GLM 5.2 repriced across 5 hosts: Wafer input down 71%, Inceptron input up 85%
Published 1 October 2026
Price move, per 1M tokens
- Inceptron · input↑ 85%$0.75 → $1.39
- Inceptron · output↑ 83%$2.40 → $4.39
- Inceptron · cache read↑ 48%$0.169 → $0.250
- Wafer · input↓ 71%$1.40 → $0.41
- Wafer · output↓ 9%$4.40 → $3.99
- Wafer · cache readunchanged$0.26 → $0.26
- Reka · input↓ 50%$1.40 → $0.70
- Reka · output↓ 68%$4.40 → $1.40
- Reka · cache read↓ 30%$0.20 → $0.14
- Morph · input↑ 20%$0.387 → $0.464
- Morph · output↑ 6%$2.69 → $2.84
- Morph · cache readunchanged$0.20 → $0.20
- Relace · input↓ 3%$0.135 → $0.131
- Relace · outputunchanged$4.00 → $4.00
- Relace · cache read↓ 3%$0.135 → $0.131
| host | rate | was | now | change |
|---|---|---|---|---|
| Inceptron | input | $0.75 | $1.39 | ↑ 85% |
| Inceptron | output | $2.40 | $4.39 | ↑ 83% |
| Inceptron | cache read | $0.169 | $0.250 | ↑ 48% |
| Wafer | input | $1.40 | $0.41 | ↓ 71% |
| Wafer | output | $4.40 | $3.99 | ↓ 9% |
| Wafer | cache read | $0.26 | $0.26 | — |
| Reka | input | $1.40 | $0.70 | ↓ 50% |
| Reka | output | $4.40 | $1.40 | ↓ 68% |
| Reka | cache read | $0.20 | $0.14 | ↓ 30% |
| Morph | input | $0.387 | $0.464 | ↑ 20% |
| Morph | output | $2.69 | $2.84 | ↑ 6% |
| Morph | cache read | $0.20 | $0.20 | — |
| Relace | input | $0.135 | $0.131 | ↓ 3% |
| Relace | output | $4.00 | $4.00 | — |
| Relace | cache read | $0.135 | $0.131 | ↓ 3% |
Inceptron input: ↑ 85%Wafer input: ↓ 71%Reka output: ↓ 68%Morph input: ↑ 20%Relace input and cache read: ↓ 3%
If you buy
Inceptron now costs more to run for the same model, so re-check your budget before the next top-up and weigh the other hosts listed beside this item.
The model
GLM 5.2open the model →
Open weights753.3B parameters1049K context34 hosts
intelligence23rd of 168 writing21st of 168 coding37th of 168 agents14th of 55
Available from 30 hosted offers, this large downloadable model from Zhipu carries a permissive MIT licence and a one-million-token request limit. It is a strong choice for teams that want top-tier capability without licensing restrictions.
Source
Read on openrouter.ai · we published this on 1 October 2026.
read the original at openrouter.ai ↗