Host Sail Research repriced DeepSeek V4.1 Flash: input down 35%, output up 25%
Published 22 September 2026
Price move, per 1M tokens
- Sail Research · input↓ 35%$0.20 → $0.13
- Sail Research · output↑ 25%$0.60 → $0.75
- Sail Research · cache read↓ 75%$0.040 → $0.010
| host | rate | was | now | change |
|---|---|---|---|---|
| Sail Research | input | $0.20 | $0.13 | ↓ 35% |
| Sail Research | output | $0.60 | $0.75 | ↑ 25% |
| Sail Research | cache read | $0.040 | $0.010 | ↓ 75% |
input: ↓ 35%output: ↑ 25%
If you buy
Workloads that lean on cached context and heavy input now stretch further here, while output-heavy jobs cost more, so re-check your mix before your next top-up.
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 22 September 2026.
read the original at openrouter.ai ↗