Sovereign inference — GLM 5.2
Your sovereign, private GLM 5.2
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 5.2 compares
Independent intelligence index for GLM 5.2 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 5.2.
Capability index vs extra-large peers
Finance & AccountingStrategy & OpsLegalHealthcare & MedicalEngineeringEconomics
The evaluations behind the index
Independent benchmark results for GLM 5.2 — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 1232.95 | 23.3 min | 115123 |
| GDPval-AA | 1357.52 | 16.0 min | 78757 |
| AutomationBench-AA | 28.4% | 7.8 min | 38464 |
| Terminal-Bench 4.0 | 1.0% | 40.0 min | 197218 |
| SciCode | 51.2% | 2.4 min | 11809 |
| Humanity's Last Exam | 41.1% | 8.2 min | 40587 |
| GDP.pdf | 10.4% | 2.3 min | 11573 |
| CritPt | 20.9% | 21.6 min | 106412 |
| AA-Omniscience | 4.43 | 0.4 min | 1912 |
| AA-LCR (long context) | 78.3% | 0.8 min | 4061 |
Run GLM 5.2 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.
