Foresea · Schema
PredictResponse
Prediction result for a single forecasting question.
Prediction-MarketIntelligenceForecastingData AnalyticsBusiness
Properties
| Name | Type | Description |
|---|---|---|
| question_type | string | Detected type: `binary`, `multiple_choice`, `numeric`, or `date`. |
| predicted_answer | object | Headline answer: Yes/No, the top option, or the median estimate. |
| confidence | object | Confidence in the headline answer (binary/MC). Null for numeric. |
| model_probability | object | Explicit model probability for conversational forecasts, when one was provided. |
| options | array | Per-option probabilities for `multiple_choice`. |
| range_forecast | object | p10/p50/p90 estimate for `numeric` and `date`. |
| rationale | object | 2–4 sentence explanation of the prediction. |
| model_rationale | object | Raw rationale as returned by the model (may differ from `rationale` after post-processing). |
| variant | string | Prompt variant used for this prediction. |
| model_key | string | Model identifier (e.g. `gpt-oss-120b`). |
| served_model_name | object | Exact upstream model name that served the response, if reported by the provider. |
| evidence_sources | array | Deduplicated citations used as evidence. |
| evidence_articles | array | Full evidence articles passed to the model. |
| evidence_error | object | Non-null if evidence retrieval failed (prediction still returned). |
| market_analysis | object | Optional comparison against a supplied prediction-market probability. |
| complexity | object | Model's own self-reported difficulty for this question: `low` or `high`. |
| bull_factors | object | Decomposed factors favoring the YES / upside outcome. |
| bear_factors | object | Decomposed counter-factors favoring the NO / downside outcome. |
| key_catalysts | object | Key upcoming events/dates that could trigger thesis revision. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/foresea-ink/json-schema/foresea-ink-predict-response-schema.json",
"title": "PredictResponse",
"description": "Prediction result for a single forecasting question.",
"x-generated": "2026-11-08",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/foresea-ink-openapi.json#/components/schemas/PredictResponse",
"properties": {
"question_type": {
"type": "string",
"title": "Question Type",
"description": "Detected type: `binary`, `multiple_choice`, `numeric`, or `date`.",
"default": "binary"
},
"predicted_answer": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Predicted Answer",
"description": "Headline answer: Yes/No, the top option, or the median estimate."
},
"confidence": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Confidence",
"description": "Confidence in the headline answer (binary/MC). Null for numeric."
},
"model_probability": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Model Probability",
"description": "Explicit model probability for conversational forecasts, when one was provided."
},
"options": {
"items": {
"$ref": "#/$defs/OptionProb"
},
"type": "array",
"title": "Options",
"description": "Per-option probabilities for `multiple_choice`."
},
"range_forecast": {
"anyOf": [
{
"$ref": "#/$defs/RangeForecast"
},
{
"type": "null"
}
],
"description": "p10/p50/p90 estimate for `numeric` and `date`."
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Rationale",
"description": "2–4 sentence explanation of the prediction."
},
"model_rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model Rationale",
"description": "Raw rationale as returned by the model (may differ from `rationale` after post-processing)."
},
"variant": {
"type": "string",
"title": "Variant",
"description": "Prompt variant used for this prediction."
},
"model_key": {
"type": "string",
"title": "Model Key",
"description": "Model identifier (e.g. `gpt-oss-120b`)."
},
"served_model_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Served Model Name",
"description": "Exact upstream model name that served the response, if reported by the provider."
},
"evidence_sources": {
"items": {
"$ref": "#/$defs/EvidenceSource"
},
"type": "array",
"title": "Evidence Sources",
"description": "Deduplicated citations used as evidence."
},
"evidence_articles": {
"items": {
"$ref": "#/$defs/NewsArticle"
},
"type": "array",
"title": "Evidence Articles",
"description": "Full evidence articles passed to the model."
},
"evidence_error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Evidence Error",
"description": "Non-null if evidence retrieval failed (prediction still returned)."
},
"market_analysis": {
"anyOf": [
{
"$ref": "#/$defs/MarketAnalysis"
},
{
"type": "null"
}
],
"description": "Optional comparison against a supplied prediction-market probability."
},
"complexity": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Complexity",
"description": "Model's own self-reported difficulty for this question: `low` or `high`."
},
"bull_factors": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Bull Factors",
"description": "Decomposed factors favoring the YES / upside outcome."
},
"bear_factors": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Bear Factors",
"description": "Decomposed counter-factors favoring the NO / downside outcome."
},
"key_catalysts": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Key Catalysts",
"description": "Key upcoming events/dates that could trigger thesis revision."
}
},
"type": "object",
"required": [
"variant",
"model_key"
],
"$defs": {
"EvidenceSource": {
"properties": {
"source": {
"type": "string",
"title": "Source",
"description": "Publisher name."
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Title",
"description": "Article headline."
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Url",
"description": "Article URL."
},
"publish_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Publish Date",
"description": "ISO 8601 publish date."
},
"relevance_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Relevance Score",
"description": "Relevance to the question (0–1)."
}
},
"type": "object",
"required": [
"source"
],
"title": "EvidenceSource",
"description": "A deduplicated citation drawn from the evidence articles."
},
"MarketAnalysis": {
"properties": {
"platform": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Platform",
"description": "Prediction market venue supplied by the caller."
},
"market_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Market Url",
"description": "Prediction market URL supplied by the caller."
},
"outcome": {
"type": "string",
"title": "Outcome",
"description": "Outcome being compared against the market price."
},
"market_probability": {
"type": "number",
"maximum": 1.0,
"minimum": 0.0,
"title": "Market Probability",
"description": "Market-implied probability for the outcome."
},
"model_probability": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Model Probability",
"description": "Foresea probability for the same outcome (recalibrated from the live track record when warranted)."
},
"model_probability_raw": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Model Probability Raw",
"description": "Raw model probability before live calibration (only set when calibration was applied)."
},
"edge": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Edge",
"description": "Model probability minus market probability."
},
"stance": {
"type": "string",
"title": "Stance",
"description": "`model_above_market`, `model_below_market`, `in_line`, or `not_comparable`."
},
"summary": {
"type": "string",
"title": "Summary",
"description": "Short human-readable market comparison."
}
},
"type": "object",
"required": [
"outcome",
"market_probability",
"stance",
"summary"
],
"title": "MarketAnalysis",
"description": "Deterministic comparison between Foresea's forecast and a market price."
},
"NewsArticle": {
"properties": {
"title": {
"anyOf": [
{
"type": "string",
"maxLength": 500
},
{
"type": "null"
}
],
"title": "Title",
"description": "Article headline."
},
"summary": {
"anyOf": [
{
"type": "string",
"maxLength": 4000
},
{
"type": "null"
}
],
"title": "Summary",
"description": "Short human-written summary."
},
"summary_llm": {
"anyOf": [
{
"type": "string",
"maxLength": 4000
},
{
"type": "null"
}
],
"title": "Summary Llm",
"description": "LLM-generated summary."
},
"text": {
"anyOf": [
{
"type": "string",
"maxLength": 20000
},
{
"type": "null"
}
],
"title": "Text",
"description": "Full article body text."
},
"source": {
"anyOf": [
{
"type": "string",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Source",
"description": "Publisher name (e.g. Reuters)."
},
"credibility": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Credibility",
"description": "Credibility score breakdown."
},
"frs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Frs",
"description": "Future-Resolution Statement metadata."
},
"url": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Url",
"description": "Canonical article URL."
},
"authors": {
"anyOf": [
{},
{
"type": "null"
}
],
"title": "Authors",
"description": "Author name(s)."
},
"publish_date": {
"anyOf": [
{
"type": "string",
"maxLength": 100
},
{
"type": "null"
}
],
"title": "Publish Date",
"description": "ISO 8601 publish timestamp."
},
"keywords": {
"anyOf": [
{},
{
"type": "null"
}
],
"title": "Keywords",
"description": "Extracted keywords."
},
"relevance_score": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Relevance Score",
"description": "Cosine similarity to the question (0–1)."
},
"search_query": {
"anyOf": [
{
"type": "string",
"maxLength": 500
},
{
"type": "null"
}
],
"title": "Search Query",
"description": "Query used to retrieve this article."
}
},
"type": "object",
"title": "NewsArticle",
"description": "A news article passed as evidence context for the prediction."
},
"OptionProb": {
"properties": {
"label": {
"type": "string",
"title": "Label",
"description": "The option text."
},
"probability": {
"type": "number",
"maximum": 1.0,
"minimum": 0.0,
"title": "Probability",
"description": "Probability assigned to this option (0–1)."
}
},
"type": "object",
"required": [
"label",
"probability"
],
"title": "OptionProb",
"description": "A single option and its probability in a multiple-choice forecast."
},
"RangeForecast": {
"properties": {
"p10": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "P10",
"description": "10th-percentile (low) estimate."
},
"p50": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "P50",
"description": "50th-percentile (median) estimate."
},
"p90": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "P90",
"description": "90th-percentile (high) estimate."
},
"unit": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Unit",
"description": "Unit of the estimate, e.g. 'USD', '%', 'people'."
}
},
"type": "object",
"title": "RangeForecast",
"description": "A numeric or date estimate expressed as percentile bounds."
}
}
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/foresea-ink-predict-response"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.