Qwen Cloud API pricing

Cloud19 language models

As of Oct 14, 2026, Qwen Cloud lists 19 language models through its API. Its cheapest language model is Qwen Turbo at $0.05 input / $0.20 output per million tokens.

Language models (19)

Prices per million tokens.

Model	Input	Output	Cached input	Context
DeepSeek V4 Flash qwencloud/deepseek-v4-flash	$0.20	$0.40	$0.04	1M
DeepSeek V4 Flash 0731 qwencloud/deepseek-v4-flash-0731	$0.20	$0.40	$0.04	1M
DeepSeek V4 Pro qwencloud/deepseek-v4-pro	$2.40	$4.80	$0.20	1M
GLM 5.1 qwencloud/glm-5.1	$1.40	$4.40	$0.26	203K
GLM 5.2 qwencloud/glm-5.2	$1.40	$4.40	$0.28	1.05M
Kimi K2.7 Code qwencloud/kimi-k2.7-code	$0.95	$4.00	$0.19	229K
Qwen Coder qwencloud/qwen-coder	$0.30	$1.50	—	1M
Qwen Max qwencloud/qwen-max	$1.60	$6.40	—	31K
Qwen Plus qwencloud/qwen-plus	$0.40	$1.20	—	129K
Qwen Turbo qwencloud/qwen-turbo	$0.05	$0.20	—	129K
Qwen3 Next 80B A3B Instruct qwencloud/qwen3-next-80b-a3b-instruct	$0.15	$1.20	—	262K
Qwen3 Next 80B A3B Thinking qwencloud/qwen3-next-80b-a3b-thinking	$0.15	$1.20	—	262K
Qwen3 VL 32B Instruct qwencloud/qwen3-vl-32b-instruct	$0.16	$0.64	—	131K
Qwen3 VL 32B Thinking qwencloud/qwen3-vl-32b-thinking	$0.16	$2.87	—	131K
Qwen3 VL 235B A22B Instruct qwencloud/qwen3-vl-235b-a22b-instruct	$0.40	$1.60	—	131K
Qwen3 VL 235B A22B Thinking qwencloud/qwen3-vl-235b-a22b-thinking	$0.40	$4.00	—	131K
Qwen3.7 Max qwencloud/qwen3.7-max	$2.50	$7.50	$0.50	992K
Qwen3.8 Max qwencloud/qwen3.8-max	$2.00	$6.00	$0.25	992K
QwQ Plus qwencloud/qwq-plus	$0.80	$2.40	—	98K

DeepSeek V4 Flash
qwencloud/deepseek-v4-flash
Input
$0.20
Output
$0.40
Context
1M
DeepSeek V4 Flash 0731
qwencloud/deepseek-v4-flash-0731
Input
$0.20
Output
$0.40
Context
1M
DeepSeek V4 Pro
qwencloud/deepseek-v4-pro
Input
$2.40
Output
$4.80
Context
1M
GLM 5.1
qwencloud/glm-5.1
Input
$1.40
Output
$4.40
Context
203K
GLM 5.2
qwencloud/glm-5.2
Input
$1.40
Output
$4.40
Context
1.05M
Kimi K2.7 Code
qwencloud/kimi-k2.7-code
Input
$0.95
Output
$4.00
Context
229K
Qwen Coder
qwencloud/qwen-coder
Input
$0.30
Output
$1.50
Context
1M
Qwen Max
qwencloud/qwen-max
Input
$1.60
Output
$6.40
Context
31K
Qwen Plus
qwencloud/qwen-plus
Input
$0.40
Output
$1.20
Context
129K
Qwen Turbo
qwencloud/qwen-turbo
Input
$0.05
Output
$0.20
Context
129K
Qwen3 Next 80B A3B Instruct
qwencloud/qwen3-next-80b-a3b-instruct
Input
$0.15
Output
$1.20
Context
262K
Qwen3 Next 80B A3B Thinking
qwencloud/qwen3-next-80b-a3b-thinking
Input
$0.15
Output
$1.20
Context
262K
Qwen3 VL 32B Instruct
qwencloud/qwen3-vl-32b-instruct
Input
$0.16
Output
$0.64
Context
131K
Qwen3 VL 32B Thinking
qwencloud/qwen3-vl-32b-thinking
Input
$0.16
Output
$2.87
Context
131K
Qwen3 VL 235B A22B Instruct
qwencloud/qwen3-vl-235b-a22b-instruct
Input
$0.40
Output
$1.60
Context
131K
Qwen3 VL 235B A22B Thinking
qwencloud/qwen3-vl-235b-a22b-thinking
Input
$0.40
Output
$4.00
Context
131K
Qwen3.7 Max
qwencloud/qwen3.7-max
Input
$2.50
Output
$7.50
Context
992K
Qwen3.8 Max
qwencloud/qwen3.8-max
Input
$2.00
Output
$6.00
Context
992K
QwQ Plus
qwencloud/qwq-plus
Input
$0.80
Output
$2.40
Context
98K

Prices in USD from LiteLLM and models.dev, checked daily; confirm on Qwen Cloud's pricing page before you rely on a number.