Qwen 2.5 VL 72 B Instruct pricing
Source: openrouter · updated 2026-10-28
Short answer: Qwen 2.5 VL 72 B Instruct costs $0.800 per million input tokens and $1.00 per million output tokens. That is a 3:1 blended rate of $0.850 per million tokens, ranking it #439 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.800 |
| Output, per 1M tokens | $1.00 |
| Output รท input multiple | 1.25× |
| 3:1 blended, per 1M tokens | $0.850 |
| Context window | 128,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.800 | $0.250 | $1.05 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $8.00 | $2.50 | $10.50 | ||||
| 100M in / 25M out | $80.00 | $25.00 | $105 |
Other qwen models
| Model | Input | Output |
|---|---|---|
| Qwen 3.7 Flash | $0.030 | $0.130 |
| Qwen 3.8 27 B | $0.039 | $1.25 |
| Qwen 3.5 Flash 02 23 | $0.065 | $0.260 |
| Qwen 3 Coder 30 B A3 B Instruct | $0.070 | $0.280 |
| Qwen 3 32 B | $0.080 | $0.280 |
Cheaper alternatives
Next cheaper option: Moondream 3 Preview at $0.300 per 1M input tokens. Next step up: Doubao Seed 2.1 Turbo 260628 at $0.431 per 1M input tokens.