GLM 5.3 cut across 3 hosts, by up to 16% at DigitalOcean (all rates)
Published 19 September 2026
Price move, per 1M tokens
- DigitalOcean · input↓ 16%$1.08 → $0.91
- DigitalOcean · output↓ 16%$3.39 → $2.86
- DigitalOcean · cache read↓ 16%$0.200 → $0.169
- Sail Research · input↓ 15%$1.207 → $1.025
- Sail Research · output↓ 15%$3.87 → $3.29
- Sail Research · cache read↓ 16%$0.225 → $0.190
- Inceptron · input↓ 3%$1.07 → $1.04
- Inceptron · output↓ 3%$4.00 → $3.88
- Inceptron · cache read↓ 4%$0.181 → $0.174
| host | rate | was | now | change |
|---|---|---|---|---|
| DigitalOcean | input | $1.08 | $0.91 | ↓ 16% |
| DigitalOcean | output | $3.39 | $2.86 | ↓ 16% |
| DigitalOcean | cache read | $0.200 | $0.169 | ↓ 16% |
| Sail Research | input | $1.207 | $1.025 | ↓ 15% |
| Sail Research | output | $3.87 | $3.29 | ↓ 15% |
| Sail Research | cache read | $0.225 | $0.190 | ↓ 16% |
| Inceptron | input | $1.07 | $1.04 | ↓ 3% |
| Inceptron | output | $4.00 | $3.88 | ↓ 3% |
| Inceptron | cache read | $0.181 | $0.174 | ↓ 4% |
DigitalOcean all rates: ↓ 16%Sail Research input and output: ↓ 15%Inceptron input and output: ↓ 3%
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 19 September 2026.
read the original at openrouter.ai ↗