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.
49 models · updated 2026-08-11 · prices in USD per 1,000,000 tokens
49
Models tracked
$0.030
Cheapest input — Qwen3.7 Flash
$2.00
Priciest input — Qwen3.8 Max
1M
Largest context — Qwen3.8 Max
Listed in the order Alibaba (Qwen) publishes them.
| Qwen3.8 MaxVia OpenRouter | $2.00 | $0.250 | $6.00 | 1M |
|---|---|---|---|---|
| Qwen3.7 FlashVia OpenRouter | $0.030 | $0.006 | $0.130 | 1M |
| Qwen3.7 PlusVia OpenRouter | $0.320 | $0.064 | $1.28 | 1M |
| Qwen3.7 MaxVia OpenRouter | $1.48 | $0.295 | $4.42 | 1M |
| Qwen3.5 Plus 2026-04-20Via OpenRouter | $0.300 | — | $1.80 | 1M |
| Qwen3.6 FlashVia OpenRouter | $0.188 | — | $1.13 | 1M |
| Qwen3.6 35B A3BVia OpenRouter | $0.150 | $0.050 | $1.00 | 262K |
| Qwen3.6 Max PreviewVia OpenRouter | $1.03 | — | $6.16 | 262K |
| Qwen3.6 27BVia OpenRouter | $0.600 | $0.120 | $3.60 | 262K |
| Qwen3.6 PlusVia OpenRouter | $0.325 | — | $1.95 | 1M |
| Qwen3.5-9BVia OpenRouter | $0.100 | — | $0.150 | 262K |
| Qwen3.5-35B-A3BVia OpenRouter | $0.140 | — | $1.00 | 262K |
| Qwen3.5-27BVia OpenRouter | $0.195 | — | $1.56 | 262K |
| Qwen3.5-122B-A10BVia OpenRouter | $0.290 | — | $2.40 | 262K |
| Qwen3.5-FlashVia OpenRouter | $0.065 | — | $0.260 | 1M |
| Qwen3.5 Plus 2026-02-15Via OpenRouter | $0.260 | — | $1.56 | 1M |
| Qwen3.5 397B A17BVia OpenRouter | $0.500 | $0.300 | $3.60 | 262K |
| Qwen3 Max ThinkingVia OpenRouter | $0.780 | — | $3.90 | 262K |
| Qwen3 Coder NextVia OpenRouter | $0.120 | $0.070 | $0.800 | 262K |
| Qwen3 VL 32B InstructVia OpenRouter | $0.104 | — | $0.416 | 131K |
| Qwen3 VL 8B ThinkingVia OpenRouter | $0.180 | — | $2.10 | 131K |
| Qwen3 VL 8B InstructVia OpenRouter | $0.117 | — | $0.455 | 262K |
| Qwen3 VL 30B A3B ThinkingVia OpenRouter | $0.200 | — | $2.40 | 262K |
| Qwen3 VL 30B A3B InstructVia OpenRouter | $0.150 | — | $0.600 | 262K |
| Qwen3 VL 235B A22B ThinkingVia OpenRouter | $0.400 | — | $4.00 | 131K |
| Qwen3 VL 235B A22B InstructVia OpenRouter | $0.210 | $0.100 | $1.90 | 262K |
| Qwen3 MaxVia OpenRouter | $0.780 | $0.156 | $3.90 | 262K |
| Qwen3 Coder PlusVia OpenRouter | $0.650 | $0.130 | $3.25 | 1M |
| Qwen3 Coder FlashVia OpenRouter | $0.195 | $0.039 | $0.975 | 1M |
| Qwen3 Next 80B A3B ThinkingVia OpenRouter | $0.150 | — | $1.20 | 262K |
| Qwen3 Next 80B A3B InstructVia OpenRouter | $0.090 | — | $1.10 | 262K |
| Qwen Plus 0728Via OpenRouter | $0.260 | — | $0.780 | 1M |
| Qwen Plus 0728 (thinking)Via OpenRouter | $0.400 | — | $1.20 | 1M |
| Qwen3 30B A3B Thinking 2507Via OpenRouter | $0.200 | — | $2.40 | 82K |
| Qwen3 Coder 30B A3B InstructVia OpenRouter | $0.070 | — | $0.280 | 262K |
| Qwen3 30B A3B Instruct 2507Via OpenRouter | $0.048 | — | $0.193 | 262K |
| Qwen3 235B A22B Thinking 2507Via OpenRouter | $0.230 | — | $2.30 | 262K |
| Qwen3 Coder 480B A35BVia OpenRouter | $0.300 | $0.100 | $1.00 | 262K |
| Qwen3 235B A22B Instruct 2507Via OpenRouter | $0.090 | — | $0.550 | 262K |
| Qwen3 30B A3BVia OpenRouter | $0.120 | — | $0.500 | 131K |
| Qwen3 8BVia OpenRouter | $0.117 | — | $0.455 | 131K |
| Qwen3 14BVia OpenRouter | $0.120 | — | $0.240 | 131K |
| Qwen3 32BVia OpenRouter | $0.080 | — | $0.280 | 131K |
| Qwen3 235B A22BVia OpenRouter | $0.455 | — | $1.82 | 131K |
| Qwen2.5 VL 72B InstructVia OpenRouter | $0.250 | — | $0.750 | 128K |
| Qwen-PlusVia OpenRouter | $0.260 | $0.052 | $0.780 | 1M |
| Qwen2.5 Coder 32B InstructVia OpenRouter | $0.660 | — | $1.00 | 33K |
| Qwen2.5 7B InstructVia OpenRouter | $0.100 | — | $0.200 | 33K |
| Qwen2.5 72B InstructVia OpenRouter | $0.360 | — | $0.400 | 33K |
Qwen pricing questions
- How much does the Qwen API cost?
- Qwen pricing runs from $0.030 to $2.00 per 1M input tokens depending on the model. Qwen3.8 Max costs $2.00 per 1M input and $6.00 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 it is $0.250 per 1M versus $2.00, 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.