Qwen 2.5 72 B Instruct pricing
Source: openrouter · updated 2026-10-27
Short answer: Qwen 2.5 72 B Instruct costs $0.360 per million input tokens and $0.400 per million output tokens. That is a 3:1 blended rate of $0.370 per million tokens, ranking it #340 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.360 |
| Output, per 1M tokens | $0.400 |
| Output รท input multiple | 1.11× |
| 3:1 blended, per 1M tokens | $0.370 |
| Context window | 32,768 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.360 | $0.100 | $0.460 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $3.60 | $1.00 | $4.60 | ||||
| 100M in / 25M out | $36.00 | $10.00 | $46.00 |
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 Coder 30 B A3 B Instruct | $0.070 | $0.280 |
| Qwen 3 32 B | $0.080 | $0.280 |
| Qwen 3 Next 80 B A3 B Instruct | $0.090 | $1.10 |
Compare against
Cheaper alternatives
Next cheaper option: Us Gov Nvidia Nemotron Nano 12 B at $0.240 per 1M input tokens. Next step up: Dolphin Mistral 24 B Venice Edition at $0.200 per 1M input tokens.