Host Wafer repriced DeepSeek V4 Pro: input up 20%, cache read down 30%
Published 27 September 2026
Price move, per 1M tokens
- Wafer · input↑ 20%$0.245 → $0.293
- Wafer · outputunchanged$3.50 → $3.50
- Wafer · cache read↓ 30%$0.245 → $0.172
| host | rate | was | now | change |
|---|---|---|---|---|
| Wafer | input | $0.245 | $0.293 | ↑ 20% |
| Wafer | output | $3.50 | $3.50 | — |
| Wafer | cache read | $0.245 | $0.172 | ↓ 30% |
input: ↑ 20%cache read: ↓ 30%
If you buy
If you lean on cached context, your bill at Wafer shifts toward cache reads, so re-check your caching setup and how much fresh input you send before your next top-up.
The model
DeepSeek V4 Proopen the model →
Open weights1598.8B parameters1049K context28 hosts
intelligence36th of 168 writing32nd of 168 coding43rd of 168 agents31st of 55
DeepSeek V4 Pro is a large downloadable text model with a one-million-token request limit and strong mathematics scores. Its mixture-of-experts design keeps only 37 billion parameters active per token, making it more efficient to run than its total size suggests.
Source
Read on openrouter.ai · we published this on 27 September 2026.
read the original at openrouter.ai ↗