News / PRICE

GLM 5.3 Flash repriced across 4 hosts: Wafer input down 11%, Cloudflare input and output up 100%

Published 23 September 2026
Price move, per 1M tokens
  • Cloudflare · input↑ 100%
    $0.15 → $0.30
  • Cloudflare · output↑ 100%
    $0.50 → $1.00
  • Cloudflare · cache readunchanged
    $0.030 → $0.030
  • Wafer · input↓ 11%
    $0.100 → $0.089
  • Wafer · outputunchanged
    $0.35 → $0.35
  • Wafer · cache read↑ 50%
    $0.020 → $0.030
  • Relace · input↓ 9%
    $0.11 → $0.10
  • Relace · outputunchanged
    $0.36 → $0.36
  • Relace · cache readunchanged
    $0.020 → $0.020
  • NextBit · input↓ 8%
    $0.180 → $0.165
  • NextBit · output↓ 8%
    $0.60 → $0.55
  • NextBit · cache read↓ 8%
    $0.036 → $0.033
Cloudflare input and output: ↑ 100%Wafer input: ↓ 11%Wafer cache read: ↑ 50%Relace input: ↓ 9%NextBit all rates: ↓ 8%
If you buy

Relace buyers now pay less for input on this model, so it suits steady prompt-heavy work; re-check your cache read and output rates before your next top-up.

The model
GLM 5.3 Flashopen the model →
Open weights321.3B parameters1311K context35 hosts
intelligence26th of 168 writing43rd of 168 coding22nd of 168 agents27th of 55

GLM 5.3 Flash is a downloadable model you can run yourself, and it is at its best when the job is agentic: picking the right tool and finishing the task. It is at its worst when the job is holding to a format under instruction, and we list no licence for it, so the terms need checking at the source.

Source

Read from the hosts' own published rates · we published this on 23 September 2026.