News / PRICE

GLM 5.3 repriced across 3 hosts: Sail Research (US region) input and output down 23%, Wafer input up 47%

Published 17 September 2026
Price move, per 1M tokens
  • Wafer · input↑ 47%
    $0.95 → $1.40
  • Wafer · outputunchanged
    $4.40 → $4.40
  • Wafer · cache read↑ 37%
    $0.19 → $0.26
  • Sail Research (US region) · input↓ 23%
    $1.26 → $0.97
  • Sail Research (US region) · output↓ 23%
    $3.95 → $3.04
  • Sail Research (US region) · cache read↓ 27%
    $0.233 → $0.171
  • Sail Research · input↓ 23%
    $1.26 → $0.97
  • Sail Research · output↓ 23%
    $3.95 → $3.04
  • Sail Research · cache read↓ 26%
    $0.23 → $0.17
  • DigitalOcean · input↑ 13%
    $0.950 → $1.078
  • DigitalOcean · output↓ 0.4%
    $3.40 → $3.39
  • DigitalOcean · cache read↑ 0.1%
    $0.2000 → $0.2002
Wafer input: ↑ 47%Sail Research (US region) input and output: ↓ 23%Sail Research input and output: ↓ 23%DigitalOcean input: ↑ 13%
If you buy

Renters on Wafer now pay more for the same model, so check whether your workload leans on input and cache reads before your next top-up.

The model
GLM 5.3open the model →
Proprietary1049K context38 hosts
intelligence16th of 168 writing19th of 168 coding23rd of 168 agents17th of 55

GLM 5.3 is a hosted-only text model: we list no download for it, so using it means choosing a host. It is strongest where people rate the answers themselves, and mid-field on the harder task sets.

Source

Read on openrouter.ai · we published this on 17 September 2026.

read the original at openrouter.ai ↗