GLM 5.3 cut across 4 hosts, by up to 60% at Phala (input)
Published 30 September 2026
Price move, per 1M tokens
- Phala · input↓ 60%$1.40 → $0.56
- Phala · output↓ 23%$4.40 → $3.40
- Phala · cache read↓ 31%$0.26 → $0.18
- Relace · input↓ 13%$0.15 → $0.13
- Relace · outputunchanged$4.00 → $4.00
- Relace · cache read↓ 13%$0.15 → $0.13
- AkashML · input↓ 10%$1.17 → $1.05
- AkashML · output↓ 10%$3.96 → $3.56
- AkashML · cache readunchanged$0.23 → $0.23
- Makora · inputunchanged$0.85 → $0.85
- Makora · output↓ 6%$4.20 → $3.93
- Makora · cache readunchanged$0.19 → $0.19
| host | rate | was | now | change |
|---|---|---|---|---|
| Phala | input | $1.40 | $0.56 | ↓ 60% |
| Phala | output | $4.40 | $3.40 | ↓ 23% |
| Phala | cache read | $0.26 | $0.18 | ↓ 31% |
| Relace | input | $0.15 | $0.13 | ↓ 13% |
| Relace | output | $4.00 | $4.00 | — |
| Relace | cache read | $0.15 | $0.13 | ↓ 13% |
| AkashML | input | $1.17 | $1.05 | ↓ 10% |
| AkashML | output | $3.96 | $3.56 | ↓ 10% |
| AkashML | cache read | $0.23 | $0.23 | — |
| Makora | input | $0.85 | $0.85 | — |
| Makora | output | $4.20 | $3.93 | ↓ 6% |
| Makora | cache read | $0.19 | $0.19 | — |
Phala input: ↓ 60%Relace input and cache read: ↓ 13%AkashML input and output: ↓ 10%Makora output: ↓ 6%
If you buy
Renting this model at this host now costs less to run, so it suits steadier, larger workloads; re-check your output budget and cache terms 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 30 September 2026.
read the original at openrouter.ai ↗