Alibaba (Qwen) › Qwen 3.5 122B A10B › Pricing
Qwen 3.5 122B A10B pricing
API list price by Alibaba (Qwen) · checked Oct 23, 2026
$0.40 / $3.20per 1M tokens in / out
$0.32per task at thinking?
#199on OpenRouter by tokens · 10.5B / week
Price sheetper 1M tokens
| Input | $0.40 | list |
| Output | $3.20 | |
| Context · max output | 262K · 66K | tokens |
Where to buy8 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| lab-qwen | $0.12 | $0.92 | — |
| model-studio-international | $0.12 | $0.92 | — |
| Alibaba | $0.26 | $2.08 | 262K |
| SiliconFlow | $0.26 | $2.08 | 262K |
| DeepInfra | $0.29 | $2.40 | — |
| AtlasCloud | $0.30 | $2.40 | 262K |
| Novita | $0.40 | $3.20 | 262K |
| qwen | $0.40 | $3.20 | — |
In Alibaba (Qwen)'s line-upper 1M in / out
| Qwen3.5 Plus 2026-04-20 | $0.40 / $2.40 | −18% |
| Qwen3.8 27B | $0.42 / $2.55 | −13% |
| Qwen3 VL 235B A22B | $0.53 / $2.66 | −3% |
| Qwen 3.5 122B A10B | $0.40 / $3.20 | this model |
| Qwen 3 VL 235B A22B Thinking | $0.45 / $3.49 | +10% |
| Qwen3 235B A22B | $0.70 / $2.80 | +11% |
| Qwen Plus 2025-04-28 | $0.40 / $4 | +18% |
Cheaper for the same workvs Qwen 3.5 122B A10B
| GPT-6.1 Sol medium | -34% | score ×3.1 | $0.21 |
| MiMo v2.6 Pro thinkingOpen | -59% | score ×3 | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -19% | score ×2.9 | $0.26 |
| Claude Haiku 5.5 max | -34% | score ×2.8 | $0.21 |
| MiniMax M3.1 Flash thinking | -32% | score ×2.7 | $0.22 |
Pricing questions
How much does Qwen 3.5 122B A10B cost?›
$0.40 per 1M input tokens and $3.20 per 1M output tokens. One Intelligence Index task costs about $0.32 at the default effort.
Is Qwen 3.5 122B A10B free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
What is a cheaper alternative to Qwen 3.5 122B A10B?›
GPT-6.1 Sol at medium effort costs -34% per task with a score ×3.1 on Humanity's Last Exam.