Model vs model
deepseek-v4-pro vs deepseek-v4.1-flash
Both models on Cent AI, priced from the active price version, next to each publisher's official rate.
deepseek-v4-pro
Checking status75% off
Price version 4 · in effect since Nov 19, 2026
per 1M tokens
InputOfficial price $0.66$0.165
Cache readOfficial price $0.022$0.0055
Cache write$0.165
OutputOfficial price $1.98$0.495
- Minimum per request
- $0.00002
- Context window
- —
Endpoints
- /v1/chat/completions
- /v1/responses
- /v1/messages
deepseek-v4.1-flash
Checking status90% off
Price version 4 · in effect since Nov 12, 2026
per 1M tokens
InputOfficial price $0.15$0.015
Cache readOfficial price $0.003$0.0021
Cache write$0.015
OutputOfficial price $0.60$0.06
- Minimum per request
- $0.00002
- Context window
- —
Endpoints
- /v1/chat/completions
- /v1/responses
- /v1/messages
The same workload on both
deepseek-v4-proOfficial price $67.32$16.83
deepseek-v4.1-flashOfficial price $15.45$1.545
On this workload deepseek-v4.1-flash costs $15.285 less than deepseek-v4-pro at Cent AI.
Workload: 99,000,000 input and 1,000,000 output tokens a month, no cache. With cache the gap changes; try your own mix in the calculator.
Try deepseek-v4-pro and deepseek-v4.1-flash with one key
One prepaid balance for every model. Pay with QRIS or USDT/USDC.