Qwen 3 VL 235 B A22 B Instruct pricing
Source: openrouter · updated 2026-10-28
Short answer: Qwen 3 VL 235 B A22 B Instruct costs $0.210 per million input tokens and $1.90 per million output tokens. That is a 3:1 blended rate of $0.632 per million tokens, ranking it #261 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.210 |
| Output, per 1M tokens | $1.90 |
| Output รท input multiple | 9.05× |
| 3:1 blended, per 1M tokens | $0.632 |
| Context window | 262,144 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.210 | $0.475 | $0.685 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $2.10 | $4.75 | $6.85 | ||||
| 100M in / 25M out | $21.00 | $47.50 | $68.50 |
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 |
Compare against
- Qwen 3 VL 235 B A22 B Instruct vs DeepSeek V4 Flash Vision Exp
- Qwen 3 VL 235 B A22 B Instruct vs Nvidia Nemotron 3.5 Super VL 120 B A12 B
Cheaper alternatives
Next cheaper option: Qwen 3.5 122 B A10 B Thinking at $0.250 per 1M input tokens. Next step up: Llama 3 70 B at $0.590 per 1M input tokens.