Qwen API pricing
Every Qwen model from Alibaba we track, with input, cached input and output cost in USD per 1M tokens. Alibaba ships the widest range of sizes of any provider here, from sub-cent flash models to flagship Max tiers.
53 models · updated 2026-09-25 · prices in USD per 1,000,000 tokens
53
Models tracked
$0.030
Cheapest input — Qwen3.7 Flash
$4.00
Priciest input — Qwen3.8 Max Prime
1M
Largest context — Qwen3.8 2.4T A95B
Listed in the order Alibaba (Qwen) publishes them.
| Qwen3.8 Max PrimeProvider API | $4.00 | $0.500 | $12.00 | 1M |
|---|---|---|---|---|
| Qwen3.8 Omni FlashProvider API | $0.150 | $0.016 | $0.470 | 1M |
| Qwen3.8 Max (0902)Provider API | $2.00 | $0.250 | $6.00 | 1M |
| Qwen3.8 FlashProvider API | $0.150 | $0.016 | $0.470 | 1M |
| Qwen3.8 27BProvider API | $0.420 | $0.085 | $3.00 | 1M |
| Qwen3.8 2.4T A95BProvider API | $2.00 | $0.250 | $6.00 | 1M |
| Qwen3.7 FlashProvider API | $0.030 | $0.006 | $0.130 | 1M |
| Qwen3.7 PlusProvider API | $0.320 | $0.064 | $1.28 | 1M |
| Qwen3.7 MaxProvider API | $1.48 | $0.295 | $4.42 | 1M |
| Qwen3.5 Plus 2026-04-20Provider API | $0.300 | — | $1.80 | 1M |
| Qwen3.6 FlashProvider API | $0.188 | — | $1.13 | 1M |
| Qwen3.6 35B A3BProvider API | $0.150 | $0.050 | $1.00 | 262K |
| Qwen3.6 Max PreviewProvider API | $1.03 | — | $6.16 | 262K |
| Qwen3.6 27BProvider API | $0.320 | $0.150 | $2.70 | 262K |
| Qwen3.6 PlusProvider API | $0.325 | — | $1.95 | 1M |
| Qwen3.5-9BProvider API | $0.100 | — | $0.150 | 262K |
| Qwen3.5-35B-A3BProvider API | $0.313 | $0.156 | $1.25 | 262K |
| Qwen3.5-27BProvider API | $0.195 | — | $1.56 | 262K |
| Qwen3.5-122B-A10BProvider API | $0.260 | — | $2.08 | 262K |
| Qwen3.5-FlashProvider API | $0.065 | — | $0.260 | 1M |
| Qwen3.5 Plus 2026-02-15Provider API | $0.260 | — | $1.56 | 1M |
| Qwen3.5 397B A17BProvider API | $0.550 | $0.225 | $3.50 | 262K |
| Qwen3 Max ThinkingProvider API | $0.780 | — | $3.90 | 262K |
| Qwen3 Coder NextProvider API | $0.120 | $0.070 | $0.800 | 262K |
| Qwen3 VL 32B InstructProvider API | $0.104 | — | $0.416 | 131K |
| Qwen3 VL 8B ThinkingProvider API | $0.180 | — | $2.10 | 131K |
| Qwen3 VL 8B InstructProvider API | $0.117 | — | $0.455 | 262K |
| Qwen3 VL 30B A3B ThinkingProvider API | $0.200 | — | $2.40 | 262K |
| Qwen3 VL 30B A3B InstructProvider API | $0.150 | — | $0.600 | 262K |
| Qwen3 VL 235B A22B ThinkingProvider API | $0.400 | — | $4.00 | 131K |
| Qwen3 VL 235B A22B InstructProvider API | $0.210 | $0.100 | $1.90 | 262K |
| Qwen3 MaxProvider API | $0.780 | $0.156 | $3.90 | 262K |
| Qwen3 Coder PlusProvider API | $0.650 | $0.130 | $3.25 | 1M |
| Qwen3 Coder FlashProvider API | $0.195 | $0.039 | $0.975 | 1M |
| Qwen3 Next 80B A3B ThinkingProvider API | $0.150 | — | $1.20 | 262K |
| Qwen3 Next 80B A3B InstructProvider API | $0.100 | $0.070 | $1.10 | 262K |
| Qwen Plus 0728Provider API | $0.260 | — | $0.780 | 1M |
| Qwen3 30B A3B Thinking 2507Provider API | $0.200 | — | $2.40 | 82K |
| Qwen3 Coder 30B A3B InstructProvider API | $0.070 | — | $0.280 | 262K |
| Qwen3 30B A3B Instruct 2507Provider API | $0.100 | — | $0.300 | 262K |
| Qwen3 235B A22B Thinking 2507Provider API | $0.230 | — | $2.30 | 131K |
| Qwen3 Coder 480B A35BProvider API | $0.300 | $0.100 | $1.00 | 262K |
| Qwen3 235B A22B Instruct 2507Provider API | $0.087 | $0.018 | $0.350 | 262K |
| Qwen3 30B A3BProvider API | $0.120 | — | $0.500 | 131K |
| Qwen3 8BProvider API | $0.117 | — | $0.455 | 131K |
| Qwen3 14BProvider API | $0.120 | — | $0.240 | 131K |
| Qwen3 32BProvider API | $0.080 | — | $0.280 | 131K |
| Qwen3 235B A22BProvider API | $0.455 | — | $1.82 | 131K |
| Qwen2.5 VL 72B InstructProvider API | $0.800 | $0.400 | $1.00 | 128K |
| Qwen-PlusProvider API | $0.260 | $0.052 | $0.780 | 1M |
| Qwen2.5 Coder 32B InstructProvider API | $0.660 | — | $1.00 | 33K |
| Qwen2.5 7B InstructProvider API | $0.100 | — | $0.200 | 33K |
| Qwen2.5 72B InstructProvider API | $0.360 | — | $0.400 | 33K |
Qwen pricing questions
- How much does the Qwen API cost?
- Qwen pricing runs from $0.030 to $4.00 per 1M input tokens depending on the model. Qwen3.8 Max Prime costs $4.00 per 1M input and $12.00 per 1M output tokens.
- What is the cheapest Qwen model?
- Qwen3.7 Flash is the cheapest Qwen model we track, at $0.030 per 1M input tokens and $0.130 per 1M output tokens.
- Does Qwen charge less for cached tokens?
- Yes. Cached input is billed at a lower rate than fresh input — for Qwen3.8 Max Prime it is $0.500 per 1M versus $4.00, about 88% cheaper. Caching applies to repeated prompt prefixes.
- How often is this Qwen pricing updated?
- Every day. Prices are read directly from the published pricing page, normalized to USD per 1,000,000 tokens, and only recorded when a number actually changes — so the history shows real price movements rather than daily noise.