Pricing
Pay as you go
Prepaid credit top-ups through Stripe. Minimum charge: $5.
No unlimited plan
Usage is metered by model input and output tokens.
Trying models
To try Qwen models with a free tier, visit qwencloud.com.
Model pricing
Current public model prices and context limits update automatically when this service catalog changes.
Available models
qwen3.6-flash
qwen3.6-plus
qwen3.5-plus
qwen3.7-max
qwen3.6-27b
qwen3.6-flash
Max context
256000
Input / 1M tokens
$0.20
Explicit cache creation / 1M tokens
$0.25
Explicit cache read / 1M tokens
$0.020
Implicit cache read / 1M tokens
$0.04
Output / 1M tokens
$1.25
Max context
1000000
Input / 1M tokens
$0.9
Explicit cache creation / 1M tokens
$1.20
Explicit cache read / 1M tokens
$0.08
Implicit cache read / 1M tokens
$0.18
Output / 1M tokens
$4
qwen3.6-plus
Max context
256000
Input / 1M tokens
$0.375
Explicit cache creation / 1M tokens
$0.5
Explicit cache read / 1M tokens
$0.04
Implicit cache read / 1M tokens
$0.075
Output / 1M tokens
$2.5
Max context
1000000
Input / 1M tokens
$1.6
Explicit cache creation / 1M tokens
$1.9
Explicit cache read / 1M tokens
$0.175
Implicit cache read / 1M tokens
$0.32
Output / 1M tokens
$6
qwen3.5-plus
Max context
128000
Input / 1M tokens
$0.3
Explicit cache creation / 1M tokens
$0.3
Explicit cache read / 1M tokens
$0.02
Implicit cache read / 1M tokens
$0.06
Output / 1M tokens
$1.2
Max context
256000
Input / 1M tokens
$0.4
Explicit cache creation / 1M tokens
$0.45
Explicit cache read / 1M tokens
$0.04
Implicit cache read / 1M tokens
$0.08
Output / 1M tokens
$2.0
Max context
1000000
Input / 1M tokens
$0.5
Explicit cache creation / 1M tokens
$0.625
Explicit cache read / 1M tokens
$0.05
Implicit cache read / 1M tokens
$0.10
Output / 1M tokens
$3
qwen3.7-max
Max context
1000000
Input / 1M tokens
$0.95
Explicit cache creation / 1M tokens
$1.2
Explicit cache read / 1M tokens
$0.1
Implicit cache read / 1M tokens
$0.19
Output / 1M tokens
$3.0
qwen3.6-27b
Max context
256000
Input / 1M tokens
$0.5
Output / 1M tokens
$3.0