DeepSeek V4.1 Flash repriced across 8 hosts: DigitalOcean down 40% on all rates, Wafer output up 36%
Published 1 October 2026
Price move, per 1M tokens
- DigitalOcean · input↓ 40%$0.30 → $0.18
- DigitalOcean · output↓ 40%$1.20 → $0.72
- DigitalOcean · cache read↓ 40%$0.0060 → $0.0036
- Wafer · input↓ 33%$0.075 → $0.050
- Wafer · output↑ 36%$0.44 → $0.60
- Wafer · cache read↓ 11%$0.045 → $0.040
- Io Net · input↑ 33%$0.090 → $0.120
- Io Net · outputunchanged$0.41 → $0.41
- Io Net · cache read↑ 11%$0.009 → $0.010
- Reka · input↓ 30%$0.20 → $0.14
- Reka · output↓ 33%$0.84 → $0.56
- Reka · cache read↑ 76%$0.0080 → $0.0141
- Morph · input↓ 32%$0.078 → $0.053
- Morph · output↓ 14%$0.50 → $0.43
- Morph · cache read↓ 50%$0.010 → $0.005
- Relace · input↑ 32%$0.0200 → $0.0264
- Relace · outputunchanged$0.60 → $0.60
- Relace · cache read↑ 32%$0.0200 → $0.0264
- AtlasCloud · input↑ 24%$0.114 → $0.141
- AtlasCloud · output↑ 24%$0.456 → $0.564
- AtlasCloud · cache read↑ 24%$0.0114 → $0.0141
- OpenInference · input↓ 22%$0.0198 → $0.0155
- OpenInference · outputunchanged$0.40 → $0.40
- OpenInference · cache readunchanged$0.003 → $0.003
| host | rate | was | now | change |
|---|---|---|---|---|
| DigitalOcean | input | $0.30 | $0.18 | ↓ 40% |
| DigitalOcean | output | $1.20 | $0.72 | ↓ 40% |
| DigitalOcean | cache read | $0.0060 | $0.0036 | ↓ 40% |
| Wafer | input | $0.075 | $0.050 | ↓ 33% |
| Wafer | output | $0.44 | $0.60 | ↑ 36% |
| Wafer | cache read | $0.045 | $0.040 | ↓ 11% |
| Io Net | input | $0.090 | $0.120 | ↑ 33% |
| Io Net | output | $0.41 | $0.41 | — |
| Io Net | cache read | $0.009 | $0.010 | ↑ 11% |
| Reka | input | $0.20 | $0.14 | ↓ 30% |
| Reka | output | $0.84 | $0.56 | ↓ 33% |
| Reka | cache read | $0.0080 | $0.0141 | ↑ 76% |
| Morph | input | $0.078 | $0.053 | ↓ 32% |
| Morph | output | $0.50 | $0.43 | ↓ 14% |
| Morph | cache read | $0.010 | $0.005 | ↓ 50% |
| Relace | input | $0.0200 | $0.0264 | ↑ 32% |
| Relace | output | $0.60 | $0.60 | — |
| Relace | cache read | $0.0200 | $0.0264 | ↑ 32% |
| AtlasCloud | input | $0.114 | $0.141 | ↑ 24% |
| AtlasCloud | output | $0.456 | $0.564 | ↑ 24% |
| AtlasCloud | cache read | $0.0114 | $0.0141 | ↑ 24% |
| OpenInference | input | $0.0198 | $0.0155 | ↓ 22% |
| OpenInference | output | $0.40 | $0.40 | — |
| OpenInference | cache read | $0.003 | $0.003 | — |
DigitalOcean all rates: ↓ 40%Wafer input: ↓ 33%Wafer output: ↑ 36%Io Net input: ↑ 33%Reka output: ↓ 33%Reka cache read: ↑ 76%Morph input: ↓ 32%Relace input and cache read: ↑ 32%AtlasCloud all rates: ↑ 24%OpenInference input: ↓ 22%
If you buy
On Wafer, output costs more while input and cache reads cost less, so re-check your budget if you generate long answers, and note prompt-heavy jobs now balance differently.
The model
DeepSeek V4.1 Flashopen the model →
Open weights763.2B parameters1049K context35 hosts
intelligence21st of 168 writing37th of 168 coding11th of 168 agents13th of 55
DeepSeek V4.1 Flash is a downloadable model with a permissive licence, and it places 11th of 168 on Arena Coding via Max as of 25 Sep 2026. At 763.2 billion parameters it is a data-centre job to run yourself, so hosted use is the practical route for most readers.
Source
Read on openrouter.ai · we published this on 1 October 2026.
read the original at openrouter.ai ↗