Your sovereign, private GLM 5.1
GLM 5.1 is Z.ai's GLM-5-series reasoner (753B total, MoE), offering strong coding, agentic tool use and reasoning with a large context window — the incremental release between GLM-5 and 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 US dollars per million tokens at the published rates below. No training on your data, no vendor lock-in.
How GLM 5.1 compares
Independent intelligence index for GLM 5.1 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 5.1.
Capability index vs extra-large peers
The evaluations behind the index
Independent benchmark results for GLM 5.1 — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 963.92 | 17.6 min | 42816 |
| GDPval-AA | 1103.36 | 12.7 min | 30858 |
| AutomationBench-AA | 20.3% | 10.1 min | 24585 |
| Terminal-Bench 4.0 | 2.0% | 64.7 min | 156878 |
| SciCode | 44.8% | 4.2 min | 10086 |
| Humanity's Last Exam | 30.1% | 15.6 min | 37819 |
| GDP.pdf | 8.4% | 2.7 min | 6554 |
| CritPt | 4.6% | 36.3 min | 88173 |
| AA-Omniscience | 85.0% | 0.9 min | 2295 |
| AA-LCR (long context) | 73.7% | 2.2 min | 5243 |
Run GLM 5.1 privately
One key, one endpoint, three jurisdictions.
- Size tierExtra-large
- Serving routeStandard
- Input rate$1.72/1M
- Output rate$5.50/1M
- Cached input rate$0.33/1M
- Context window203K 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