Qwen pricing — 2026
Qwen API starts at $0.0325/1M input tokens. Prices effective since April 25, 2026.
| Model | Input $/1M | Output $/1M | Cached | Notes |
|---|---|---|---|---|
| Qwen3.5-27B | $0.195 | $1.56 | — | |
| Qwen3.5 397B A17B | $0.390 | $2.34 | $0.195 | |
| Qwen3 VL 32B Instruct | $0.104 | $0.416 | — | |
| Qwen3 VL 8B Thinking | $0.117 | $1.36 | — | |
| Qwen3 VL 8B Instruct | $0.0800 | $0.500 | — | |
| Qwen3 VL 30B A3B Thinking | $0.130 | $1.56 | — | |
| Qwen3 VL 30B A3B Instruct | $0.130 | $0.520 | — | |
| Qwen3 VL 235B A22B Thinking | $0.260 | $2.60 | — | |
| Qwen3 VL 235B A22B Instruct | $0.200 | $0.880 | $0.110 | |
| Qwen3 Max | $0.780 | $3.90 | $0.156 | |
| Qwen3 Coder Plus | $0.650 | $3.25 | $0.130 | |
| Qwen3.5-9B | $0.100 | $0.150 | — | |
| Qwen3.5-122B-A10B | $0.260 | $2.08 | — | |
| Qwen3 30B A3B | $0.0800 | $0.280 | — | |
| Qwen3 8B | $0.0500 | $0.400 | $0.0500 | |
| Qwen3 14B | $0.0600 | $0.240 | — | |
| Qwen3 32B | $0.0800 | $0.240 | $0.0400 | |
| Qwen3 235B A22B | $0.455 | $1.82 | — | |
| QwQ 32B | $0.150 | $0.580 | — | |
| Qwen3 Max Thinking | $0.780 | $3.90 | — | |
| Qwen3.6 Plus | $0.325 | $1.95 | — | |
| Qwen3 Coder Next | $0.140 | $0.800 | $0.0900 | |
| Qwen3.5-35B-A3B | $0.163 | $1.30 | — | |
| Qwen3.5 Plus 2026-02-15 | $0.260 | $1.56 | — | |
| Qwen3.5-Flash | $0.0650 | $0.260 | — | |
| Qwen3 Coder Flash | $0.195 | $0.975 | $0.0390 | |
| Qwen3 Next 80B A3B Thinking | $0.0975 | $0.780 | — | |
| Qwen3 Next 80B A3B Instruct | $0.0900 | $1.10 | — | |
| Qwen Plus 0728 (thinking) | $0.260 | $0.780 | — | |
| Qwen Plus 0728 | $0.260 | $0.780 | — | |
| Qwen3 30B A3B Thinking 2507 | $0.0800 | $0.400 | $0.0800 | |
| Qwen3 Coder 30B A3B Instruct | $0.0700 | $0.270 | — | |
| Qwen3 30B A3B Instruct 2507 | $0.0900 | $0.300 | — | |
| Qwen3 235B A22B Thinking 2507 | $0.149 | $1.50 | — | |
| Qwen3 Coder 480B A35B | $0.220 | $1.00 | $0.0220 | |
| Qwen3 235B A22B Instruct 2507 | $0.0710 | $0.100 | — | |
| Qwen VL Plus | $0.137 | $0.409 | $0.0273 | |
| Qwen VL Max | $0.520 | $2.08 | — | |
| Qwen-Turbo | $0.0325 | $0.130 | $0.0065 | |
| Qwen2.5 VL 72B Instruct | $0.250 | $0.750 | — | |
| Qwen-Plus | $0.260 | $0.780 | $0.0520 | |
| Qwen-Max | $1.04 | $4.16 | $0.208 | |
| Qwen2.5 Coder 32B Instruct | $0.660 | $1.00 | — | |
| Qwen2.5 7B Instruct | $0.0400 | $0.100 | — | |
| Qwen2.5 72B Instruct | $0.120 | $0.390 | — |
Prices effective since April 25, 2026. Verified April 25, 2026. Confirm at source before billing.
Cost calculator
Estimated monthly cost · 70% input / 30% output split
+39 more models not shown
Price history
Input price per 1M tokens — tracked from Apr 25, 2026 · chart fills in as prices change
Prices scraped daily from official provider documentation. Chart shows input token pricing.
Related pages
About Qwen API pricing
Qwen API pricing is set by Alibaba Cloud and billed per million tokens processed. Input tokens (your prompt) and output tokens (the response) are priced separately. Cached input pricing applies when the same context is reused across requests, offering significant savings for repeated prompts.
Prices on this page are sourced from official Alibaba Cloud documentation and updated when Qwen announces pricing changes. Check the official Qwen pricing page for the most current rates.
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries — every Monday. Free.