What is Octagon?
Octagon combines research reports with structured prediction-market data. Each report focuses on an event and compares an estimated probability with the market price. The broader workspace adds news, thematic baskets and a trust score, while developer interfaces let you incorporate the research into a custom process.
Who it is for
- Researchers who want cited event analysis
- Traders comparing a model view with market prices
- Developers adding research to agents or trading tools
Features and coverage
- Available on
- Web, API, MCP, CLI
- Markets & venues
- Polymarket, Kalshi
- Research topics
- Cited research, Model probabilities
- Event research
Read summaries, probability estimates and linked supporting sources.
- Model-price comparison
See the difference between the model estimate and market-implied probability.
- Research news
Follow market moves and open the report behind them.
- Trust Index
Inspect a score combining market integrity and trade quality.
- Thematic baskets
Review a thesis expressed through several sized Kalshi contracts.
- REST API
Search markets, inspect clusters and retrieve ranked edge data.
- MCP and SDK
Integrate research with compatible AI clients and agents.
- Trading CLI
Use the terminal workflow for research and supported trading actions.
Workflows with Octagon
Research a market
Open its report, inspect the cited evidence and compare the model estimate with the current contract price.
Review a basket
Read the thesis, check each contract’s rules and inspect how the legs are sized.
Integrate with an agent
Create an API key, choose MCP or REST and account for per-call credit use.
Pricing and total cost
Reports are publicly browsable. Paid API and agent access includes a 15-day trial.
Plus, annual billing
$17/month equivalent
- 200 credits/month
- Agent access
- MCP and API keys
Pro, annual billing
$41/month equivalent
- 600 credits/month
- Historical prediction-market reports
Enterprise
Custom
- Team access and customized workflows
Fees and usage costs
- 500 extra credits cost $50.
- Prediction-market agents use 3 credits/call; public-market agents use 1 and deep research uses 2.
Getting started
Before you start: The public site covers Polymarket and Kalshi, but several documented endpoints and basket workflows are Kalshi-specific.
- Browse a report for a market you follow.
- Inspect the sources and model-versus-price comparison.
- Choose a paid plan only for the access or volume you need.
- Create an API key or connect an MCP client.
- Track credit use by agent type.
Useful links
What to check
- The public site covers Polymarket and Kalshi, but several documented endpoints and basket workflows are Kalshi-specific.
- The displayed annual prices require annual billing.
- Basket backtests are hypothetical results, separate from executed account performance.
- Model edge is a disagreement with price, not an observed trading return.
A closer look
Ratings & reviews
User reviews 0
The main score switches to user ratings after 5 published reviews.
A specific example helps the next person choose the right tool.
Write a review
How was your experience with Octagon?
Share what you used, what worked and what could be better. We confirm your email and review the submission before publishing.
To submit a review, email info@polytradingbot.com with the tool name, your rating and your experience. Enable JavaScript to prepare a draft here.
Related tools
Browse categoryFrequently asked questions about Octagon
Can I read reports without subscribing?
Yes. Public report browsing is offered free.
What does edge mean here?
The model probability minus the market probability.
How many credits does a prediction-market call use?
Three credits.
Does Pro add historical reports?
Yes. That is one of its listed additions.


