 at high effort costs -32% per task with a score +33% on .