TheoArca Magnus 5.1
Theo's own deep-reasoning engine, governed and audited.
Theo's own engines, built and operated by TheoVex. TheoArca Velox answers fast; TheoArca Magnus reasons deeply. Both reach Theo through Theo's orchestration API on a key routed only to Arca. Magnus is the deep-reasoning tier: it reasons at full effort by default and answers in text.
- Context window
- 1,000,000 tokens
- Measured Sep 3, 2026
- Longest answer
- 131,072 tokens
- Measured Sep 3, 2026
What it does
In plain words
- Reasons deeply by default, with a 1M-token context window and answers of up to 131K tokens.
- Passes every request through a privacy guardrail: sensitive values are tokenized before inference and prompt-injection attempts are blocked.
- Records every request on an append-only, hash-chained audit ledger, tagged with its purpose.
- Answers in text. Flowcharts, notes, images and files are built by Theo's usual engine.
How it works
4 steps, every one of them ours to explain
01
You pick it, or Theo does
Choose Theo Arca from the composer, pin it as your engine in Settings, or pick a compliance tier in Code Canvas. Theo keeps its usual engines on standby behind it.
02
The request is screened and tagged
Sensitive values are tokenized before inference, prompt-injection attempts are blocked, and the request is tagged with the purpose it serves.
03
The engine answers in text
Flowcharts, notes, images and files are built by Theo's usual engine; Arca answers in words, with a 1M-token context window.
04
The ledger records it
Every request lands on an append-only, hash-chained audit ledger, so what ran and why can be shown after the fact.
Measured
Our numbers, with their dates
Measurements on our own hardware, not benchmark scores. Each one says what it is of, when it was taken and where it came from, and is re-measured rather than extrapolated when something changes.
- Context window
- 1,000,000 tokens
- The whole conversation, documents included, in one request.
- Measured Sep 3, 2026 · Gateway limits, read from the live endpoint
- Longest answer
- 131,072 tokens
- The gateway's output ceiling per request.
- Measured Sep 3, 2026 · Gateway limits, read from the live endpoint
Safety and retention
The controls we run, stated
A model we run is a model we are accountable for. These are the mechanisms in front of and behind TheoArca Magnus, and what is kept.
- A privacy guardrail screens every request: sensitive values are tokenized before inference and prompt-injection attempts are blocked.
- Every request lands on an append-only, hash-chained audit ledger, tagged with its purpose.
- Zero retention: nothing you send is used to train anything.
- Compliance is the product name for the governed pipeline. It is not a HIPAA or BAA claim; the managed deployment is the non-PHI tier.
Where it runs
The facts of the deployment
What you can hold us to: where TheoArca Magnus runs, how it is versioned, what happens to what you send it, and what is kept.
- Who runs it
- TheoVex, Theo's own lab, serves the TheoArca 5.1 family behind a governed gateway.
- How it's reached
- Through Theo's orchestration API (hitheo.ai), on a dedicated key whose routing is pinned to Arca.
- Your data
- Zero retention. Nothing you send is used to train anything.
- Guardrail
- A privacy guardrail screens every request: sensitive values are tokenized before inference and prompt-injection attempts are blocked.
- Audit
- Every request lands on an append-only, hash-chained audit ledger, tagged with its purpose.
- Capacity
- A 1M-token context window and answers of up to 131K tokens.
- Answers in text
- Flowcharts, notes, images and files are built by Theo's usual engine, Arca answers in words.
Where to find it
In Theo today, elsewhere as it becomes real
Theo Chat and Code Canvas
Available where enabled: choose Theo Arca in the composer, pin it in Settings, or pick the deep-reasoning compliance tier in Code Canvas.
- Rolling outInside Theo. The composer's Theo Arca pick, an engine pin in Settings and the Code Canvas compliance tiers, where enabled.
- In progressPublic API. Served through the TheoVex gateway today; a public, metered listing on model marketplaces is in progress.
- PlannedThird-party evaluation. Follows the public listing. Until then the benchmarks page shows OpenCharts' own runs, labelled internal.
Questions
About TheoArca Magnus
No. Let Theo orchestrate runs the standard lab engines and shows which one answered each step. TheoArca is the composer's pick and a pin: it leads only when you choose it, and Theo's usual engines stay on standby behind it.
Every request passes a privacy guardrail that tokenizes sensitive values and blocks prompt-injection attempts, is tagged with its purpose, and is recorded on an append-only, hash-chained audit ledger. These are mechanisms the platform documents, not certifications: it is not a HIPAA or BAA claim.
On the benchmarks page, labelled internal until a third party publishes a score. OpenCharts runs the public tests itself with versioned prompts and deterministic graders, records the engine that actually served each sample, and refuses to write a score the requested engine did not serve.
Built here, measured here, shown here.
One of these engines is in Theo today, and every one says what it is. Theo picks the right engine for each step and always shows which one answered.