Qwen 3 VL 235 B A22 B Thinking pricing
Source: litellm · updated 2026-10-28
Short answer: Qwen 3 VL 235 B A22 B Thinking costs $0.400 per million input tokens and $4.00 per million output tokens. That is a 3:1 blended rate of $1.30 per million tokens, ranking it #354 of 713 tracked models by input price.
Input / 1M
$0.400
Output / 1M
$4.00
Output ÷ input
10.00×
Context window
131,072
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.400 |
| Output, per 1M tokens | $4.00 |
| Output ÷ input multiple | 10.00× |
| 3:1 blended, per 1M tokens | $1.30 |
| Context window | 131,072 tokens |
| Vendor | dashscope |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.400 | $1.00 | $1.40 |
| 10M in / 2.5M out | $4.00 | $10.00 | $14.00 |
| 100M in / 25M out | $40.00 | $100 | $140 |
Other dashscope models
| Model | Input | Output |
|---|---|---|
| Qwen Turbo | $0.050 | $0.200 |
| Qwen 3 VL 32 B Instruct | $0.160 | $0.640 |
| Qwen 3 VL 32 B Thinking | $0.160 | $2.87 |
| Qwen Coder | $0.300 | $1.50 |
| Qwq Plus | $0.800 | $2.40 |
Compare against
Cheaper alternatives
Next cheaper option: Qwen 3.5 397 B A17 B at $0.500 per 1M input tokens. Next step up: Kimi K2.6 at $0.650 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.