Racing Alpha Signals API
66
AI ReadinessAI-Aware (B)66/100
Official vendor OpenAPI document · agent-readyAI/MLMl Inferencebearer7 EndpointsREST
For Agents
Read Racing Alpha's model picks for today's GB and IRE horse races, per-runner AI scores and fair prices for a race, draw bias by course, trainer-jockey strike rates, and the public tips ledger.
Use for: Get today's horse racing picks for UK and Irish meetings, Retrieve the fair prices for every runner in a race, Check whether there is a draw bias at Chester, List the strongest trainer and jockey combinations
Not supported: Does not place bets, supply raw racecards or live bookmaker odds, or serve betting operators. Use for reading Racing Alpha model signals for GB and IRE horse racing only.
The Racing Alpha Signals API returns model-derived horse-racing signals for Great Britain and Ireland races. It lists today's GB and IRE races with Racing Alpha model picks at frozen advised prices, and for a single race it returns per-runner AI scores, fair prices, value against fair, and draw bias. A public tips ledger with a closing-line-value summary, three-year draw-bias aggregates by course, and trainer and jockey combination strike rates round out the data. All values are Racing Alpha computations rather than a raw racecard or odds feed, and the free tier requires the attribution 'Signals by Racing Alpha'.
Install Jentic One Beta
Connect the Racing Alpha Signals API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Racing Alpha Signals API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fracingalpha.co.uk%2Fracingalpha" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fracingalpha.co.uk%2Fracingalpha" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Racing Alpha Signals API.
List today's GB and IRE races with Racing Alpha model picks at frozen advised prices
Pull per-runner AI scores, fair prices, value against fair, and draw bias for one race by raceId
Look up three-year draw-bias aggregates for a course, split by surface and distance band
Rank trainer and jockey combinations by strike rate with a min_runs threshold
Audit Racing Alpha's public tips ledger and closing-line-value summary
Request a free API key by email, which raises the keyless daily allowance
Use Cases
Patterns agents use Racing Alpha Signals API for, with concrete tasks.
★ Racing research agent through Jentic
A racing research agent can brief a user on the day's GB and IRE cards using model signals instead of raw odds. Through Jentic the agent searches for 'get today's horse racing picks', receives the getTodayRaces operation, then calls getRaceSignals for any race of interest, with the optional ra_live_ bearer key injected at execution time. It returns per-runner scores and fair prices, crediting 'Signals by Racing Alpha' as the free tier requires.
Call GET /api/v1/today, pick the first race's raceId, then call GET /api/v1/races/{raceId} and summarise the top three runners by AI score with their fair prices
Draw-bias analysis by course
Stall position matters more at some tracks than others, and punters and analysts check it before a race. Racing Alpha's GET /api/v1/draw-bias returns three-year aggregates expressed as IV, A-E, and PRB by course, surface, and distance band, filtered with the course query parameter, so an analyst can see whether low or high draws have outperformed.
Call GET /api/v1/draw-bias with course 'Chester' and report which draw positions show the highest IV for sprint distance bands
Model track-record verification
Anyone evaluating a tipping model wants its full record, including losing runs. Racing Alpha publishes a database-frozen tips ledger with a closing-line-value summary through GET /api/v1/ledger, returning up to 500 entries with the limit parameter, so a user can check whether picks beat the closing price over time.
Fetch GET /api/v1/ledger with limit 500 and compute the share of tips that beat the closing line
Trainer and jockey form
Trainer and jockey partnerships are a common form angle. Racing Alpha's GET /api/v1/combos returns strike rates for trainer-jockey pairs from settled races in its archive, with min_runs to exclude small samples and limit up to 500 results.
Call GET /api/v1/combos with min_runs 20 and limit 50 and list the five pairs with the highest strike rate
Key Endpoints
7 endpoints — the racing alpha signals api returns model-derived horse-racing signals for great britain and ireland races.
METHOD
PATH
DESCRIPTION
GET
/api/v1/today
Today's races with model picks
GET
/api/v1/races/{raceId}
Per-runner signals for one race
GET
/api/v1/ledger
Public tips ledger and CLV summary
GET
/api/v1/draw-bias
Draw-bias aggregates by course
GET
/api/v1/combos
Trainer-jockey strike rates
POST
/api/v1/keys
Create a free API key
GET
/api/v1/today
Today's races with model picks
GET
/api/v1/races/{raceId}
Per-runner signals for one race
GET
/api/v1/ledger
Public tips ledger and CLV summary
GET
/api/v1/draw-bias
Draw-bias aggregates by course
GET
/api/v1/combos
Trainer-jockey strike rates
POST
/api/v1/keys
Create a free API key
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
R
Racing Alpha Signals API
- AI-Aware (B)66/100
100
Foundational Compliance66
Developer Experience & Jentic Compatibility46
AI-Readiness & Agent Experience94
Agent Usability60
Security63
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
66
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: BSignals: 4
14%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
46
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
38%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
47%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
63
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B-Signals: 1
62%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Racing Alpha by hand means requesting a free key by email, sending it as an ra_live_ bearer token, and tracking the keyless and keyed daily allowances. Through Jentic you install once, import Racing Alpha from the API Directory, store the key once, and your agent calls it.
Permission scoping
Racing Alpha puts the race id in the URL path (/api/v1/races/{raceId}), and every data route is a read, so a rule can limit your agent to the signal reads you pick. You choose the operations it may call, so key creation and rotation through POST /api/v1/keys is not included unless you add it.
Credential isolation
Your Racing Alpha key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get today's horse racing picks' or 'check draw bias at a course', and Jentic returns the matching Racing Alpha operation with its input schema so the agent calls the right endpoint directly.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Racing Alpha Signals API through Jentic.
What authentication does the Racing Alpha Signals API use?
Per its OpenAPI spec, the Racing Alpha Signals API accepts an HTTP bearer token in the form ra_live_..., but authentication is optional: the spec also allows keyless calls. POST /api/v1/keys creates a free key from an email address, and re-requesting it rotates the key. Through Jentic the key is stored by your own instance and attached at call time, so it never enters the agent's context.
What are the rate limits for the Racing Alpha Signals API?
The OpenAPI spec states that keyless callers get 50 requests per day per IP and that a free API key allows 1,000 requests per day. GET /api/v1/meta returns the service's current limits and terms.
Can I get fair prices for each runner with the Racing Alpha Signals API?
Yes. GET /api/v1/races/{raceId} returns per-runner AI scores, fair prices, value against fair, and draw bias for one race. Get race ids from GET /api/v1/today, which lists the day's GB and IRE races with model picks.
Is there a Racing Alpha MCP server?
You don't need an MCP server to give your agent Racing Alpha. Jentic connects it directly from the API Directory: import it, store your ra_live_ key once, and your agent calls the race, ledger, and draw-bias operations on demand.
Can I limit what my agent is allowed to do with the Racing Alpha Signals API?
Yes. For example, write a rule that allows only GET /api/v1/today and GET /api/v1/races/{raceId}, so the agent can read picks and race signals but cannot call POST /api/v1/keys and rotate your key. Every call it makes is logged.
How do I get today's racing picks through Jentic?
Search Jentic for 'get today's horse racing picks', load the GET /api/v1/today operation, and execute it. Follow up with GET /api/v1/races/{raceId} for runner-level signals. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED