Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PrizePicks 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.
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%2Fprizepicksapi.com%2Fprizepicksapi" | shStep 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%2Fprizepicksapi.com%2Fprizepicksapi" | 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.
What an agent can do with PrizePicks API.
List current PrizePicks projections by league, stat, tier such as goblin or demon, and status
Rebuild the board as it stood at a past time with as_of, and read change-only history for one projection
Grade recorded lines against final box scores and compute a player's over hit rate across their last N games
Compare PrizePicks lines with FanDuel, DraftKings, BetRivers, Novig, Kalshi, and Polymarket prices and an edge against break-even
GET STARTED
Flag stale lines where an outside price moved materially while the PrizePicks line stayed
Export a flat training set of graded lines as JSON or CSV for building a prop model
Rank current lines by reported pick count with the trending operation
Patterns agents use PrizePicks API for, with concrete tasks.
★ AI prop research agent
An agent asked whether a PrizePicks line is worth taking needs the line, outside prices, and the player's recent form. Through Jentic the agent searches for 'compare PrizePicks lines to sportsbooks', loads the LiveCompare operation, reads the edge against the PrizePicks break-even, and pulls the player's hit rate. The bearer key is injected by Jentic, and the agent answers with numbers from the recorded data.
Call GET /api/v1/compare for a player and stat, then GET /api/v1/hit-rates with the player_id, the stat, and last 10, and recommend over or under with the edge and hit rate
Stale line detection
When a sportsbook or exchange moves on news and PrizePicks does not, the line is stale. GET /api/v1/stale-lines returns PrizePicks lines for NBA, NFL, or NHL whose FanDuel, DraftKings, BetRivers, Novig, Kalshi, or Polymarket price moved materially, with min_move, lookback_minutes of 15, 30, or 60, and max_age_minutes filters.
Call GET /api/v1/stale-lines with league 'NBA', book 'draftkings', and lookback_minutes 30, and alert on each line returned
Model training and backtesting
Modellers need clean historical rows. GET /api/v1/training-set returns one flat row per graded line with opening and closing line, tier, opponent, home or away, rest days, minutes, actual value, and result, as JSON with a cursor or as CSV. GET /api/v1/board with as_of rebuilds the board at a past moment from recorded events, so a backtest sees only what was known then. On the Free plan the training set is one page of up to 100 rows.
Page GET /api/v1/training-set with league 'NBA', a from and to date range, and format 'csv' following the cursor, then fit a baseline model on the result column
Live board monitoring
Apps that track the board in real time can subscribe to GET /api/v1/stream, a server-sent events stream of every recorded board change, or poll GET /api/v1/changes and save the last event cursor between calls. GET /api/v1/projections/trending ranks lines by reported pick count or by how fast the count is rising.
Poll GET /api/v1/changes with league 'NFL' every minute, store the cursor, and post any new or moved lines to a channel
39 endpoints — the prizepicks api, an independent developer data service, records the live prizepicks projections board and serves current lines, change-only line history, replayable change feeds, and a rebuilt board as it stood at any past time.
METHOD
PATH
DESCRIPTION
/api/v1/projections
Live current projections
/api/v1/projections/{id}/history
Change-only history for one projection
/api/v1/board
Board as of a past time
/api/v1/results
Graded results
/api/v1/hit-rates
Player over hit rates
/api/v1/compare
Lines beside sportsbook and exchange prices
/api/v1/stale-lines
Stale PrizePicks lines
/api/v1/training-set
Graded training rows
/api/v1/projections
Live current projections
/api/v1/projections/{id}/history
Change-only history for one projection
/api/v1/board
Board as of a past time
/api/v1/results
Graded results
/api/v1/hit-rates
Player over hit rates
/api/v1/compare
Lines beside sportsbook and exchange prices
/api/v1/stale-lines
Stale PrizePicks lines
/api/v1/training-set
Graded training rows
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the PrizePicks API by hand means attaching the bearer key, following cursors and X-Next-Cursor headers across pages, tracking credit headers, and handling plan_limit responses on the Free tier. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
Most PrizePicks API routes take league, player, and stat filters as query parameters, so rules mainly bound which operations your agent may call rather than which markets it reads. You choose the operations it may call, so account-changing ones like POST /api/v1/billing/cancel are not included unless you add them.
Credential isolation
Your PrizePicks API bearer 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 PrizePicks lines' or 'find stale prop lines', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using PrizePicks API through Jentic.
What authentication does the PrizePicks API use?
The OpenAPI spec declares BearerAuth, an HTTP bearer key created in your dashboard, for the live routes. The /api/v1/demo routes, which serve fictional fixed-date fixtures, are open, as are GET /api/v1/credit-costs, the agent signup and key-collection routes, and POST /api/v1/feedback. The spec warns never to expose the key in browser source or URLs.
Is the PrizePicks API affiliated with PrizePicks?
The spec describes it as an independent developer data service. It records the PrizePicks board itself, labels third-party imported lines separately from lines it recorded, and states that no official settlement dataset is currently exposed.
What are the rate limits for the PrizePicks API?
The spec meters usage in weighted credits rather than a stated request rate: Free has 100 credits per month, Developer 10000 per month at $49, Production 50000 at $149, and Scale 250000 at $499. Responses carry X-Credits-Cost, X-Credits-Remaining, and X-Quota-Reset headers, and GET /api/v1/credit-costs quotes the cost of a call.
Is there a PrizePicks MCP server?
You don't need an MCP server to give your agent the PrizePicks API. Jentic connects it directly from the API Directory: import it, store your bearer key once, and your agent calls the projections, results, or comparison operations it needs, discovered on demand rather than preloaded into its context.
Can I limit what my agent is allowed to do with the PrizePicks API?
Yes. For example, write a rule that allows only GET /api/v1/projections, GET /api/v1/compare, and GET /api/v1/hit-rates, so the agent can research lines but cannot cancel your plan through POST /api/v1/billing/cancel or change account setup through POST /api/v1/onboarding. Every call it makes is logged.
What does the Free plan limit?
Per the spec, the live board is full on every plan. On Free, line history, changes, the as_of board, results, and imported lines reach back 7 days, game logs and team stats cover the last 10 games, the training set is one page of up to 100 rows, and compare as_of and closing prices are off. A limited answer keeps its real rows and adds meta.plan_limit.
How do I get current PrizePicks lines through Jentic?
Add the PrizePicks API to your Jentic One instance from the directory and store your bearer key. Your agent searches for 'get PrizePicks lines', loads the LiveProjections operation, and calls GET /api/v1/projections with filters such as league, stat, and tier. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read live and historical PrizePicks lines, graded results, player hit rates, sportsbook and exchange comparisons, stale-line alerts, and player game logs from an independent data service.
Use for: Get today's PrizePicks NBA points lines, Find PrizePicks lines that are stale compared to DraftKings, Check a player's over hit rate on rebounds over the last 10 games, Retrieve the PrizePicks board as it was at tip-off yesterday
Not supported: Does not place entries, manage PrizePicks accounts, or provide official settlement data. Use for reading recorded PrizePicks lines, results, comparisons, and player stats only.
The PrizePicks API, an independent developer data service, records the live PrizePicks projections board and serves current lines, change-only line history, replayable change feeds, and a rebuilt board as it stood at any past time. Recorded lines are graded against final box scores as over, under, push, or void, and feed per-player hit rates and a flat training set with opening and closing lines, tier, opponent, rest days, minutes, and results. Comparison routes put PrizePicks lines beside FanDuel, DraftKings, BetRivers, Novig, Kalshi, and Polymarket prices with a Novig fair probability, and flag stale lines where outside prices moved while the PrizePicks line stayed. Fixtures, player search, game logs, team and opponent stats, injuries, pick-count popularity, and an SSE stream of board changes round it out, with fictional demo routes available without a key.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>