Nox Orion 2.1
Frontier AI health model · Released in Nox: October 22, 2026 · Page last updated: November 10, 2026
The Nox 2.1 flagship, with a peer-review answer pipeline
Orion 2.1 is the flagship of the Nox 2 generation and the successor to Orion 2. The engine is unchanged — an 824-billion-parameter mixture-of-experts model, 46 billion active per token, with a roughly one-million-token context window — and the change is in how the answer is produced: a peer-review pipeline that briefs the case, writes a specialist checklist before drafting, drafts against it, and has the draft reviewed before anything reaches you. It was designed from the point losses measured on HealthBench Professional: missing named specifics, embedded errors in pasted plans that went unflagged, decisive context that was never asked for, mixed-language replies, and over-long answers.
Architecture: mixture-of-experts, 824 billion parameters total, 46 billion active per token — the 700-billion-parameter backbone of 1.3 Astra extended with roughly 100 billion parameters of additional trainable components. Orion 2.1 runs the same engine as Orion 2.
Peer-review pipeline (new in 2.1): before drafting, Orion 2.1 writes a task brief — deliverable, audience, language, constraints, claims embedded in the user's own text, missing context that would change the advice, and the named specifics a specialist would expect — and, in parallel, a specialist checklist. The draft is written against both, then an independent review pass checks the draft item by item and returns the corrected reply. Only the final reply is shown; the review is never pasted into the answer.
Length: earlier Nox models answered under a fixed 4,000-character cap. Lifting that cap alone raised HealthBench Hard by 8.4 ± 2.0 points on a 150-example paired test, almost entirely on completeness. Orion scales length to the question instead — short for simple questions, up to 9,000 characters for multi-part ones — and covers the direct answer, main alternatives, next steps, and what would warrant urgent care.
Measured on the 1.4 Orion pipeline in September 2026: HealthBench Hard, Nox self-run, official open protocol, all 1,000 examples, scored 46.4% (±0.8) at level 5 (Ultra) and 53.3% (±1.0) at level 6 (then called Hyper Ultra). Orion 2.1 runs the same engine, so these remain the most recent published Hard results; they have not been re-measured under the Orion 2.1 name. 1.3 Astra on the identical protocol: 34.8%. Separately, the evaluated Orion 2.1 + compact Peer Review configuration completed all 525 HealthBench Professional tasks on October 23, 2026: raw 72.8%, length-adjusted 69.5%, using GPT-5.4 low as grader. This evaluation includes live web evidence and failure-only recovery of three tasks. On October 24, 2026 the HealthBenchAI team listed it on its HealthBench Professional results page at 69.5 length-adjusted (95% CI 65.81–73.03), the highest score on that page among the 22 models listed; HealthBenchAI states this is a team-operated, tool-assisted evaluation whose arithmetic was checked, not a third-party certification, and that scores from different protocols are not directly comparable.
Hyper Ultra was Orion’s sixth thinking level, in Plan mode on MAX, until it was removed in November 2026: the same model making several passes over one question — draft, self-written rubric, self-grade, revision — in about five to six minutes per answer. Orion 2.1 now has five thinking levels: Low, Medium, High, Extra High, and Ultra. On a fixed 150-prompt development subset the 1.4 Orion pipeline scored 36.2% at level 1 (then called Light), 36.8% at level 2 (then Balanced), 36.9% at level 3 (then Extra), and 38.5% at level 4 (then Max).
Multimodal and tool-using: up to ten photos per message; live web access in Plan mode with up to ten search-and-read rounds per answer, every source cited; inline health and anatomy image generation; thinking time shown on every answer and a live step timeline in Plan mode. In NOX WORK it also reads attached documents (PDF, Word, Excel, PowerPoint, CSV, text, code — three files of 15 MB each), removes backgrounds from and upscales images, and reads connected apps.
Orion 2.1 Pro is Orion 2.1 in Plan mode on the Nox web app with new tools: ask for an interactive page, chart, calculator, 3D model, or MP4 video and Orion builds it, checks that it runs in an isolated browser sandbox, and opens it beside the chat with a live preview, source view, version history, restore, and download; follow-up messages edit the same artifact. You can also attach a file to a message and Nox reads it; the original file is deleted once it has been read.
Available in Plan mode on Pro and MAX and as a selectable model in NOX WORK. Not an everyday-chat model.
Capabilities
- 824-billion-parameter mixture-of-experts model, 46 billion active per token
- ~1,000,000-token context window
- Deliberate internal reasoning pass before every answer, thinking time shown
- Five thinking levels, Low to Ultra
- Dynamic answer length, up to a 9,000-character cap
- Photo input — up to ten images per message
- Live web access in Plan mode — up to ten search-and-read rounds per answer, every source cited
- Image generation — health and anatomy illustrations inline
- Plan mode progress timeline
- In NOX WORK: document reading, image background removal and upscaling, connected-app reads
- Orion 2.1 Pro (Plan mode, web): live artifacts built and checked in a browser sandbox, with versions and download
Model details
- Architecture — Mixture-of-experts — 824 billion parameters total, 46 billion active per token; the 700-billion-parameter 1.3 Astra backbone extended with roughly 100 billion parameters of additional trainable components.
- Context window — ~1,000,000 tokens
- Answer length — Dynamic — sized to the question, up to a 9,000-character hard cap
- Reasoning — Deliberate internal reasoning pass before every answer, with thinking time shown
- Answer pipeline — Peer review (new in 2.1) — task brief and specialist checklist before drafting, draft against both, independent review pass; only the final reply is shown
- HealthBench Hard — Measured on the 1.4 Orion pipeline (same engine): 46.4% (±0.8) at level 5 (Ultra), September 5, 2026; 53.3% (±1.0) at level 6 (then called Hyper Ultra, removed in November 2026), September 11, 2026 — Nox's own self-runs, official open protocol, all 1,000 examples; not re-measured under 2.1; not independently verified.
- HealthBench Professional — Nox Orion 2.1 (Ultra): evaluated October 23, 2026, all 525 tasks completed. Raw 72.8%; length-adjusted 69.5%; 485 tasks held out of tuning scored 69.8% adjusted. GPT-5.4 low grader; single run with failure-only recovery of three tasks, live web evidence and multi-stage review. Forty tasks were used during development. This measures the evaluated configuration, not every production request; listed first at 69.5 (95% CI 65.81–73.03) on the HealthBenchAI Professional results page on October 24, 2026 — a team-operated, tool-assisted evaluation with arithmetic checked, not a third-party certification or clinical validation. Summary and methodology: /data/healthbench/orion-2-peer-review/README.md
- Thinking levels — Five — Low, Medium, High, Extra High, Ultra
- Raw evidence — Every answer, every grader verdict, aggregate files and SHA-256 checksums are published: level 5 (Ultra) at https://www.getnox.ai/data/healthbench/orion/README.md, level 6 (then called Hyper Ultra) at https://www.getnox.ai/data/healthbench/orion-hyper-ultra/README.md
- Orion 2.1 Pro — Orion 2.1 in Plan mode on the web app with the artifact workspace, on Pro and MAX. Artifacts are built, checked in an isolated browser sandbox, versioned, and downloadable. Building artifacts does not use credits.
- Photo understanding — Yes — up to ten images per message, read automatically
- Live web access — Yes — in Plan mode, up to ten search-and-read rounds per answer, every source cited
- Image generation — Yes — health and anatomy illustrations rendered inline on request
- Available on — Plan mode on Pro and MAX; selectable in NOX WORK
Availability: Available in Plan mode on Pro and MAX; selectable in NOX WORK.
Nox Orion 2.1 is the named replacement for Nox Orion 2 (retired on October 22, 2026), Nox 1.3 Astra (retired on October 5, 2026), Nox 1.4 Orion (retired on September 23, 2026), Nox 1.3 Nova (retired on September 23, 2026), Nox Agent 1.2 (retired on September 23, 2026).
Nox Orion 2.1 — frequently asked questions
What is Nox Orion 2.1?
Nox Orion 2.1 is Nox's frontier ai health model. Orion 2.1 is the flagship of the Nox 2 generation and the successor to Orion 2. The engine is unchanged — an 824-billion-parameter mixture-of-experts model, 46 billion active per token, with a roughly one-million-token context window — and the change is in how the answer is produced: a peer-review pipeline that briefs the case, writes a specialist checklist before drafting, drafts against it, and has the draft reviewed before anything reaches you. It was designed from the point losses measured on HealthBench Professional: missing named specifics, embedded errors in pasted plans that went unflagged, decisive context that was never asked for, mixed-language replies, and over-long answers.
What can Nox Orion 2.1 do?
Nox Orion 2.1's capabilities: 824-billion-parameter mixture-of-experts model, 46 billion active per token; ~1,000,000-token context window; Deliberate internal reasoning pass before every answer, thinking time shown; Five thinking levels, Low to Ultra; Dynamic answer length, up to a 9,000-character cap; Photo input — up to ten images per message; Live web access in Plan mode — up to ten search-and-read rounds per answer, every source cited; Image generation — health and anatomy illustrations inline; Plan mode progress timeline; In NOX WORK: document reading, image background removal and upscaling, connected-app reads; Orion 2.1 Pro (Plan mode, web): live artifacts built and checked in a browser sandbox, with versions and download.
What architecture does Nox Orion 2.1 use?
Architecture: Mixture-of-experts — 824 billion parameters total, 46 billion active per token; the 700-billion-parameter 1.3 Astra backbone extended with roughly 100 billion parameters of additional trainable components.
How large is Nox Orion 2.1's context window?
Context window: ~1,000,000 tokens
How long are Nox Orion 2.1's answers?
Answer length: Dynamic — sized to the question, up to a 9,000-character hard cap
Which thinking levels does Nox Orion 2.1 offer?
Thinking levels: Five — Low, Medium, High, Extra High, Ultra
Which Nox plans include Nox Orion 2.1?
Available in Plan mode on Pro and MAX; selectable in NOX WORK.
Which retired Nox models does Nox Orion 2.1 replace?
Nox Orion 2.1 is the named replacement for Nox Orion 2 (retired on October 22, 2026), Nox 1.3 Astra (retired on October 5, 2026), Nox 1.4 Orion (retired on September 23, 2026), Nox 1.3 Nova (retired on September 23, 2026) and Nox Agent 1.2 (retired on September 23, 2026). Each retired model's page states what its replacement covers.
Related Nox models
- Nox Orion 2 — Retired — the first flagship of the Nox 2 generation (retired)
- Nox 1.3 Astra — Deep reasoning with a one-million-token context — retired October 5, 2026 (retired)
- Nox 1.4 Orion — Retired — the flagship of the Nox 1.4 generation (retired)
- Nox 1.3 Nova — Retired — the balanced model of the 1.3 family (retired)
- Nox Agent 1.2 — Retired — Nox's former dedicated research mode (retired)
- Nox GHI 1 — The officially released model system that powers Pebs, Nox's agent
- Nox Orion 2.5 — The new flagship — workspace tools built in, health research tools, and a staged review at Ultra
- Nox Orion Flash 2.5 — The fast Orion 2.5 — native photo input, workspace tools built in, and the same review at Ultra
- Nox Orion 2.6 Cyber Preview — A dedicated security model for defensive and authorized security work — hardened against misuse and prompt injection
- Nox Orion 2.1 Pro — Visualize your body: 3D models, code, and MP4 video
- Nox Orion Flash 2.1 — The fast Orion on a new engine — 552B mixture-of-experts, native photo input
- Nox Vela 2.5 — The fast everyday model on every plan — now reads images
- Nox Voice 2 — The most powerful Nox voice yet — expressive, interruptible, Plan mode in the call
Back to the Nox model family · Plans and pricing · Nox features