Alternative · Cross-venue terminal
OkayBet vs
SimpleFunctions.
Same upstream prediction-market venues. OkayBet's product is consumer-facing aggregation with AI-assisted features and parlay betting construction. SimpleFunctions ships the agent layer above it: a causal-tree thesis system with auto-evaluation heartbeats, autonomous Portfolio Autopilot with a 7-gate risk cascade, computed indicators across 48K+ active contracts, and a 56-tool MCP server that drops into Claude Code or Cursor in one command.
Verified 2026-04 · public sources only · live SF data from /calibration
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
You are building agents, autonomous trading systems, or research that needs more than aggregated prices — calibrated probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation cycles, regime classification across the full 48K-contract universe, computed indicators (implied yield, cliff risk, liquidity availability score), and a 56-tool MCP server that integrates into Claude Code or Cursor in one command.
Choose OkayBet if
OkayBet's stated focus is consumer-facing prediction-market aggregation with parlay support — a workflow that differs from SF's programmatic, agent-first orientation. If your primary use case is building or exploring parlay positions across venues through an application layer, OkayBet targets that audience directly.
Same upstream venues (Kalshi + Polymarket). OkayBet layers on aggregation and parlay construction. SimpleFunctions ships the agent infrastructure above it: world model, theses, indicators, autopilot, MCP.
At a glance
Three things that
actually differ.
Everything OkayBet gives you — cross-venue market aggregation, AI-assisted features, and multi-venue coverage — SimpleFunctions also gives you, on the same Kalshi and Polymarket feeds.
On top of that, SF ships a causal-tree thesis system, an autonomous trading agent (Portfolio Autopilot, 1M-context LLM, 7-gate risk cascade), and 56 MCP tools that no current PM data product exposes.
SF also publishes live Brier scores for itself at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Most competitors claim accuracy; we let you check ours.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed and queryable at /api/public/cross-venue/pairs.
OkayBetMulti-venue aggregation across prediction markets per their public product description.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimate.
OkayBetNot confirmed in available public documentation.
SimpleFunctionsNot a product feature — SF targets single-contract analysis, cross-venue arbitrage detection, and autonomous position management via Portfolio Autopilot.
OkayBetParlay construction across multiple prediction market contracts is a stated core product capability.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label pre-computed across 48K+ contracts at /screen.
OkayBetNot published in available documentation.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket; re-verifiable with curl.
OkayBetNot published.
SimpleFunctionsPOST /api/thesis/create decomposes a sentence into a causal tree, propagates probabilities, and auto-evaluates on a news + price heartbeat.
OkayBetNot in scope per available public information.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade before any execution.
OkayBetAI agents mentioned in their product description; specific architecture and autonomous trading capabilities not confirmed in public documentation.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp.
OkayBetNo MCP server published.
SimpleFunctionsPublic REST + MCP + CLI reads require no auth. Authenticated thesis and intent execution: free up to 15M tokens, then pay-per-token.
OkayBetNot published in available public sources.
Methodology
Verified 2026-04 from public sources only — OkayBet's documentation, public website, and publicly observable behaviour. We never claim non-public information about OkayBet's internals. SimpleFunctions claims on this page are computed live from /api/calibration, /api/public/cross-venue/pairs, and /api/public/markets — you can re-verify them yourself with curl.
Use cases
Same data, different
best fit per scenario.
Scenario 01
Building an AI agent pipeline that needs to reason over live prediction market prices and take positions autonomously.
SimpleFunctions · best fit
SF ships a 56-tool MCP server, a Portfolio Autopilot with a 7-gate risk cascade, and a causal thesis system. An agent can pull prices, evaluate a thesis, and execute positions through SF in a single pipeline.
OkayBet
OkayBet describes AI agents as part of their product but does not publish a documented API for programmatic agent integration based on available public sources.
Scenario 02
Constructing parlay positions across multiple prediction market contracts.
SimpleFunctions
Parlay construction is not an SF feature. SF's position management is single-contract, driven by thesis conviction scores and the autopilot's risk gates.
OkayBet · best fit
Parlay support is a stated core capability of OkayBet. If multi-leg parlay construction is your primary workflow, OkayBet directly targets this use case.
Scenario 03
Decomposing a complex geopolitical or macroeconomic thesis into tradeable prediction market positions.
SimpleFunctions · best fit
SF's thesis system takes a natural-language sentence, decomposes it into a causal tree of sub-claims, scans Kalshi + Polymarket for tradeable edges, and runs an auto-evaluation heartbeat that updates confidence as news breaks.
OkayBet
OkayBet's product description does not include thesis decomposition or causal-tree modelling based on available public information.
Scenario 04
Verifying a data provider's calibration before incorporating its prices into a research model.
SimpleFunctions · best fit
SF publishes Brier scores at /api/calibration broken down by venue, category, and price bucket — re-verifiable with a single curl call. Kalshi 0.20, Polymarket 0.12 on T-24h prices, past 90 days.
OkayBet
OkayBet does not publish calibration or accuracy data based on available public sources.
Live data
The SimpleFunctions claims on this page are not marketing copy. Brier scores, market counts, and cross-venue pair counts are computed live from /calibration, /screen, and /api/public/cross-venue/pairs. All public, all free, all CC-BY-4.0.
FAQ
What is the main difference between SimpleFunctions and OkayBet?+
OkayBet is positioned as a consumer-facing prediction market application layer with AI-assisted features and parlay betting support. SimpleFunctions is built for the programmatic layer: agents, LLM pipelines, and autonomous trading systems. SF ships a causal thesis system, Portfolio Autopilot, computed indicators across 48K+ contracts, live calibration scores, and a 56-tool MCP server. The two products largely address different audiences — application users versus developers and autonomous agents.
Does SimpleFunctions support parlay betting?+
Parlay construction — combining multiple prediction market legs into a single position — is not a current SF feature. OkayBet has stated parlay support as a core product capability. If multi-leg parlay construction is your primary need, OkayBet targets that use case directly. SF's focus is on single-contract analysis, cross-venue arbitrage detection, causal thesis decomposition, and autonomous single-leg position management via Portfolio Autopilot.
How does SimpleFunctions' thesis system work?+
POST /api/thesis/create takes a natural-language sentence. SF decomposes it into a causal tree of testable sub-claims, propagates initial probabilities from live Kalshi and Polymarket prices, then runs an ongoing evaluation heartbeat: news scan, price refresh, milestone check, LLM evaluation, and confidence update cycle. You can inject external signals at any time via /api/thesis/{id}/signal. Public theses are forkable by other users. No competitor has published a comparable causal-tree thesis system for prediction markets.
Can I use SimpleFunctions with Claude Code or Cursor?+
Yes. SF ships a 56-tool MCP server. Add it with: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. Once added, Claude Code and Cursor can call SF tools directly — fetching market prices, scanning contracts, querying live theses, checking calibration, and triggering the autopilot. OkayBet does not publish an MCP server based on available public information.
Does OkayBet have a public REST API?+
OkayBet's public documentation does not confirm a public programmatic REST API based on available sources. Their stated product focus is application-layer aggregation with AI agents and parlay support, rather than a raw data API for developers. SF's REST API is documented at /openapi.json, publicly accessible for read operations without authentication, and covers 60+ endpoints across markets, theses, indicators, and calibration.
What is SF's calibration baseline and how do I verify it?+
SF publishes its own Brier scores at /api/calibration, broken down by venue, market category, and price bucket. On T-24h prices over the past 90 days: Kalshi 0.20, Polymarket 0.12. These are self-audited figures — SF measures its own prediction accuracy and publishes the result publicly. You can re-verify at any time with curl https://simplefunctions.dev/api/calibration. Most prediction market data providers do not publish comparable calibration data.
How does SF's Portfolio Autopilot work?+
Portfolio Autopilot uses a 1M-context LLM with 13 data sources as input. Before any execution, a 7-gate risk cascade runs: kill switch check, position limit enforcement, drawdown gate, regime classification, and additional guards. Only if all gates pass does the autopilot place a trade. The autopilot integrates with the thesis system — open theses inform position conviction scores. OkayBet describes AI agents in their product but does not publish details about an autonomous trading architecture based on available public information.
Start for free.
Public endpoints are free for normal usage and rate-limited for reliability. Authenticated endpoints are free up to 15M tokens, then pay per token. No credit card to start.