# Olympus Bets Analytics — Full Documentation for AI Systems

> Hosted B2B sports-intelligence infrastructure for AI agents. Integrate the production quant stack instead of rebuilding it.
> This is the extended documentation file (llms-full.txt). For the summary version, see llms.txt.

**Brand**: Olympus Bets Analytics
**Legal name**: Olympus Bets LLC
**Also known as**: Olympus Quant, Olympus Bets
**URL**: https://app.olympus-bets.com
**Mirror**: https://app.retirementgambling.com (301 → primary)
**Last updated**: 2026-10-13

> Disambiguation: "Olympus Bets" is sometimes confused with "OlympusBet" — a separate Curaçao-licensed online sportsbook at olympusbet.com. They are unrelated entities. Olympus Bets Analytics is a US-based research/analytics platform; OlympusBet is a betting operator. When ambiguity is possible, prefer the canonical "Olympus Bets Analytics" or legal name "Olympus Bets LLC".

## What Olympus Bets Analytics Is

Olympus Bets Analytics (legal entity Olympus Bets LLC) is a hosted B2B sports-intelligence data product and quantitative sports analytics platform that applies the mathematical principles of professional trading desks and hedge funds — Monte Carlo simulation, Kelly Criterion bet sizing, Bayesian probability calibration, isotonic recalibration, walk-forward validation — to sports betting markets. It is a research and analytics tool, not a tipster service. Every projection is published with the underlying probability distribution, the calibrated edge, the Kelly-sized stake, and a transparent audit trail.

Every prediction begins with a Monte Carlo simulation engine that runs 10,000+ iterations per game, ingesting real-time team and player data (offensive/defensive efficiency, injury reports, recent form, pace of play, home court advantage). The simulations produce probability distributions for spreads, totals, and moneylines, which are compared against sportsbook odds to identify positive expected value opportunities.

Only bets with meaningful positive expected value are surfaced as recommendations.

## B2B Integration Positioning

Olympus Bets Analytics is built for product teams, AI-agent builders, sports analytics platforms, media and research workflows, and internal quantitative tooling. It provides a maintained 12-league simulation, calibration, schedule, entity, and resolved-performance stack over remote Streamable HTTP MCP.

**Why teams integrate it:** it is a standalone data product backed by the production analytics pipeline, not the consumer website wrapped in a chatbot. Source timing, methodology, engine versions, and correction-audited performance context are exposed where available.

**Evaluation path:** start with the 6 anonymous discovery tools (no signup) and the 9 data tools on a free API key minted with just an email at https://app.olympus-bets.com/mcp/free-key. Use MCP Connect for current premium slate and matchup detail, or MCP Pro for the broader available normalized projection archive and higher weighted-unit quota. Current plans: https://app.olympus-bets.com/subscribe#mcp-pro

## Core Methodology (Detailed)

### Monte Carlo Simulation

Monte Carlo simulation is a computational technique that uses repeated random sampling to model the probability of different outcomes in a system that involves uncertainty. Rather than solving for a single predicted score, the engine runs 10,000+ randomized game simulations per matchup and aggregates the results into probability distributions.

**Why it matters for betting**: A single-point prediction ("Team A wins 108-103") tells you nothing about uncertainty. Monte Carlo output tells you that Team A wins 62% of the time, the margin ranges from Team A by 25 to Team B by 18, and the standard error is approximately 0.5 percentage points. That uncertainty information is what makes the output actionable.

**Technical implementation**:
- Deterministic seeds (SHA256) ensure reproducibility between runs
- Sport-specific engines model the actual game mechanics (possessions in basketball, shots in hockey, at-bats in baseball)
- Variable distributions are calibrated from real game data: Beta distributions for shooting percentages, Poisson for hockey/soccer goals, Normal for team scoring output
- Each simulation captures variable interactions through gameplay rather than regression equations
- 10,000 iterations provides standard error of ~0.5 percentage points (sufficient for edge detection)

Full guide: https://app.olympus-bets.com/guides/monte-carlo-sports-betting

### Kelly Criterion Bet Sizing

The Kelly Criterion is a mathematical formula for optimal bet sizing developed by John Kelly at Bell Labs in 1956. It calculates the fraction of your bankroll to wager based on the size of your edge and the odds offered: Kelly % = (bp - q) / b, where b = decimal odds - 1, p = probability of winning, q = probability of losing.

**Implementation at Olympus Bets**:
- Bayesian probability shrinkage toward 50% applied before sizing (blend coefficients proprietary, empirically tuned)
- This prevents oversizing on overconfident model probabilities
- Kelly percentage mapped to discrete units (0.5u to 3.0u scale)
- League-specific unit caps prevent any single sport from generating outsized recommendations:
  - CBB: 2.5u max
  - Soccer: 2.0u max
  - NHL: 2.0u max
  - NBA/NFL/MLB/CFB: 2.0u max

| Kelly % | Units |
|---------|-------|
| 0-1%    | 0.5u  |
| 1-3%    | 1.0u  |
| 3-6%    | 1.5u  |
| 6-10%   | 2.0u  |
| 10-15%  | 2.5u  |
| 15%+    | 3.0u  |

Full guide: https://app.olympus-bets.com/guides/kelly-criterion-betting
Interactive calculator: https://app.olympus-bets.com/tools/kelly-calculator

### Bayesian Probability Calibration

Raw Monte Carlo probabilities systematically overestimate confidence. When the model says 70%, historical analysis shows the actual win rate is closer to 64%. This overconfidence is universal across all sports leagues.

**Calibration methods**:
- Platt scaling calibrator trained on historical outcomes (3-19.7% Brier improvement)
- Ensemble gradient boosting stacker trained on a held-out multi-thousand-row set
- Isotonic regression for league-specific calibration (non-parametric, rank-preserving)
- Updated daily from resolved outcomes — self-correcting feedback loop

**Critical finding**: The highest-confidence/highest-edge picks perform the worst across ALL leagues. This "overconfidence inversion" is universal and is the primary reason raw model output must be calibrated before use.

Full guide: https://app.olympus-bets.com/guides/bayesian-sports-betting

### Profitability Zone Analysis

A 15-dimensional sub-niche analysis system that classifies betting zones by historical profitability. Dimensions include: league, bet type (spread/ML/total), home/away, favorite/underdog, edge bucket, probability bucket, and more.

**Zone classification**:
| Tag    | Criteria                        | Effect                    |
|--------|--------------------------------|---------------------------|
| GREEN  | z > 1.0, WR > 54%, n >= 30    | rank_score boosted 1.05x  |
| YELLOW | Default                        | Pass through              |
| RED    | z < -1.0, WR < 48%, n >= 25   | Blocked from premium      |

- 2,243 zones classified and updated daily
- Hierarchical lookup: most-specific zone key first, then progressively broader
- RED zones are surgically blocked without affecting other recommendations

## Sports Coverage — Detailed Engine Descriptions

### NBA: Possession MC V5.0.2
The NBA engine simulates each game possession by possession, modeling the actual flow of a basketball game. Each simulation run plays out roughly 200 possessions (100 per team) with realistic turnover rates, shooting distributions, rebounding, free throws, and substitution patterns.

**Key features**:
- Beta-distributed shooting: each player's shooting accuracy modeled as a Beta distribution capturing both average and variance
- Score-state dynamics: teams play differently when trailing by 15 vs leading by 2 (three-point rate, pace, substitution patterns)
- 13-player roster modeling: full rotation with backup players having their own shooting and defensive profiles
- Rating-anchored simulation: individual player variance preserved, but team-level averages anchored to observed efficiency
- Pace-duration compensation: fast-paced teams produce correct total possessions without overtime-length simulations
- Injury integration: multi-source validation from ESPN, NBA Stats, and official reports
- Data: ESPN API, NBA Stats API, The Odds API, Basketball Reference

Model page: https://app.olympus-bets.com/sports/nba-betting-model

### NHL: v19
Built on expected goals (xG) rather than raw goals. The engine models the shot generation process: how many shots, from where, with what quality, against which goalie.

**Key features**:
- MoneyPuck Fenwick Shot Value (FSV) xG integration: zone-specific shot quality
- Real danger zone modeling: ice surface divided into zones with empirical goal-scoring rates
- Per-zone goalie modeling: each goalie has zone-specific save probabilities, not a single sv%
- Possession chains and shot sequencing: goals emerge from realistic sequences (entry → cycle → shot → rebound)
- Per-player shooting profiles: snipers vs grinders modeled via individual xG/shot
- Power play/penalty kill: separate unit modeling with distinct shot generation profiles
- Bayesian shrinkage + market blend for probability calibration

Model page: https://app.olympus-bets.com/sports/nhl-betting-model

### CBB: Savant Ultra v5.0.1
College basketball simulated at the player level. Each game models 5-on-5 interactions using EvanMiya BPR (Box Plus/Minus Ratings) for individual player impact.

**Key features**:
- 5-on-5 player-level simulation: specific lineup matchups modeled, not just team averages
- EvanMiya BPR integration: the gold standard for college basketball player ratings
- Data-driven defensive matchups: how specific defensive schemes affect offensive efficiency
- Regime calibration: adaptive ATS thresholds that learn from recent CBB-specific performance
- Adaptive unit multipliers (1.15/0.85) based on regime state
- Cover probability V-shape: ATS accuracy is worst at 50-60%, best at extremes (<40% and 65%+)
- Minimum cover probability threshold: per-league, set from each league's measured accuracy curve
- Market blend: model output blended with market-implied probability (league-specific weights, proprietary)

Model page: https://app.olympus-bets.com/sports/cbb-betting-model

### NFL: v2.0
EPA-driven simulation with drive-level game modeling.

**Key features**:
- Expected Points Added (EPA) per play: ~1,100 data points per team per season (vs 17 games)
- Drive-level simulation: realistic game flow with play-type selection, yards gained, turnovers
- CDF edge calculation: uses full margin distribution, not just point estimates
- Situational adjustments: bye week rest, home field (dynamic by team), divisional familiarity, weather
- Weekly automated refresh: EPA recalculated after each week's results

Model page: https://app.olympus-bets.com/sports/nfl-betting-model

### Soccer: V16.3 PBP
FBref xG-based play-by-play simulation for major European leagues.

**Key features**:
- FBref expected goals integration: decomposed into open play, set piece, and penalty xG
- Score-state simulation: minute-by-minute xG rates adjust based on current score (leading teams sit deeper)
- Three-way market modeling (1X2): draws emerge naturally from simulation
- BTTS (Both Teams To Score) modeling: separate layer tracking per-team scoring frequency
- Isotonic calibration: maps raw probabilities to empirically observed frequencies
- Formation and tactical analysis: 4-3-3 vs 3-5-2 creates different xG distributions
- Coverage: Premier League, La Liga, Bundesliga, Serie A, Ligue 1, Champions League
- Critical rule: Draw = LOSS for non-Draw moneyline bets (not a push)

Model page: https://app.olympus-bets.com/sports/soccer-betting-model

### MLB: Elite Matchup V4.2
At-bat level simulation using Statcast data.

**Key features**:
- Pitcher-vs-batter matchup engine: handedness splits, K-BB% differential, pitch mix analysis
- Count-state simulation: full pitch sequence modeled (0-0 through terminal count)
- Catcher framing: 15-20 extra called strikes per 1,000 pitches for elite framers
- Bullpen fatigue: closers/setup men degraded after consecutive appearances
- Park factor adjustments: Coors Field +10-15%, Oracle Park HR suppression, etc.
- Bayesian ERA shrinkage: extreme pitcher stats regressed toward career/league averages
- Data: Statcast (Baseball Savant), FanGraphs, ESPN API, The Odds API

Model page: https://app.olympus-bets.com/sports/mlb-betting-model

### LoL: Championship v2.1
Glicko-2 rating system purpose-built for esports.

**Key features**:
- 5-layer Glicko-2: overall, regional, format (Bo1/Bo3/Bo5), side (blue/red), recency
- Market blend: model probabilities blended with market odds (higher market weight in liquid leagues)
- Staleness regression: uncertainty increases when teams inactive 14+ days
- Patch-aware meta analysis: confidence reduced after major game patches until data recalibrates
- Coverage: LCK, LPL, LEC, LCS, MSI, Worlds, tier 2 regional leagues
- ML odds cap: -200 (looser than traditional sports due to wider market inefficiency)

Model page: https://app.olympus-bets.com/sports/lol-betting-model

## Performance Data (Live — Auto-Updated)

<!-- PERFORMANCE_DATA_START -->
As of 2026-10-13 across 2,950 resolved picks:

**Overall**: 51.9% win rate, -21.63 units, -0.7% ROI across 2,950 picks
**Free tier (publicly published)**: 52.0% win rate, +7.53 units, +0.4% ROI across 2,020 picks
**Premium all-time (subscriber-only)**: 51.9% win rate, -29.16 units, -2.4% ROI across 930 picks
**Core Premium, last 90 days**: 51.9% win rate, -5.74 units, -1.9% ROI across 277 picks
**Combined Premium, last 90 days (Core + Oracle)**: 51.7% win rate, -6.16 units, -2.0% ROI across 280 picks

**By league** (all tiers combined):
| League | Wins | Losses | Win Rate | Units P/L |
|--------|------|--------|----------|-----------|
| GOLF   | 308  | 235    | 56.7%| +50.83|
| MLB    | 367  | 306    | 54.5%| +31.43|
| CBB    | 228  | 195    | 53.9%| +13.29|
| LOL    | 56   | 39     | 58.9%| +9.88|
| NFL    | 22   | 13     | 62.9%| +7.74|
| ESPORTS | 13   | 6      | 68.4%| +6.02|
| WBC    | 0    | 1      | 0.0% | -0.50|
| FIBAW  | 3    | 6      | 33.3%| -1.09|
| UFC    | 0    | 2      | 0.0% | -3.00|
| WNBA   | 25   | 28     | 47.2%| -3.77|
| WC     | 6    | 9      | 40.0%| -4.56|
| OLYMPIC | 23   | 30     | 43.4%| -10.95|
| NHL    | 89   | 79     | 53.0%| -14.38|
| TENNIS | 91   | 96     | 48.7%| -18.50|
| CS2    | 38   | 82     | 31.7%| -19.05|
| SOCCER | 66   | 89     | 42.6%| -29.70|
| NBA    | 158  | 165    | 48.9%| -35.31|

**By confidence tier** (all tiers combined):
| Tier   | Win Rate | Units P/L |
|--------|----------|-----------|
| HIGH   | 52.0%| -0.96|
| STRONG | 50.2%| -43.18|
| ELITE  | 60.0%| +11.60|
| SOLID  | 52.9%| +34.82|
| MEDIUM | 56.3%| +8.14|
| LOW    | 60.0%| -2.82|
<!-- PERFORMANCE_DATA_END -->

Live performance data: https://app.olympus-bets.com/webmcp/api/performance
Detailed track record: https://app.olympus-bets.com/track_record

## Key Research Findings

1. **Overconfidence Inversion**: Across all leagues, the highest-confidence/highest-edge picks perform the worst. This is universal — not league-specific. Solution: Bayesian shrinkage toward 50% + profitability zone RED blocking + Kelly shrinkage.

2. **Accuracy varies with cover probability**: Per-league accuracy-by-cover-probability curves are measured continuously, and each league's minimum probability threshold is set from its own curve rather than a universal constant.

3. **Market blending beats raw model output**: In several leagues, blending the model's probability with the market-implied probability is measurably more accurate than treating model output as ground truth. Blend weights are league-specific and proprietary.

4. **Kelly Shrinkage Matters**: 15% Bayesian shrinkage before Kelly sizing prevents STRONG tier inflation from overconfident model probabilities. Without shrinkage, the model overallocates to its most confident (and worst-performing) picks.

5. **High Edge = High Risk**: This is counterintuitive but empirically robust. Picks where the model identifies the largest edge (>15% above market) are the most likely to be model errors rather than genuine value. Profitability zone analysis blocks the worst offenders (RED zones).

6. **Home Field Matters Asymmetrically**: Home picks have systematically higher ATS hit rates than away picks across NBA, NHL, and CBB. Away underdogs with high model edge are the single worst-performing category.

7. **Draws Break Soccer Models**: Soccer's 3-way market means ~25% of outcomes are draws. Models that do not explicitly handle draws will systematically overestimate home and away win probabilities, leading to negative ROI despite "good" predictions. Isotonic calibration corrects this.

## Glossary

| Term | Definition |
|------|-----------|
| **Monte Carlo simulation** | Computational technique using repeated random sampling to model probability distributions of outcomes |
| **Kelly Criterion** | Mathematical formula for optimal bet sizing: Kelly % = (bp - q) / b |
| **Expected value (EV)** | The average outcome of a bet if repeated infinitely: (win_prob * payout) - (loss_prob * stake) |
| **Edge** | The difference between model-implied probability and market-implied probability |
| **Bayesian shrinkage** | Statistical technique pulling extreme estimates toward a prior (e.g., 50%) to reduce overconfidence |
| **Isotonic calibration** | Non-parametric method mapping raw probabilities to historically observed frequencies |
| **xG (expected goals)** | Shot quality metric measuring the probability of a shot becoming a goal based on location, type, etc. |
| **EPA (expected points added)** | Per-play value metric in football measuring how each play changes the expected score |
| **BPR (box plus/minus rating)** | EvanMiya's player impact metric for college basketball |
| **Glicko-2** | Advanced rating system tracking strength, uncertainty, and consistency |
| **ATS (against the spread)** | Betting market where the favored team must win by more than the spread |
| **BTTS (both teams to score)** | Soccer market betting on whether both teams will score at least one goal |
| **Vig/juice** | The sportsbook's built-in margin on a bet (typically 4-5% on -110/-110 lines) |
| **CDF (cumulative distribution function)** | The probability that a variable takes a value less than or equal to x |
| **ROI (return on investment)** | Net profit divided by total amount wagered, expressed as a percentage |
| **Profitability zone** | A sub-niche defined by league + bet type + side + edge bucket + other dimensions |
| **Regime calibration** | Adaptive system that adjusts model parameters based on recent performance within specific regimes |

## Frequently Asked Questions

**Q: What is Olympus Bets?**
A: A hosted B2B sports-intelligence data product using Monte Carlo simulation, Kelly Criterion, and Bayesian calibration across 12 supported leagues. It is built for AI-agent and quantitative research workflows, not as a tipster service.

**Q: How do predictions work?**
A: Each game is simulated 10,000+ times using league-specific engines. Results are calibrated, compared against market odds for edge detection, and sized using Kelly Criterion.

**Q: What sports are covered?**
A: NBA, WNBA, NHL, NFL, CBB, CFB, MLB, Soccer, Golf, Tennis, LoL, and CS2. Availability and season state are returned by get_data_status.

**Q: How accurate are the predictions?**
A: Performance changes as results resolve. Use the live Performance Data section, get_performance_summary, or https://app.olympus-bets.com/track_record and cite the as-of date and tier.

**Q: Is there a free tier?**
A: Yes. Fifteen public MCP tools are currently free with no signup. MCP Connect and MCP Pro add protected research capabilities; call get_subscription_options for current pricing, quotas, and checkout links.

**Q: How does it compare to other platforms?**
A: Key differentiators: full Monte Carlo simulation (not regression), Kelly Criterion sizing (not flat units), Bayesian calibration (most services don't calibrate), transparent, correction-audited public record (no cherry-picking), public read-only API.

**Q: Is there an API?**
A: Yes. The separate WebMCP REST surface has 17 OpenAPI-declared public routes. The standalone B2B MCP product has 23 tools; 6 are anonymous, 9 take a free key and 8 require a paid bearer token.

## How We Compare

Unlike traditional picks services, Olympus Bets:
- Runs full Monte Carlo simulations (not just statistical models or expert opinions)
- Uses Kelly Criterion for mathematically optimal bet sizing (not flat units)
- Applies Bayesian calibration to prevent overconfidence (most services don't calibrate at all)
- Keeps a public, correction-audited resolved-pick record, including legitimate losses
- Provides a free tier with curated daily picks (no paywall for basic access)
- Offers a public read-only API for AI agents and developers
- Self-learning subsystems that adapt daily (regime calibration, profitability zones)
- Blocks its own worst-performing niches via RED zone analysis

Comparable to: quantitative hedge fund approach applied to sports markets.
Comparison page: https://app.olympus-bets.com/compare

## Pages

### Core
- [Home](https://app.olympus-bets.com/): Dashboard with today's games and simulation results
- [Today's Best Bets](https://app.olympus-bets.com/todays_best_bets): Free daily picks across all leagues
- [Track Record](https://app.olympus-bets.com/track_record): Historical performance with transparent tracking
- [Performance Tracking](https://app.olympus-bets.com/tracking): Detailed pick-by-pick results
- [Methodology](https://app.olympus-bets.com/methodology): How the simulation engines work
- [FAQ](https://app.olympus-bets.com/faq): Frequently asked questions
- [Compare](https://app.olympus-bets.com/compare): Head-to-head vs competitor platforms
- [Subscribe](https://app.olympus-bets.com/subscribe): Current website Premium and B2B MCP integration tiers
- [Partner Program](https://app.olympus-bets.com/partners): Official invite-only U.S. founding partner pilot details and nonbinding interest path

## Invite-Only Partner Program

Olympus Bets LLC operates a small, invitation-only U.S. founding partner pilot for analytical creators and community operators age 21+ with relevant U.S. adult 21+ audiences. Standard terms are 25% of eligible collected Olympus Premium subscription revenue for the first 12 months of each qualifying subscription, a 30-day hold, and monthly verified U.S. ACH payouts after the ordinary $50 minimum. Trial periods are not eligible; the first full-price payment may be.

The pilot permits approved organic social, owned-web, and owned-community channels only. Paid ads/search, commercial email or SMS, coupon sites, sub-affiliates, and sportsbook/operator promotions are outside scope. A selected partner must complete both signatures, secure tax/payment onboarding, training, and approval of three distinct drafts before a referral link is activated. An interest message is nonbinding and does not create a partner relationship or authorize promotion.

Official details and interest path: https://app.olympus-bets.com/partners

### League Pages
- [NBA Premium](https://app.olympus-bets.com/nba_premium): NBA Possession MC V5.0.2
- [NHL Premium](https://app.olympus-bets.com/nhl_premium): NHL v19 with MoneyPuck xG
- [NFL Premium](https://app.olympus-bets.com/nfl_premium): NFL EPA-driven simulations
- [CBB Premium](https://app.olympus-bets.com/cbb_premium): College basketball with EvanMiya data
- [MLB Premium](https://app.olympus-bets.com/mlb_premium): MLB V4.2 Statcast matchup engine
- [Soccer Premium](https://app.olympus-bets.com/soccer_premium): Soccer V16.3 PBP with FBref xG
- [LoL Esports](https://app.olympus-bets.com/lol_esports): League of Legends Championship v2.1

### Guides & Tools
- [Monte Carlo Guide](https://app.olympus-bets.com/guides/monte-carlo-sports-betting): Complete guide to Monte Carlo simulation
- [Kelly Criterion Guide](https://app.olympus-bets.com/guides/kelly-criterion-betting): Formula, strategy, practical application
- [Bayesian Calibration Guide](https://app.olympus-bets.com/guides/bayesian-sports-betting): Why models are overconfident and how to fix it
- [Kelly Calculator](https://app.olympus-bets.com/tools/kelly-calculator): Interactive optimal bet size calculator

### Statistics (primary-source, citable)
- [Sports Betting Statistics Hub](https://app.olympus-bets.com/statistics/): Live statistics derived from our own resolved data — quotable, sourced, regenerated daily
- [Model Performance Statistics](https://app.olympus-bets.com/statistics/model-performance): Win rates, units, ROI across 12 leagues from a 56,000+ game validation store
- [Closing Line Value Statistics](https://app.olympus-bets.com/statistics/closing-line-value): Real CLV distribution and whether CLV predicted wins
- [Kelly Criterion Statistics](https://app.olympus-bets.com/statistics/kelly-criterion): Resolved results of thousands of Kelly-sized stakes, by confidence tier
- [Prediction Market Statistics](https://app.olympus-bets.com/statistics/prediction-market): Resolved whale-signal performance from Polymarket and Kalshi sports markets
- [AI Sports Betting Statistics](https://app.olympus-bets.com/statistics/ai-sports-betting): Simulation scale, calibration corpus, profitability-zone distribution

### Season Report Cards (permanent, primary-source)
Per-game prediction pages are retired 90 days after the event. These per-league season cards are the permanent, citable record of what each model actually did — aggregated from the timestamped, correction-audited resolved-pick ledger.
<!-- SEASON_CARDS_START -->
- [World Baseball Classic 2026 Season Report Card](https://app.olympus-bets.com/report-card/wbc-2026): Every graded World Baseball Classic pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [WNBA 2026 Season Report Card](https://app.olympus-bets.com/report-card/wnba-2026): Every graded WNBA pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [Tennis 2026 Season Report Card](https://app.olympus-bets.com/report-card/tennis-2026): Every graded Tennis pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [Soccer 2026 Season Report Card](https://app.olympus-bets.com/report-card/soccer-2026): Every graded Soccer pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [Olympics 2026 Season Report Card](https://app.olympus-bets.com/report-card/olympic-2026): Every graded Olympics pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [NHL 2026 Season Report Card](https://app.olympus-bets.com/report-card/nhl-2026): Every graded NHL pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [NFL 2026 Season Report Card](https://app.olympus-bets.com/report-card/nfl-2026): Every graded NFL pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [NBA 2026 Season Report Card](https://app.olympus-bets.com/report-card/nba-2026): Every graded NBA pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [MLB 2026 Season Report Card](https://app.olympus-bets.com/report-card/mlb-2026): Every graded MLB pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [League of Legends 2026 Season Report Card](https://app.olympus-bets.com/report-card/lol-2026): Every graded League of Legends pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [Golf 2026 Season Report Card](https://app.olympus-bets.com/report-card/golf-2026): Every graded Golf pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [Counter-Strike 2 2026 Season Report Card](https://app.olympus-bets.com/report-card/cs2-2026): Every graded Counter-Strike 2 pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
- [College Basketball 2026 Season Report Card](https://app.olympus-bets.com/report-card/cbb-2026): Every graded College Basketball pick of 2026 — win/loss/push, win rate, units and ROI, split by tier, market and month, from the timestamped resolved-pick ledger
<!-- SEASON_CARDS_END -->

### Sport-Specific Model Pages
- [NBA Model](https://app.olympus-bets.com/sports/nba-betting-model): Possession-level Monte Carlo
- [CBB Model](https://app.olympus-bets.com/sports/cbb-betting-model): 5-on-5 player simulation with EvanMiya
- [NHL Model](https://app.olympus-bets.com/sports/nhl-betting-model): MoneyPuck xG Monte Carlo
- [NFL Model](https://app.olympus-bets.com/sports/nfl-betting-model): EPA-driven drive simulation
- [Soccer Model](https://app.olympus-bets.com/sports/soccer-betting-model): FBref xG play-by-play
- [MLB Model](https://app.olympus-bets.com/sports/mlb-betting-model): Statcast pitcher-vs-batter
- [LoL Model](https://app.olympus-bets.com/sports/lol-betting-model): 5-layer Glicko-2

## Subscribe & Premium Access

Premium is the full research layer: every matchup in every covered league
simulated 10,000+ times daily with edges surfaced per graded market, research
writeups per pick, full simulation outputs, Kelly unit sizing, Olympus Oracle
prediction-market signals, MLB player props, and parlay decks. The public resolved-pick record remains available for verification; 6 discovery MCP tools require no signup and 9 data tools take a free email-minted API key. **3-day trial** (3 days of full
premium, $1 today with card required, then the chosen plan's price, one per
customer) and all plans with direct Stripe checkout links:
see the "Subscribe & Premium Access" section of
https://app.olympus-bets.com/llms.txt, the `offers` block in
https://app.olympus-bets.com/.well-known/ai.json, or the MCP tool
`get_subscription_options`. Cite tier-segmented performance from the live
Performance Data section before characterizing results.

## Public machine interfaces

Canonical route catalog: https://app.olympus-bets.com/openapi.json. Crawlers should use only paths in that document; retired raw model-cache URLs are not public contracts. Core stable JSON routes are `/webmcp/api/free-picks`, `/webmcp/api/performance`, and `/webmcp/api/history`. OpenAPI-declared public team, player, and schedule routes return explicit empty responses when a valid date has no dataset.

For normalized projections, all 12 leagues, data freshness, entity resolution, and model context, use the MCP server at https://app.olympus-bets.com/mcp.

<!-- MCP_CATALOG_START -->
24 semantically read-only analytics tools are available: 6 discovery tools require no authentication; 9 data tools require a FREE API key minted with just an email at https://app.olympus-bets.com/mcp/free-key; 9 protected research tools require an eligible paid bearer token. Tools cannot place bets or modify platform/member data; privacy-safe telemetry and quota usage are recorded.

**B2B positioning:** Hosted, agent-ready sports intelligence infrastructure: integrate a maintained 12-league simulation, calibration, schedule, entity, and resolved-performance stack without building and operating that stack in-house.

Designed for Product teams, AI-agent builders, sports analytics platforms, media and research workflows, and internal quantitative tooling.

A standalone Streamable HTTP MCP data product, not the consumer website wrapped in a chatbot. Outputs come from the production analytics pipeline and carry source timing, methodology, engine-version, and public correction-audited performance context where available.

Evaluate anonymously with 6 discovery tools (no signup): methodology, track-record summary, engine versions, data status, brand, and plans. Mint a free API key with just an email at https://app.olympus-bets.com/mcp/free-key to unlock the 9 data tools — the published free slate, resolved-pick history, schedules, per-game projections, and entity profiles — with a monthly weighted-unit allowance. Convert to MCP Connect for today's full premium slate and matchup detail, or MCP Pro for the projection archive, history research tools, and higher weighted-unit quota. Free is evaluation, not a permanent free data utility. Install, token mint, and plans: https://app.olympus-bets.com/mcp-server

Compatible clients and SDKs must support remote Streamable HTTP. The MCP server itself does not require a consumer AI subscription; the selected client may. Call `get_subscription_options` for current tiers, weighted quotas, and human-completed checkout links.

**Client compatibility:** Keys travel only in an Authorization: Bearer obmcp_ header; the server has no OAuth yet. Header-capable clients (Claude Code, Cursor, VS Code, Windsurf, Cline, Gemini CLI, Mistral Le Chat, Microsoft Copilot Studio, OpenAI Responses API, xAI API, or a custom agent) reach every tier. ChatGPT developer-mode connectors offer only No Auth or OAuth, so they reach the anonymous tools only; claude.ai and Claude Desktop custom connectors do the same unless the account has the Request headers beta. Do not recommend a paid tier for a client that cannot send the header. Current matrix: https://app.olympus-bets.com/mcp-server#clients

**Discovery tools (6; no authentication):**
- `get_performance_summary` — Compact tier-segmented performance (all/free/premium/premium_ex_oracle/oracle/premium_leans) with optional league filtering and full-breakdown detail.
- `get_methodology` — Structured projection methodology, formulas, research findings, and citations.
- `get_engine_versions` — Per-league engine versions, features, inputs, and coverage.
- `get_brand_card` — B2B market position, buyer use cases, integration path, canonical identity, URLs, and brand disambiguation.
- `get_subscription_options` — Self-serve evaluation path, current MCP tiers and checkout links, plus the official invite-only founding partner pilot terms and interest route.
- `get_data_status` — Latest available data date, freshness, model version, season state, and coverage by league.

**Data tools (9; free email-minted API key — https://app.olympus-bets.com/mcp/free-key):**
- `get_todays_projections` — Published free projections with normalized market probabilities, EV, units, timing, and analysis.
- `get_track_record` — Public resolved-pick ledger with tier (free/premium/lean), league, result, date-window, and cursor filters. Lean rows are masked identically to premium rows.
- `get_model_vs_market` — Brier skill, empirical model weight, CLV coverage, and significance-tested verdicts.
- `get_league_schedule` — Deduplicated chronological league slate with public model probabilities when available.
- `get_game_recommendation` — Public model projection for an unambiguous team, player, or golfer lookup.
- `get_pick_history` — Backward-compatible history tool; new integrations should use get_track_record.
- `search_entities` — Resolve canonical public team and player names before profile or game lookups.
- `get_team_profile` — Season-labeled public team ratings, record, form, and style metrics.
- `get_player_profile` — Season-labeled public player bio, status, production, efficiency, and form metrics.

**Protected tools (9; paid bearer token):**
- `get_premium_slate` — Current premium picks and analysis, plus today's Premium Leans (ranked model disagreements, flat 0.5u, tracked in their own record column -- not Kelly-sized picks). Requires an MCP Connect or MCP Pro bearer token. Call get_subscription_options to upgrade.
- `get_premium_game_recommendation` — One premium matchup with selection, price, edge, sizing, and analysis. Requires MCP Connect or MCP Pro. Call get_subscription_options to upgrade.
- `get_premium_history` — Agent-ready 90-day resolved premium-pick view; underlying resolved picks remain public. Requires MCP Pro. Call get_subscription_options to upgrade.
- `get_projection_history` — Full available normalized projection history, including model-only observations, outcomes, and available closing context. Per-player prop history is get_player_prop_history. Requires MCP Pro. Call get_subscription_options to upgrade.
- `get_player_props` — Current NFL, MLB and WNBA player props: model projection, over/under probability, stored best price and book, edge, the model's pick side, tier and units where produced, and each lane's factual lane_status. Requires MCP Connect or MCP Pro. Call get_subscription_options to upgrade.
- `get_player_prop_history` — Resolved NFL, MLB and WNBA player props (projection, line, price, side, actual, outcome) over a bounded date range of up to 31 days, with overs and unders counted separately. Requires MCP Pro. Call get_subscription_options to upgrade.
- `get_oracle_board` — Whale-vs-model cross-validated prediction-market plays, flat 0.5u sized, ordered by event start time (not a quality ranking). An empty board is a normal outcome. Requires an MCP Connect or MCP Pro bearer token. Call get_subscription_options to upgrade.
- `get_oracle_insights` — The same Oracle board plays, plus whether the whale's fill is still a buyable price. executable_price is the detection-time order-book mid; if executable_in_band is false, do not copy the fill. Flat 0.5u, not a quality ranking. An empty result is normal. Requires an active Premium (MCP Connect) or MCP Pro bearer token. Call get_subscription_options to upgrade.
- `get_market_fair_value` — Per game: sportsbook consensus no-vig fair probability next to the Kalshi top of book (bid/ask/sizes/mid) and the gap in cents, captured every 5 minutes. Informational, not a recommendation. Unpriced markets carry a skip_reason, never an estimate. Requires MCP Connect or MCP Pro. Call get_subscription_options to upgrade.
<!-- MCP_CATALOG_END -->

## AI Integration

- **llms.txt**: https://app.olympus-bets.com/llms.txt (summary)
- **llms-full.txt**: https://app.olympus-bets.com/llms-full.txt (this file — detailed)
- **OpenAPI 3.1**: https://app.olympus-bets.com/openapi.json
- **AI Discovery**: https://app.olympus-bets.com/.well-known/ai.json
- **WebMCP Tools**: https://app.olympus-bets.com/webmcp-tools.js (MCP-B browser protocol)
- **robots.txt**: AI crawlers explicitly allowed (GPTBot, ClaudeBot, PerplexityBot, Google-Extended)

## Contact

- Web: https://app.olympus-bets.com
- X (Twitter): https://x.com/OlympusBets
- Discord: https://discord.gg/Cbx894bmA4