qwen API Pricing
All 67 qwen models by input price. Refreshed hourly.
| Model | Input /1M | Output /1M | Blended | Context | Intelligence | CPS | |
|---|---|---|---|---|---|---|---|
| Qwen: Qwen3.8 Max | $2.00 | $6.00 | $3.00 | 1.0M | 45 | A | Details → |
| Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | $3.00 | 1.0M | 40 | A | Details → |
| Qwen: Qwen3.8 27B | $0.20 | $2.50 | $0.78 | 1.0M | 34 | A | Details → |
| Qwen: Qwen3 Max Thinking | $0.78 | $3.90 | $1.56 | 262K | 16 | B | Details → |
| Qwen: Qwen3.7 Max | $1.48 | $4.42 | $2.21 | 1.0M | 30 | B | Details → |
| Qwen: Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | $0.26 | 262K | 8 | B | Details → |
| Qwen: Qwen3 Next 80B A3B Instruct | $0.09 | $1.10 | $0.34 | 262K | 10 | B | Details → |
| Qwen: Qwen3.7 Plus | $0.32 | $1.28 | $0.56 | 1.0M | 25 | B | Details → |
| Qwen: Qwen3 VL 32B Instruct | $0.10 | $0.42 | $0.18 | 131K | 8 | B | Details → |
| Qwen: Qwen3 VL 235B A22B Instruct | $0.21 | $1.90 | $0.63 | 262K | 10 | B | Details → |
| Qwen: Qwen3.6 Plus | $0.33 | $1.95 | $0.73 | 1.0M | 27 | B | Details → |
| Qwen: Qwen3 Max | $0.78 | $3.90 | $1.56 | 262K | 13 | B | Details → |
| Qwen: Qwen3.6 27B | $0.25 | $2.00 | $0.69 | 262K | 21 | B | Details → |
| Qwen: QwQ 32B | $0.15 | $0.58 | $0.26 | 131K | 10 | B | Details → |
| Qwen: Qwen3.6 35B A3B | $0.10 | $0.95 | $0.31 | 262K | 18 | B | Details → |
| Qwen: Qwen3.5-122B-A10B | $0.40 | $3.20 | $1.10 | 262K | 16 | B | Details → |
| Qwen: Qwen3.5 397B A17B | $0.50 | $3.60 | $1.27 | 262K | 18 | B | Details → |
| Qwen: Qwen3 Coder 30B A3B Instruct | $0.07 | $0.28 | $0.12 | 262K | 10 | B | Details → |
| Qwen: Qwen-Turbo | $0.03 | $0.13 | $0.06 | 131K | 6 | B | Details → |
| Qwen: Qwen3.5-27B | $0.27 | $2.16 | $0.74 | 262K | 23 | B | Details → |
| Qwen: Qwen3 VL 8B Instruct | $0.25 | $0.75 | $0.38 | 262K | 7 | B | Details → |
| Qwen: Qwen3 Coder Next | $0.12 | $0.80 | $0.29 | 262K | 9 | B | Details → |
| Qwen: Qwen3.5-35B-A3B | $0.14 | $1.00 | $0.35 | 262K | 19 | B | Details → |
| Qwen: Qwen3.5-9B | $0.17 | $0.25 | $0.19 | 262K | 11 | B | Details → |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1.00 | $0.74 | 33K | — | — | Details → |
| Qwen: Qwen3 8B | $0.12 | $0.46 | $0.20 | 131K | — | — | Details → |
| Qwen: Qwen3 14B | $0.12 | $0.24 | $0.15 | 41K | — | — | Details → |
| Qwen: Qwen Plus 0728 | $0.26 | $0.78 | $0.39 | 1.0M | — | — | Details → |
| Qwen: Qwen3.8 Max Prime | $4.00 | $12.00 | $6.00 | 1.0M | — | — | Details → |
| Qwen: Qwen2.5 7B Instruct | $0.10 | $0.20 | $0.13 | 33K | — | — | Details → |
| Qwen: Qwen3.8 2.4T A95B (batch) | $2.00 | $6.00 | $3.00 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Coder Plus | $0.65 | $3.25 | $1.30 | 1.0M | — | — | Details → |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 | $0.23 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Next 80B A3B Instruct (free) | Free | Free | $0.00 | 262K | — | — | Details → |
| Qwen: Qwen-Max | $1.04 | $4.16 | $1.82 | 33K | — | — | Details → |
| Qwen: Qwen3 235B A22B | $0.46 | $1.82 | $0.80 | 131K | — | — | Details → |
| Qwen2.5 72B Instruct | $0.36 | $0.40 | $0.37 | 33K | — | — | Details → |
| Qwen: Qwen3 VL 30B A3B Thinking | $0.29 | $1.00 | $0.47 | 262K | — | — | Details → |
| Qwen: Qwen3.8 27B (free) | Free | Free | $0.00 | 262K | — | — | Details → |
| Qwen: Qwen3.8 Max (0902) | $2.00 | $6.00 | $3.00 | 1.0M | — | — | Details → |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 | $0.23 | 1.0M | — | — | Details → |
| Qwen: Qwen2.5 VL 32B Instruct | $0.20 | $0.60 | $0.30 | 128K | — | — | Details → |
| Qwen: Qwen3 VL 8B Thinking | $0.18 | $2.10 | $0.66 | 131K | — | — | Details → |
| Qwen: Qwen3.7 Flash | $0.03 | $0.13 | $0.06 | 1.0M | — | — | Details → |
| Qwen: Qwen VL Plus | $0.14 | $0.41 | $0.20 | 131K | — | — | Details → |
| Qwen: Qwen VL Max | $0.52 | $2.08 | $0.91 | 131K | — | — | Details → |
| Qwen: Qwen Plus 0728 (thinking) | $0.26 | $0.78 | $0.39 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Coder 480B A35B (free) | Free | Free | $0.00 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Coder 480B A35B | $0.30 | $1.00 | $0.47 | 262K | — | — | Details → |
| Qwen: Qwen3.5-9B (batch) | $0.17 | $0.25 | $0.19 | 262K | — | — | Details → |
| Qwen: Qwen3.6 Max Preview | $1.03 | $6.16 | $2.31 | 262K | — | — | Details → |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.09 | $0.55 | $0.20 | 262K | — | — | Details → |
| Qwen: Qwen3 30B A3B | $0.12 | $0.50 | $0.21 | 41K | — | — | Details → |
| Qwen: Qwen3.7 Plus (batch) | $0.23 | $0.92 | $0.40 | 262K | — | — | Details → |
| Qwen: Qwen3 VL 235B A22B Thinking | $0.40 | $4.00 | $1.30 | 131K | — | — | Details → |
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.09 | $0.30 | $0.14 | 262K | — | — | Details → |
| Qwen: Qwen3.5 Plus 2026-04-20 | $0.30 | $1.80 | $0.68 | 1.0M | — | — | Details → |
| Qwen: Qwen3.6 Flash | $0.19 | $1.13 | $0.42 | 1.0M | — | — | Details → |
| Qwen: Qwen3 235B A22B Thinking 2507 | $0.45 | $3.50 | $1.21 | 128K | — | — | Details → |
| Qwen: Qwen3.5-Flash | $0.07 | $0.26 | $0.11 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Coder Flash | $0.20 | $0.97 | $0.39 | 1.0M | — | — | Details → |
| Qwen: Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | $0.58 | 1.0M | — | — | Details → |
| Qwen: Qwen3 Next 80B A3B Thinking | $0.15 | $1.20 | $0.41 | 262K | — | — | Details → |
| Qwen: Qwen3 30B A3B Thinking 2507 | $0.20 | $2.40 | $0.75 | 82K | — | — | Details → |
| Qwen: Qwen-Plus | $0.26 | $0.78 | $0.39 | 1.0M | — | — | Details → |
| Qwen: Qwen2.5 VL 72B Instruct | $0.80 | $1.00 | $0.85 | 128K | — | — | Details → |
| Qwen: Qwen3 32B | $0.08 | $0.28 | $0.13 | 131K | — | — | Details → |
FAQ
What is the cheapest qwen model?
By input price, Qwen: Qwen3.8 Max is lowest ($2.00/1M tokens). See the full table above.
How is qwen priced?
Usage-based: input and output priced separately per 1M tokens, with cache read/write discounts on some models. The Blended column estimates a typical 3:1 request cost.