Sovereign inference — GLM 5.3
Your sovereign, private GLM 5.3
A reasoning model in the extra-large tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in Units of Intelligence at the published rates below. No training on your data, no vendor lock-in.
AU · EU · US resident1.56 UoI/1M input4.68 UoI/1M output0.33 UoI/1M cached input800K context
How GLM 5.3 compares
Independent intelligence index for GLM 5.3 against every peer in the Extra-large tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Capability indexes
Domain-weighted agentic performance for GLM 5.3.
Capability index vs extra-large peers
Finance & AccountingStrategy & OpsLegalHealthcare & MedicalEngineeringEconomics
The evaluations behind the index
Independent benchmark results for GLM 5.3 — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 1516.38 | 31.1 min | 136335 |
| GDPval-AA | 1645.52 | 21.5 min | 94423 |
| AutomationBench-AA | 62.2% | 6.3 min | 27738 |
| Terminal-Bench 4.0 | 41.9% | 44.3 min | 194566 |
| SciCode | 59.0% | 4.0 min | 17515 |
| Humanity's Last Exam | 42.3% | 12.0 min | 52817 |
| GDP.pdf | 11.2% | 6.5 min | 28417 |
| CritPt | 19.1% | 22.8 min | 99950 |
| AA-Omniscience | 14.30 | 0.6 min | 2543 |
| AA-LCR (long context) | 79.7% | 0.6 min | 2806 |
Run GLM 5.3 privately
One key, one endpoint, three jurisdictions.
- Size tierExtra-large
- Input rate1.56 UoI/1M
- Output rate4.68 UoI/1M
- Cached input rate0.33 UoI/1M
- Context window800K tokens
- Max output16K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputText only
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call
Copyright 2026 ToothFairyAI PTY LTD. All Rights Reserved.
