Host Relace cut DeepSeek V4.1 Flash input and output pricing by 13%
Published 19 September 2026
Price move, per 1M tokens
- Relace · input↓ 13%$0.15 → $0.13
- Relace · output↓ 13%$0.60 → $0.52
- Relace · cache read↓ 83%$0.0150 → $0.0026
| host | rate | was | now | change |
|---|---|---|---|---|
| Relace | input | $0.15 | $0.13 | ↓ 13% |
| Relace | output | $0.60 | $0.52 | ↓ 13% |
| Relace | cache read | $0.0150 | $0.0026 | ↓ 83% |
input and output: ↓ 13%
If you buy
anyone running long prompts with heavy cache reuse on this host now gets more work out of the same top-up, so re-check your cache hit rate before sizing the next one.
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 19 September 2026.
read the original at openrouter.ai ↗