Last updated: 11/21/2026Last verified: 2026-11-21
Antinuous is a research platform from Antinuous, Inc. that runs autonomous research, experiments and simulations in parallel: agent swarms split a question, run code in simulations on their own compute, and return cited artifacts such as notebooks, decks, sheets and CAD models. The site sells monthly plans from Free $0 to Ultra $200, and the same tools are reachable over MCP or A2A from Claude, ChatGPT, Codex and Cursor.
What is Antinuous?
Antinuous is a research and simulation platform from Antinuous, Inc. A lead agent splits a question into smaller tasks, and agent swarms search, plan and run experiments or simulations in parallel; each round drops weaker branches after review. Every run gets its own computer with simulation and engineering tools, and large jobs split across worker pools. Results arrive as artifacts - notebooks, documents, decks, charts, maps, tables, CAD models and protein structures - where each value links to its source or code. The same tools are reachable over MCP and A2A, so Claude, ChatGPT, Claude Code, Codex and Cursor can start or continue research.
Key Features
- Agent swarms: a lead agent splits a question across many agents that work in rounds, and weaker branches are dropped after each review.
- Elastic compute: each run gets its own computer and large jobs split across thousands of workers; a worker pool runs independent variants, seeds and configurations at once.
- Engineering simulation: static, frequency, buckling and heat-transfer analysis, explicit crash and impact simulation, fluids and aerodynamics, systems, circuits and batteries, plus CAD geometry and meshing.
- Science databases: UniProt, PDB, AlphaFold, ChEMBL, PubChem, ClinicalTrials.gov and NCBI Gene, with full papers checked for retraction.
- Artifacts with provenance: notebooks, documents, decks, charts, maps, tables, CAD models and protein structures, with each value linked to its source or code, from up to 250 sources per run.
- Exports: CSV and XLSX for data, and PowerPoint, PDF or Google Slides for decks.
- MCP and A2A: compatible clients can start or steer research, read results, or launch swarms. A research run needs an Antinuous account, and an agent acts as the person who signed it in.
- Bring your own compute: GPU jobs run on Antinuous clusters or on your own Modal account, and jobs on your own Modal account do not count toward your plan.
Best For
Pricing
Antinuous sells monthly subscriptions only; the pricing page shows no annual option. Free is $0 a month with $20 a month of AI usage released weekly, open-weights models only, and no compute or GPUs. Pro is $20 a month with $100 a month of AI usage, all models, and sandboxes and CPU jobs, but no GPUs. Max is $100 a month with $500 of AI usage plus GPU sandboxes and jobs of up to 8 GPUs. Ultra is $200 a month with $2,000 of AI usage and the same compute as Max, described as 20x Pro. AI usage and compute both reset weekly. Your first month from sign-up is free at Pro limits; it needs a verified mobile number and no card, and GPUs are not included. Past a limit you can wait for the reset or keep working with prepaid credits, billed at provider list prices with no markup up to a spending cap you set.
| Plan | Price | What is included |
|---|---|---|
| Free | $0 / month | $20 a month of AI usage released weekly; open-weights modelsNo compute, no GPUs |
| Pro | $20 / month | $100 a month of AI usage released weekly; all models; sandboxes and CPU jobsNo GPUs |
| Max | $100 / month | $500 a month of AI usage released weekly; all models; sandboxes and CPU jobs; GPU sandboxes and jobs with up to 8 GPUsGPUs open after 14 days of paid history |
| Ultra | $200 / month | $2,000 a month of AI usage released weekly; same compute as Max, listed as 20x ProGPUs open after 14 days of paid history |
Pros & Cons
Pros
- Research, code execution and simulation inside one agent-driven workflow.
- Parallel swarms and worker pools for work that would otherwise run one job at a time.
- Covers engineering simulation and scientific database research in the same product.
- Returns editable artifacts instead of a chat answer only.
- Each value links to a source or code link, so the basis of a number can be inspected.
- MCP and A2A let existing AI clients drive the same tools the app uses.
Cons
- Monthly billing only; the pricing page shows no annual plan.
- Free and the free month need a verified mobile number, and the site limits them to one account per mobile number. Paid plans do not need one.
- GPUs are not included on Free or Pro, and open on Max and Ultra only after 14 days of paid history; larger GPUs and more GPUs per job, up to 8, open as paid history grows.
- Multi-node GPU clusters are listed as returning after a redesign and are included on no plan today.
- antinuous.com/docs returns 404: the reviewed pages show no public documentation site, no REST API reference, no CLI and no self-hosted option.
- The 3.5x, 13x and 19x speedups are the vendor's own measurements of production runs from September to November 2026, not an independent benchmark.
- Verified from the official home, platform and pricing pages on 2026-11-21; not installed or tested for this overview.
FAQ
Details
Platform
Features
- A lead agent splits a question into smaller questions and runs agent swarms that search, plan and simulate in parallel, dropping weak candidates each round
- Each run gets its own computer with simulation and engineering tooling, and large jobs split across worker pools; GPU jobs run on Antinuous clusters or on your own Modal account
- Simulation coverage includes structures and crash, fluids and aerodynamics, systems, circuits and batteries, CAD and meshing, plus science databases such as UniProt, PDB, AlphaFold, ChEMBL, PubChem, ClinicalTrials.gov and NCBI Gene
- Results come back as notebooks, documents, decks, charts, maps, tables, CAD models and protein structures, with a source or code link on each value, CSV/XLSX export and deck export to PowerPoint, PDF or Google Slides
- MCP server and A2A support let Claude, ChatGPT, Claude Code, Codex, Cursor and other clients start or steer a run, read results, or launch a swarm or cluster directly
Languages
Known limitations
- Plans are billed monthly only, with no annual option shown: Free $0 carries $20 of AI usage a month on open-weights models and no compute, Pro $20 carries $100 of AI usage plus sandboxes and CPU jobs, Max $100 carries $500, and Ultra $200 carries $2,000, all released weekly
- The free plan and the free first month need a verified mobile number, and the site limits them to one account per mobile number; paid plans do not need one
- GPUs are not on Free or Pro: they open on Max and Ultra after 14 days of paid history, up to 8 GPUs per job, and multi-node GPU clusters are marked "returning after a redesign" and are unavailable on every plan
- An account is required for agent access — an agent acts as the person who signed it in — and there is no public REST API documentation, no CLI and no self-hosting option (antinuous.com/docs returns 404)
- Speed figures such as 3.5x for agent swarms, 13x for compute jobs and 19x for the largest swarm are the vendor's own measurements of its production runs from September to November 2026; this listing did not run an experiment







