Qwen: Qwen3 Next 80B A3B Thinking API Pricing
by qwen · 128K context window ·
$0.150
Input /1M tokens
$1.200
Output /1M tokens
128K
Context window
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | $0.07 |
| 1M tokens/month | $0.67 |
| 10M tokens/month | $6.75 |
| 100M tokens/month | $67.50 |
Compare with other models
Qwen: Qwen3 Next 80B A3B Thinking vs OpenAI: GPT-4o →Qwen: Qwen3 Next 80B A3B Thinking vs OpenAI: GPT-4o-mini →Qwen: Qwen3 Next 80B A3B Thinking vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use Qwen: Qwen3 Next 80B A3B Thinking when your quality requirements demand it.