News / PRICE

DeepSeek V4 Flash 0423 repriced across 4 hosts: OpenInference input down 25%, Sail Research output up 90%

Published 17 September 2026
Price move, per 1M tokens
  • Sail Research · input↑ 14%
    $0.065 → $0.074
  • Sail Research · output↑ 90%
    $0.180 → $0.342
  • Sail Research · cache read↑ 14%
    $0.0200 → $0.0228
  • DigitalOcean · input↑ 44%
    $0.068 → $0.098
  • DigitalOcean · output↑ 17%
    $0.168 → $0.196
  • DigitalOcean · cache read↑ 17%
    $0.0168 → $0.0196
  • OpenInference · input↓ 25%
    $0.040 → $0.030
  • OpenInference · output↑ 30%
    $0.10 → $0.13
  • OpenInference · cache readunchanged
    $0.010 → $0.010
  • Inceptron · input↓ 3%
    $0.061 → $0.059
  • Inceptron · output↓ 3%
    $0.203 → $0.197
  • Inceptron · cache read↓ 1%
    $0.0096 → $0.0095
Sail Research output: ↑ 90%DigitalOcean input: ↑ 44%OpenInference input: ↓ 25%OpenInference output: ↑ 30%Inceptron input and output: ↓ 3%
If you buy

Renters on this host now pay more for both directions, so check your usage mix and cache settings 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 17 September 2026.

read the original at openrouter.ai ↗