Alexey Shurov.
Free tool

Qwen API pricing, every Alibaba model per million tokens

On 25 September 2026, Alibaba models on this list cost from $0.03 per million input tokens (Qwen3.7 Flash) to $4.00 (Qwen3.8 Max Prime), and from $0.13 per million output tokens (Qwen3.7 Flash) to $12.00 (Qwen3.8 Max Prime).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens
ModelInputOutputCached inputBatch in / outContextYour monthListed
Qwen3.8 Max Prime$4.00$12.00$0.501M$420.002026-09-23
Qwen3.8 Omni Flash$0.15$0.47$0.0161M$16.052026-09-21
Qwen3.8 Max (0902)$2.00$6.00$0.251M$210.002026-09-03
Qwen3.8 Flash$0.15$0.47$0.0161M$16.052026-08-26
Qwen3.8 27B
free tier on OpenRouter
$0.42$3.00$0.0851M$70.202026-08-14
Qwen3.8 2.4T A95B$2.00$6.00$0.251.04858M$210.002026-08-12
Qwen3.7 Flash$0.03$0.13$0.0061M$3.752026-07-27
Qwen3.7 Plus$0.32$1.28$0.0641M$38.402026-06-03
Qwen3.7 Max$1.48$4.42$0.2951M$154.882026-05-21
Qwen3.5 Plus 2026-04-20$0.30$1.801M$45.002026-04-27
Qwen3.6 Flash$0.1875$1.121M$28.122026-04-27
Qwen3.6 35B A3B$0.15$1.00$0.05262K$24.002026-04-27
Qwen3.6 Max Preview
retiring 2026-10-09
$1.03$6.16262K$154.052026-04-27
Qwen3.6 27B$0.32$2.70$0.15262K$59.702026-04-27
Qwen3.6 Plus$0.325$1.951M$48.752026-04-02
Qwen3.5-9B$0.10$0.15262K$8.252026-03-10
Qwen3.5-35B-A3B$0.3125$1.25$0.1562262K$37.502026-02-25
Qwen3.5-27B$0.195$1.56262K$35.102026-02-25
Qwen3.5-122B-A10B$0.26$2.08262K$46.802026-02-25
Qwen3.5-Flash$0.065$0.261M$7.802026-02-25
Qwen3.5 Plus 2026-02-15$0.26$1.561M$39.002026-02-16
Qwen3.5 397B A17B$0.55$3.50$0.225262K$85.502026-02-16
Qwen3 Max Thinking
retiring 2026-10-09
$0.78$3.90262K$105.302026-02-09
Qwen3 Coder Next$0.12$0.80$0.07262K$19.202026-02-04
Qwen3 VL 32B Instruct
retiring 2026-10-09
$0.104$0.416131K$12.482025-10-23
Qwen3 VL 8B Thinking
retiring 2026-10-09
$0.18$2.10131K$42.302025-10-14
Qwen3 VL 8B Instruct
retiring 2026-10-09
$0.117$0.455262K$13.852025-10-14
Qwen3 VL 30B A3B Thinking
retiring 2026-10-09
$0.20$2.40262K$48.002025-10-06
Qwen3 VL 30B A3B Instruct$0.15$0.60262K$18.002025-10-06
Qwen3 VL 235B A22B Thinking
retiring 2026-10-09
$0.40$4.00131K$84.002025-09-23
Qwen3 VL 235B A22B Instruct$0.21$1.90$0.10262K$41.102025-09-23
Qwen3 Max
retiring 2026-10-09
$0.78$3.90$0.156262K$105.302025-09-23
Qwen3 Coder Plus
retiring 2026-10-09
$0.65$3.25$0.131M$87.752025-09-23
Qwen3 Coder Flash$0.195$0.975$0.0391M$26.322025-09-17
Qwen3 Next 80B A3B Thinking$0.15$1.20262K$27.002025-09-11
Qwen3 Next 80B A3B Instruct$0.10$1.10$0.07262K$22.502025-09-11
Qwen Plus 0728
retiring 2026-10-09
$0.26$0.781M$27.302025-09-08
Qwen3 30B A3B Thinking 2507
retiring 2026-10-09
$0.20$2.4082K$48.002025-08-28
Qwen3 Coder 30B A3B Instruct$0.07$0.28262K$8.402025-07-31
Qwen3 30B A3B Instruct 2507$0.10$0.30262K$10.502025-07-29
Qwen3 235B A22B Thinking 2507
retiring 2026-10-09
$0.23$2.30131K$48.302025-07-25
Qwen3 Coder 480B A35B$0.30$1.00$0.10262K$33.002025-07-23
Qwen3 235B A22B Instruct 2507$0.0875$0.35$0.0175262K$10.502025-07-21
Qwen3 30B A3B$0.12$0.50131K$14.702025-04-28
Qwen3 8B
retiring 2026-10-09
$0.117$0.455131K$13.852025-04-28
Qwen3 14B$0.12$0.24131K$10.802025-04-28
Qwen3 32B$0.08$0.28131K$9.002025-04-28
Qwen3 235B A22B
retiring 2026-10-09
$0.455$1.82131K$54.602025-04-28
Qwen2.5 VL 72B Instruct$0.80$1.00$0.40128K$63.002025-02-01
Qwen-Plus$0.26$0.78$0.0521M$27.302025-02-01
Qwen2.5 Coder 32B Instruct$0.66$1.0033K$54.602024-11-11
Qwen2.5 7B Instruct$0.10$0.2033K$9.002024-10-16
Qwen2.5 72B Instruct$0.36$0.4033K$27.602024-09-19

Compare Alibaba with every other provider

Common questions

How much does the Qwen API cost?

On 25 September 2026, Alibaba models on this list cost from $0.03 per million input tokens (Qwen3.7 Flash) to $4.00 (Qwen3.8 Max Prime), and from $0.13 per million output tokens (Qwen3.7 Flash) to $12.00 (Qwen3.8 Max Prime).

What is the cheapest Qwen model?

For a typical mix of three input tokens to every output token, the cheapest is Qwen3.7 Flash at $0.03 per million input tokens and $0.13 per million output tokens.

What is the newest Qwen model on the list?

Qwen3.8 Max Prime, listed on 23 September 2026, at $4.00 per million input tokens and $12.00 per million output tokens.

Which Qwen model has the largest context window?

Qwen3.8 2.4T A95B, with 1.04858M tokens of context.

Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.

shurco.aiGuidesFree toolsSolutionsInsightsRSSllms.txt