DeepSeek V4 Pro repriced across 3 hosts: Relace input and cache read down 18%, Ionstream input up 104%
Published 30 September 2026
Price move, per 1M tokens
- Ionstream · input↑ 104%$0.608 → $1.238
- Ionstream · output↓ 6%$1.96 → $1.85
- Ionstream · cache readunchanged$0.088 → $0.088
- Relace · input↓ 18%$0.150 → $0.123
- Relace · outputunchanged$3.50 → $3.50
- Relace · cache read↓ 18%$0.150 → $0.123
- Wafer · input↓ 1%$0.480 → $0.475
- Wafer · output↓ 17%$4.20 → $3.49
- Wafer · cache read↑ 24%$0.38 → $0.47
| host | rate | was | now | change |
|---|---|---|---|---|
| Ionstream | input | $0.608 | $1.238 | ↑ 104% |
| Ionstream | output | $1.96 | $1.85 | ↓ 6% |
| Ionstream | cache read | $0.088 | $0.088 | — |
| Relace | input | $0.150 | $0.123 | ↓ 18% |
| Relace | output | $3.50 | $3.50 | — |
| Relace | cache read | $0.150 | $0.123 | ↓ 18% |
| Wafer | input | $0.480 | $0.475 | ↓ 1% |
| Wafer | output | $4.20 | $3.49 | ↓ 17% |
| Wafer | cache read | $0.38 | $0.47 | ↑ 24% |
Ionstream output: ↓ 6%Ionstream input: ↑ 104%Relace input and cache read: ↓ 18%Wafer output: ↓ 17%Wafer cache read: ↑ 24%
If you buy
Ionstream now charges far more for input on this model, so if your workload is prompt-heavy, re-check your cost per call 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 30 September 2026.
read the original at openrouter.ai ↗