Alternative · On-chain market
Azuro vs
SimpleFunctions.
Azuro provides on-chain EVM infrastructure for developers building decentralized sportsbooks and event-prediction front-ends with shared liquidity. SimpleFunctions is the agent layer above off-chain prediction markets: a causal-tree thesis system with auto-evaluation cycles, an autonomous trading agent with a 7-gate risk cascade, computed indicators across 48K+ contracts, and a 56-tool MCP server that plugs into any AI agent in one command.
Verified 2026-04 · public sources only · live SimpleFunctions data from /calibration
Category
On-chain market
Differences
10
Use cases
4
Verified
2026-04
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
You are building agents, autonomous trading systems, or research pipelines that need more than raw market data — calibrated probabilities with public Brier scores, a causal-tree thesis system that decomposes any claim into testable sub-claims and scans Kalshi and Polymarket for edges, regime classification across 48K contracts, computed indicators (implied yield, cliff risk, liquidity availability score), and a 56-tool MCP server ready for Claude Code or Cursor in one command.
Choose Azuro if
You are building a decentralized sportsbook or event-prediction front-end on EVM chains. Azuro provides the shared LiquidityTree, vAMM, and AzuroSDK that power products like BetSwirl and BookmakerXYZ. If your product requires on-chain pooled liquidity infrastructure rather than programmatic access to off-chain prediction markets, Azuro is the right layer.
Azuro is on-chain EVM infrastructure for sportsbook builders. SimpleFunctions is an off-chain agent layer for prediction market traders, researchers, and autonomous systems.
At a glance
Three things that
actually differ.
Everything Azuro gives you — event-prediction infrastructure, shared liquidity, and SDK tooling for building market front-ends — SimpleFunctions also gives you as normalized REST and MCP access to Kalshi and Polymarket with cross-venue pricing and orderbook depth.
On top of that, SF ships a causal-tree thesis system, an autonomous trading agent (Portfolio Autopilot, 1M-context LLM, 7-gate risk cascade), computed indicators across 48K+ contracts, and 56 MCP tools no current on-chain protocol exposes.
SF publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Azuro is a liquidity infrastructure layer and does not publish a prediction accuracy baseline.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsNormalised prices across Kalshi and Polymarket, 48K+ active contracts indexed live.
AzuroEVM-native sports and event prediction markets with shared on-chain liquidity; distinct from Kalshi and Polymarket.
SimpleFunctionsOff-chain REST API, MCP server, and CLI — no wallet or gas required.
AzuroOn-chain EVM smart contracts with a vAMM and LiquidityTree; interactions require on-chain transactions.
SimpleFunctionsREST endpoints, 56-tool MCP server (claude mcp add simplefunctions), and a CLI (npm i -g @spfunctions/cli) for scripting and agent integration.
AzuroAzuroSDK for building EVM-native sportsbook and event-prediction front-ends; currently powers products like BetSwirl and BookmakerXYZ.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimates.
AzuroLiquidity is pooled via vAMM; no traditional orderbook ladder is exposed.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label — pre-computed across 48K contracts at /screen.
AzuroNot published; Azuro is a liquidity infrastructure layer, not a market analytics product.
SimpleFunctionsLive Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days.
AzuroNot published; Azuro does not produce a probability accuracy baseline.
SimpleFunctionsPOST /api/thesis/create decomposes any claim into a testable causal tree, scans Kalshi and Polymarket for edges, and runs an auto-evaluation heartbeat.
AzuroNot in scope; Azuro provides liquidity infrastructure, not a thesis or research layer.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade before each trade execution.
AzuroNot in scope.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, and any MCP client.
AzuroNo MCP server published.
SimpleFunctionsPublic REST, MCP, and CLI reads require no authentication. Thesis and intent execution: free up to 15M tokens, then pay-per-token.
AzuroOn-chain protocol; fees are governed by smart contract parameters rather than a subscription tier. Public documentation does not specify a flat rate.
Methodology
Verified 2026-04 from public sources only — Azuro's documentation, public website, and publicly observable behaviour. We never claim non-public information about Azuro'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 that monitors prediction market contracts and executes trades autonomously.
SimpleFunctions · best fit
SF exposes a 56-tool MCP server, a causal-thesis pipeline, and Portfolio Autopilot with a 7-gate risk cascade. The agent layer is designed for this exact pattern — read markets, evaluate theses, execute with risk gates.
Azuro
Azuro targets human-facing front-end builders on EVM, not programmatic agent integrations on off-chain venues. It does not offer a REST or MCP interface aligned to this workflow.
Scenario 02
Launching a decentralized sportsbook product on an EVM chain with pooled liquidity.
SimpleFunctions
SF does not provide on-chain smart contract infrastructure or a shared liquidity pool. It is not the right tool for building a decentralized sportsbook.
Azuro · best fit
Azuro exists precisely for this. Its LiquidityTree, vAMM, and AzuroSDK provide the on-chain primitives for building products like BetSwirl and BookmakerXYZ — this is their core product focus.
Scenario 03
Decomposing a geopolitical thesis into a set of tradeable prediction market contracts.
SimpleFunctions · best fit
POST /api/thesis/create accepts any natural-language claim, decomposes it into a causal tree of testable sub-claims, and scans Kalshi and Polymarket for contracts where an edge exists. An evaluation heartbeat refreshes confidence as news arrives.
Azuro
Azuro does not offer a thesis decomposition or research layer. Its scope is on-chain liquidity infrastructure for sportsbook builders.
Scenario 04
Scanning cross-venue arbitrage opportunities between Kalshi and Polymarket in real time.
SimpleFunctions · best fit
GET /api/public/cross-venue/pairs?preset=arb returns matched pairs with normalised prices and spread. Computed indicators — implied yield, event overround — are pre-calculated across 48K contracts.
Azuro
Azuro operates on EVM chains with its own liquidity pool and does not index Kalshi or Polymarket contracts. Cross-venue arbitrage scanning against those venues is outside its scope.
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
How does SimpleFunctions' causal thesis system work?+
POST /api/thesis/create takes any natural-language claim — for example, 'The Fed cuts rates before December' — and decomposes it into a causal tree of testable sub-claims. Each node is mapped to contracts on Kalshi and Polymarket where a tradeable edge exists. An evaluation heartbeat runs continuously: news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject new signals via /api/thesis/{id}/signal. Public theses are forkable. No current prediction market data product offers this pipeline.
What is Portfolio Autopilot and how does the risk cascade work?+
Portfolio Autopilot is SF's autonomous trading agent. It uses a 1M-context LLM and 13 data sources to identify and size positions. Before any trade executes, it passes through a 7-gate risk cascade: kill switch, position limits, drawdown gate, regime check, and additional safeguards. The system logs every decision for audit. It is designed for autonomous operation rather than a human-in-the-loop dashboard workflow.
Does SimpleFunctions have an MCP server?+
Yes. Run claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp to register 56 tools in Claude Code, Cursor, or any MCP-compatible client. Tools cover market search, thesis creation, cross-venue arbitrage scanning, world snapshot, orderbook depth, computed indicators, and more. No authentication is required for read operations.
Can SimpleFunctions connect to Azuro or EVM prediction markets?+
No. SimpleFunctions indexes Kalshi and Polymarket — off-chain, regulated prediction markets. Azuro operates on EVM chains as a decentralized sportsbook and event-prediction protocol. These are distinct ecosystems. If your goal is on-chain sportsbook infrastructure with pooled liquidity, Azuro's AzuroSDK is the right starting point. If your goal is programmatic access to off-chain prediction markets for agents or research, SF is the appropriate layer.
How does SF's calibration baseline work, and why does it matter?+
GET /api/calibration returns SF's own Brier scores broken down by venue, category, and price bucket. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Brier score measures probability accuracy — lower is better. Publishing this lets you verify SF's accuracy before committing capital. Azuro is a liquidity infrastructure layer and does not publish a probability accuracy baseline.
What computed indicators does SimpleFunctions expose?+
SF pre-computes six indicators across 48K+ active contracts: IY (implied yield), CRI (cliff risk index, measuring non-linear settlement risk), LAS (liquidity availability score), EE (event overround, measuring book margin), τ-days (time to settlement), and a regime label that classifies each market's adverse-selection environment. All are available at /screen without authentication and queryable via the MCP server.
Who should choose Azuro over SimpleFunctions?+
Developers building decentralized sportsbook or event-prediction front-ends on EVM chains. Azuro provides the shared LiquidityTree, vAMM, and AzuroSDK that power products like BetSwirl and BookmakerXYZ. If your product requires on-chain pooled liquidity infrastructure for sports markets, Azuro is purpose-built for that audience. SF does not offer on-chain smart contract infrastructure and is not the right tool for that use case.
Same category
Other On-chain market alternatives.
SimpleFunctions vs Drift BET
Solana perpetual-trading protocol's prediction-market sub-product.
SimpleFunctions vs Limitless
Base-L2 short-duration binary market protocol, settled by Pyth oracle.
SimpleFunctions vs Myriad Markets
Prediction market integrated with media properties (Decrypt, Rug Radio); $20M raise Feb 2026.
SimpleFunctions vs Opinion
AI-driven on-chain prediction-market protocol — reported ~31% of global PM volume by 2026-Q1; OPN token launched March 2026; Hack VC + Jump-led $20M raise.
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.