Qwen 3.8 Max Prime pricing
Source: openrouter · updated 2026-11-17
Short answer: Qwen 3.8 Max Prime costs $4.00 per million input tokens and $12.00 per million output tokens. That is a 3:1 blended rate of $6.00 per million tokens, ranking it #751 of 823 tracked models by input price.
Input / 1M
$4.00
Output / 1M
$12.00
Output ÷ input
3.00×
Context window
1,000,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $4.00 |
| Output, per 1M tokens | $12.00 |
| Output ÷ input multiple | 3.00× |
| 3:1 blended, per 1M tokens | $6.00 |
| Context window | 1,000,000 tokens |
| Vendor | qwen |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $4.00 | $3.00 | $7.00 |
| 10M in / 2.5M out | $40.00 | $30.00 | $70.00 |
| 100M in / 25M out | $400 | $300 | $700 |
Other qwen models
| Model | Input | Output |
|---|---|---|
| Qwen 3.7 Flash | $0.030 | $0.130 |
| Qwen 3.5 Flash 02 23 | $0.065 | $0.260 |
| Qwen 3 32 B | $0.080 | $0.280 |
| Qwen 3.5.9 B | $0.087 | $0.128 |
| Qwen 3 Next 80 B A3 B Instruct | $0.090 | $1.10 |
Cheaper alternatives
Next cheaper option: Gemini 2.5 Pro Preview Tts at $1.00 per 1M input tokens. Next step up: GPT-5.6 Terra Pro at $2.70 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.