DeepSeek V4 Flash repriced across 4 hosts: Sail Research input down 49%, Relace output up 100%
Published 22 September 2026
Price move, per 1M tokens
- Relace · inputunchanged$0.040 → $0.040
- Relace · output↑ 100%$0.32 → $0.64
- Relace · cache readunchanged$0.016 → $0.016
- OpenInference · inputunchanged$0.040 → $0.040
- OpenInference · output↑ 67%$0.30 → $0.50
- OpenInference · cache readunchanged$0.014 → $0.014
- Sail Research · input↓ 49%$0.074 → $0.038
- Sail Research · output↑ 61%$0.342 → $0.550
- Sail Research · cache readunchanged$0.023 → $0.023
- Inceptron · input↑ 50%$0.080 → $0.120
- Inceptron · outputunchanged$0.50 → $0.50
- Inceptron · cache readunchanged$0.050 → $0.050
| host | rate | was | now | change |
|---|---|---|---|---|
| Relace | input | $0.040 | $0.040 | — |
| Relace | output | $0.32 | $0.64 | ↑ 100% |
| Relace | cache read | $0.016 | $0.016 | — |
| OpenInference | input | $0.040 | $0.040 | — |
| OpenInference | output | $0.30 | $0.50 | ↑ 67% |
| OpenInference | cache read | $0.014 | $0.014 | — |
| Sail Research | input | $0.074 | $0.038 | ↓ 49% |
| Sail Research | output | $0.342 | $0.550 | ↑ 61% |
| Sail Research | cache read | $0.023 | $0.023 | — |
| Inceptron | input | $0.080 | $0.120 | ↑ 50% |
| Inceptron | output | $0.50 | $0.50 | — |
| Inceptron | cache read | $0.050 | $0.050 | — |
Relace output: ↑ 100%OpenInference output: ↑ 67%Sail Research input: ↓ 49%Sail Research output: ↑ 61%Inceptron input: ↑ 50%
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 22 September 2026.
read the original at openrouter.ai ↗