Docs › MathLab › FAQ

Research Tiers: Haiku, Sonnet, Opus

June 16, 20261 min read

Three AI models, three capability levels. Haiku (free tier) is fast and capable for straightforward problems. Sonnet (Pro) adds deeper reasoning and longer context for complex proofs. Opus (Pro) is the most capable model — best for original research, multi-step proofs, and War Room sessions. Each tier shows its per-round cost upfront. Choose based on the difficulty of your problem.

MG
Matthew J. Goss, Jr.
Retired COMEX/NYMEX floor trader, Goldman Sachs and FlexTrade Systems alumnus, multi-instrumentalist, published author, and independent mathematics researcher. Founder of Quantiterate.