Qwen API pricing
As of October 21, 2026, the Qwen API prices run from $0.13 to $12.00 per million output tokens across 42 models, as listed on OpenRouter. Qwen3.7 Flash is the cheapest paid model at $0.03 input and $0.13 output per million tokens, and Qwen3.8 Max Prime the most expensive at $4.00 input and $12.00 output.
Qwen3.8 27B ranks first among Qwen models in our Vibe Coding Index, at 74.2 on 4 benchmarks. 8 of 42 Qwen models have any benchmark score. Cost per solved task is known for 7 of 42 models.
| Model | Input $/Mtok | Output $/Mtok | Context | Evidence | Index | Cost per solved task |
|---|---|---|---|---|---|---|
| Qwen3.8 Max Prime | $4.00 | $12.00 | 1M | Not benchmarked | No run cost | |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | 1M | Not benchmarked | No run cost | |
| Qwen3.8 Max (0902) | $2.00 | $6.00 | 1M | 62.4 | $1.32 | |
| Qwen3.8 Flash | $0.15 | $0.47 | 1M | Not enough data | No run cost | |
| Qwen3.8 27B | $0.425 | $2.55 | 1M | 74.2 | $1.26 | |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 1.05M | Not benchmarked | No run cost | |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | Not benchmarked | No run cost | |
| Qwen3.7 Plus | $0.32 | $1.28 | 1M | 33.2 | No run cost | |
| Qwen3.7 Max | $1.475 | $4.425 | 1M | 54.1 | $4.69 | |
| Qwen3.5 Plus 2026-04-20 | $0.30 | $1.80 | 1M | 39.5 | $1.35 | |
| Qwen3.6 27B | $0.45 | $2.70 | 262K | 36.8 | $1.30 | |
| Qwen3.6 35B A3B | $0.10 | $1.00 | 262K | Not benchmarked | No run cost | |
| Qwen3.6 Flash | $0.1875 | $1.125 | 1M | Not benchmarked | No run cost | |
| Qwen3.6 Plus | $0.325 | $1.95 | 1M | 44.1 | $1.19 | |
| Qwen3.5-9B | $0.10 | $0.15 | 262K | Not benchmarked | No run cost | |
| Qwen3.5-122B-A10B | $0.26 | $2.08 | 262K | Not enough data | No run cost | |
| Qwen3.5-27B | $0.195 | $1.56 | 262K | Not enough data | No run cost | |
| Qwen3.5-35B-A3B | $0.1625 | $1.30 | 262K | Not enough data | No run cost | |
| Qwen3.5-Flash | $0.065 | $0.26 | 1M | 41.1 | $0.40 | |
| Qwen3.5 397B A17B | $0.39 | $2.34 | 262K | Not enough data | No run cost | |
| Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | 1M | Not benchmarked | No run cost | |
| Qwen3 Coder Next | $0.12 | $0.80 | 262K | Not benchmarked | No run cost | |
| Qwen3 VL 8B Instruct | $0.25 | $0.75 | 262K | Not benchmarked | No run cost | |
| Qwen3 VL 30B A3B Instruct | $0.20 | $0.70 | 262K | Not benchmarked | No run cost | |
| Qwen3 VL 30B A3B Thinking | $0.29 | $1.00 | 262K | Not benchmarked | No run cost | |
| Qwen3 VL 235B A22B Instruct | $0.21 | $1.90 | 262K | Not benchmarked | No run cost | |
| Qwen3 Coder Flash | $0.195 | $0.975 | 1M | Not benchmarked | No run cost | |
| Qwen3 Next 80B A3B Instruct | $0.10 | $1.10 | 262K | Not benchmarked | No run cost | |
| Qwen3 Next 80B A3B Thinking | $0.15 | $1.20 | 262K | Not benchmarked | No run cost | |
| Qwen3 Coder 30B A3B Instruct | $0.11 | $0.44 | 262K | Not benchmarked | No run cost | |
| Qwen3 30B A3B Instruct 2507 | $0.09 | $0.30 | 262K | Not benchmarked | No run cost | |
| Qwen3 235B A22B Thinking 2507 | $0.45 | $3.50 | 128K | Not benchmarked | No run cost | |
| Qwen3 Coder 480B A35B | $0.30 | $1.50 | 262K | Not enough data | No run cost | |
| Qwen3 235B A22B Instruct 2507 | $0.15 | $0.75 | 262K | Not benchmarked | No run cost | |
| Qwen3 14B | $0.11 | $0.23 | 41K | Not benchmarked | No run cost | |
| Qwen3 30B A3B | $0.12 | $0.50 | 41K | Not benchmarked | No run cost | |
| Qwen3 32B | $0.14 | $0.40 | 131K | Not benchmarked | No run cost | |
| Qwen-Plus | $0.26 | $0.78 | 1M | Not benchmarked | No run cost | |
| Qwen2.5 VL 72B Instruct | $0.80 | $1.00 | 128K | Not benchmarked | No run cost | |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1.00 | 33K | Not benchmarked | No run cost | |
| Qwen2.5 7B Instruct | $0.10 | $0.20 | 33K | Not benchmarked | No run cost | |
| Qwen2.5 72B Instruct | $0.36 | $0.40 | 33K | Not benchmarked | No run cost |
Price changes
No change in a maker's own API price recorded yet. We read prices daily from OpenRouter (since October 15, 2026) and list a change only when the maker's own price moves between two of our snapshots.