Host Wafer cut DeepSeek V4 Flash input pricing by 30%
Published 16 September 2026
Price move, per 1M tokens
- Wafer · input↓ 30%$0.100 → $0.070
- Wafer · outputunchanged$0.25 → $0.25
- Wafer · cache read↓ 60%$0.050 → $0.020
| host | rate | was | now | change |
|---|---|---|---|---|
| Wafer | input | $0.100 | $0.070 | ↓ 30% |
| Wafer | output | $0.25 | $0.25 | — |
| Wafer | cache read | $0.050 | $0.020 | ↓ 60% |
input: ↓ 30%
If you buy
Long prompts and repeated context now cost less to run here, so it is worth re-checking your cache settings and whether your workload fits this host before your next top-up.
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 16 September 2026.
read the original at openrouter.ai ↗