TokenPlan Modeller

Every model included in TokenPlan, with prices per million tokens and the plans that include it.

DeepSeek

deepseek-v4-pro

Inmatning: $2.40
Utdata: $4.80
Cache read: $0.20
Implicit cache read: $0.20

per 1M tokens

deepseek-v4.1-flash

Inmatning: $0.30
Utdata: $1.20
Cache read: $0.03
Implicit cache read: $0.03

per 1M tokens

Zhipu GLM

glm-5.3

Inmatning: $1.40
Utdata: $4.40
Cache read: $0.28
Implicit cache read: $0.28

per 1M tokens

Alibaba Qwen

qwen3.7-max

Inmatning: $2.50
Utdata: $7.50
Cache read: $0.25
Implicit cache read: $0.50
Cache write: $3.125

per 1M tokens

qwen3.7-plus

Inmatning: $0.40
Utdata: $1.60
Cache read: $0.04
Implicit cache read: $0.08
Cache write: $0.50

per 1M tokens

qwen3.8-flash

Inmatning: $0.15
Utdata: $0.47
Cache read: $0.016
Implicit cache read: $0.016
Cache write: $0.20

per 1M tokens

qwen3.8-max

Inmatning: $2.00
Utdata: $6.00
Cache read: $0.17
Implicit cache read: $0.25
Cache write: $2.50

per 1M tokens