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.
Free tokens to start
New accounts get 10,000 free tokens to try any model before topping up.
Cost estimator
Estimated cost
$0.00
Context band
-
Approx. requests per $5
-
Estimate uses input and output token prices before cache or tool-call charges.
Model pricing
Prices are in USD per 1M tokens. Some models charge more for longer requests; pick a context size to see its price.
Available models
qwen3.6-flash
qwen3.6-plus
qwen3.5-plus
qwen3.7-max
qwen3.6-27b
qwen3.7-plus
qwen3.8-flash
qwen3.8-27b
qwen3.6-flash
Max context: 256K tokens
Max context
256,000
Input / 1M tokens
$0.21
Explicit cache creation / 1M tokens
$0.27
Explicit cache read / 1M tokens
$0.021
Implicit cache read / 1M tokens
$0.043
Output / 1M tokens
$1.28
qwen3.6-plus
Max context: 256K tokens
Max context
256,000
Input / 1M tokens
$0.43
Explicit cache creation / 1M tokens
$0.53
Explicit cache read / 1M tokens
$0.043
Implicit cache read / 1M tokens
$0.085
Output / 1M tokens
$2.55
qwen3.5-plus
Max context: 256K tokens
Max context
128,000
Input / 1M tokens
$0.34
Explicit cache creation / 1M tokens
$0.43
Explicit cache read / 1M tokens
$0.034
Implicit cache read / 1M tokens
$0.068
Output / 1M tokens
$2.04
Max context
256,000
Input / 1M tokens
$0.34
Explicit cache creation / 1M tokens
$0.43
Explicit cache read / 1M tokens
$0.034
Implicit cache read / 1M tokens
$0.068
Output / 1M tokens
$2.04
qwen3.7-max
Max context: 1M tokens
Max context
1,000,000
Input / 1M tokens
$2.13
Explicit cache creation / 1M tokens
$2.66
Explicit cache read / 1M tokens
$0.21
Implicit cache read / 1M tokens
$0.43
Output / 1M tokens
$6.38
qwen3.6-27b
Max context: 256K tokens
Max context
256,000
Input / 1M tokens
$0.51
Output / 1M tokens
$3.06
qwen3.7-plus
Max context: 1M tokens
Max context
256,000
Input / 1M tokens
$0.34
Explicit cache creation / 1M tokens
$0.43
Explicit cache read / 1M tokens
$0.034
Implicit cache read / 1M tokens
$0.068
Output / 1M tokens
$1.36
Max context
1,000,000
Input / 1M tokens
$1.02
Explicit cache creation / 1M tokens
$1.28
Explicit cache read / 1M tokens
$0.10
Implicit cache read / 1M tokens
$0.20
Output / 1M tokens
$4.08
qwen3.8-flash
Max context: 1M tokens
Max context
1,000,000
Input / 1M tokens
$0.14
Explicit cache creation / 1M tokens
$0.17
Explicit cache read / 1M tokens
$0.014
Implicit cache read / 1M tokens
$0.027
Output / 1M tokens
$0.45
qwen3.8-27b
Max context: 1M tokens
Max context
1,000,000
Input / 1M tokens
$0.493
Explicit cache creation / 1M tokens
$0.62
Explicit cache read / 1M tokens
$0.0493
Implicit cache read / 1M tokens
$0.099
Output / 1M tokens
$2.15