DeepSeek V4 Flash repriced across 2 hosts: Sail Research input down 21%, Inceptron output up 17%
Published 25 September 2026
Price move, per 1M tokens
- Sail Research · input↓ 21%$0.038 → $0.030
- Sail Research · outputunchanged$0.55 → $0.55
- Sail Research · cache read↓ 30%$0.023 → $0.016
- Sail Research (US region) · input↓ 21%$0.038 → $0.030
- Sail Research (US region) · outputunchanged$0.55 → $0.55
- Sail Research (US region) · cache read↓ 30%$0.023 → $0.016
- Inceptron · inputunchanged$0.083 → $0.083
- Inceptron · output↑ 17%$0.41 → $0.48
- Inceptron · cache read↓ 17%$0.060 → $0.050
| host | rate | was | now | change |
|---|---|---|---|---|
| Sail Research | input | $0.038 | $0.030 | ↓ 21% |
| Sail Research | output | $0.55 | $0.55 | — |
| Sail Research | cache read | $0.023 | $0.016 | ↓ 30% |
| Sail Research (US region) | input | $0.038 | $0.030 | ↓ 21% |
| Sail Research (US region) | output | $0.55 | $0.55 | — |
| Sail Research (US region) | cache read | $0.023 | $0.016 | ↓ 30% |
| Inceptron | input | $0.083 | $0.083 | — |
| Inceptron | output | $0.41 | $0.48 | ↑ 17% |
| Inceptron | cache read | $0.060 | $0.050 | ↓ 17% |
Sail Research input: ↓ 21%Sail Research (US region) input: ↓ 21%Inceptron output: ↑ 17%Inceptron cache read: ↓ 17%
If you buy
On Inceptron, output now costs more while cache reads cost less, so re-check your mix of fresh output against cached input 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 25 September 2026.
read the original at openrouter.ai ↗