DeepSeek V4 Flash repriced across 3 hosts: StreamLake output down 79%, Wafer output up 100%
Published 1 October 2026
Price move, per 1M tokens
- Wafer · input↑ 71%$0.070 → $0.120
- Wafer · output↑ 100%$0.35 → $0.70
- Wafer · cache read↓ 6%$0.053 → $0.050
- StreamLake · input↓ 68%$0.44 → $0.14
- StreamLake · output↓ 79%$1.32 → $0.28
- StreamLake · cache read↑ 100%$0.014 → $0.028
- Relace · input↓ 50%$0.0090 → $0.0045
- Relace · outputunchanged$1.28 → $1.28
- Relace · cache read↓ 50%$0.0090 → $0.0045
| host | rate | was | now | change |
|---|---|---|---|---|
| Wafer | input | $0.070 | $0.120 | ↑ 71% |
| Wafer | output | $0.35 | $0.70 | ↑ 100% |
| Wafer | cache read | $0.053 | $0.050 | ↓ 6% |
| StreamLake | input | $0.44 | $0.14 | ↓ 68% |
| StreamLake | output | $1.32 | $0.28 | ↓ 79% |
| StreamLake | cache read | $0.014 | $0.028 | ↑ 100% |
| Relace | input | $0.0090 | $0.0045 | ↓ 50% |
| Relace | output | $1.28 | $1.28 | — |
| Relace | cache read | $0.0090 | $0.0045 | ↓ 50% |
Wafer output: ↑ 100%Wafer cache read: ↓ 6%StreamLake output: ↓ 79%StreamLake cache read: ↑ 100%Relace input and cache read: ↓ 50%
If you buy
On Wafer, running this model now costs more per token, so check your usage mix and cache settings before your next top-up, and confirm the current rate on the host page.
The model
DeepSeek V4 Flashopen the model →
Open weights290.9B parameters1049K context33 hosts
intelligence65th of 168 writing57th of 168 coding64th of 168 agents20th of 55
DeepSeek V4 Flash is a downloadable text model with a permissive licence, built for long-document work where the bill matters more than peak quality. Its measured quality is weak on the LiveBench boards and mid-pack on the Arena boards, so treat it as a cheap workhorse rather than a quality leader.
Source
Read on openrouter.ai · we published this on 1 October 2026.
read the original at openrouter.ai ↗