{ "openapi": "3.1.0", "info": { "title": "SocialCrawl API: Google News", "version": "1.0.0", "description": "Unified social media data API - one API key, one consistent response format, 69 platforms, 679 endpoints. Power AI agents with clean social data.\n\nThis document covers the Google News endpoints only (1 operations). The full contract for every platform is at https://www.socialcrawl.dev/v1/openapi.json, and every per-platform document is listed at https://www.socialcrawl.dev/openapi/index.json.", "contact": { "name": "SocialCrawl", "url": "https://www.socialcrawl.dev", "email": "socialcrawl@ridio.io" } }, "servers": [ { "url": "https://www.socialcrawl.dev/v1", "description": "Production" } ], "security": [ { "ApiKeyAuth": [] }, { "BearerAuth": [] } ], "components": { "securitySchemes": { "ApiKeyAuth": { "type": "apiKey", "in": "header", "name": "x-api-key", "description": "API key authentication. Send your key in the `x-api-key` request header on every call. Create and manage keys in the dashboard." }, "BearerAuth": { "type": "http", "scheme": "bearer", "description": "The same API key sent as `Authorization: Bearer `, the default in most agents and HTTP tools. Same key, same rules; when both headers are sent, `x-api-key` wins." } }, "schemas": { "ErrorEnvelope": { "type": "object", "description": "Unified error response envelope. Every 4xx/5xx response returns this shape; `error.type` is a machine-readable code from the API's error catalog.", "properties": { "success": { "type": "boolean", "enum": [ false ], "example": false, "description": "Always false on an error response." }, "error": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "MISSING_API_KEY", "INVALID_API_KEY", "INSUFFICIENT_CREDITS", "INVALID_REQUEST", "ENDPOINT_NOT_FOUND", "RESOURCE_NOT_FOUND", "CONCURRENCY_LIMIT", "UPSTREAM_ERROR", "SERVICE_UNAVAILABLE", "INTERNAL_ERROR", "METHOD_NOT_ALLOWED", "IDEMPOTENCY_KEY_CONFLICT", "IDEMPOTENCY_IN_PROGRESS", "IDEMPOTENCY_REPLAY_UNAVAILABLE", "IDEMPOTENCY_KEY_PAYLOAD_MISMATCH", "COHORT_MEMBER_LIMIT_EXCEEDED", "COHORT_LIMIT_EXCEEDED", "COHORT_IDENTITY_PLATFORM_UNSUPPORTED", "COHORT_IDENTITY_CONFLICT", "COHORT_QUERY_NOT_CANCELLABLE", "COHORT_QUERY_NOT_READY", "COHORT_RESULT_TOO_LARGE", "PAYLOAD_TOO_LARGE", "RATE_LIMITED", "KEY_BUDGET_EXCEEDED", "RUN_NOT_FOUND", "RUN_STATE_CONFLICT", "RUN_EXPIRED", "NEEDS_ASYNC", "CURSOR_EXPIRED", "SCHEDULE_NOT_FOUND", "STREAM_NOT_FOUND", "STREAM_STATE_CONFLICT" ], "example": "INVALID_REQUEST", "description": "Machine-readable error code. The per-status `x-error-codes` list on each response narrows which codes that status can carry." }, "message": { "type": "string", "description": "Human-readable explanation of the error." }, "status": { "type": "integer", "description": "HTTP status code, echoed in the body." }, "doc_url": { "type": "string", "description": "Link to the docs page for this error code." }, "retryable": { "type": "boolean", "description": "Whether retrying the identical request can succeed. True for rate limits, concurrency limits, idempotency contention and transient upstream or server failures; false for every other code, including both 402s." }, "details": { "type": [ "object", "null" ], "additionalProperties": true, "description": "Optional structured context. Omitted on ordinary errors. Both 402s carry `reason` (`balance_too_low` or `key_budget_reached`), `retry_will_succeed: false`, a one-sentence `next_step`, and `top_up_url` or `key_settings_url`; the GET endpoints add `credits_required`; a metered endpoint adds `pricing` (`\"ceiling\"` when the hold is the most the call can cost and the unused part is refunded, `\"exact\"` when the call is charged what it holds; measured on recent production calls), `credits_typical` (on a ceiling, what a call like this is usually charged), and, when a cheaper shape of the same request exists, `lower_cost_with`, `lower_cost_options` (`param`, `value` or null to leave it out, and `credits_required` with that change) and `credits_required_cheapest`. A `max_credits` page that switched to a cheaper form to fit (`threads/search` with `expand=false`) and still found the balance short adds `balance_fallback`: the `param` and `value` it switched to, and `credits_required` for the call as sent. A page-cap rejection carries `reason: \"page_limit\"` with `max_page`, `requested_page` and `narrow_with`. An `INVALID_REQUEST` that sends no member of a required one-of group carries `fields` (the parameters of that group) and a one-sentence `next_step`. Other endpoints use it for their own taxonomies, such as the comment-lookup not-found reasons." }, "status_url": { "type": "string", "format": "uri", "description": "Present on 5xx responses: the public status page, filtered to the platform when one is known." }, "incident": { "type": "object", "description": "Present on a 5xx response when an open public incident explains the failure.", "properties": { "id": { "type": "string", "example": "k3v9w2m8q1zt" }, "title": { "type": "string" }, "status": { "type": "string", "example": "investigating" }, "impact": { "type": "string", "example": "major" }, "url": { "type": "string", "format": "uri" } }, "required": [ "id", "title", "status", "impact", "url" ] } }, "required": [ "type", "message", "status", "doc_url" ] }, "credits_used": { "type": "integer", "description": "Net credits charged for this request. Error paths deduct-then-refund, so this is 0 in almost every case; a partial-coverage composite may keep the succeeded-leg cost." }, "credits_remaining": { "type": [ "integer", "null" ], "description": "Credits left after this request when established. Some unauthenticated errors use null; on a prebilling route whose attempted balance lookup fails, this field is omitted instead of fabricated." }, "request_id": { "type": "string", "description": "Unique request identifier - matches the X-Request-Id header. Quote it in support requests." } }, "required": [ "success", "error", "credits_used", "request_id" ] }, "MonitorAlertRule": { "description": "A numeric condition evaluated against a monitor run and, for change operators, a previous comparable run.", "properties": { "metric": { "description": "Dot path to a numeric key in the recipe's own result, for example `coverage` or `summary.total`. On a numbers-only monitor (created with `track`) the metric must be one of `track.metrics`, and an `items[].` metric is evaluated once per row: a fired alert then carries `row_id`. The special metric `rows_new` (numbers-only monitors only; it needs an `items[].` metric in `track.metrics` and is not itself tracked) counts the list rows this run has that the previous run did not: `{\"metric\":\"rows_new\",\"op\":\"gt\",\"value\":0}` alerts on any new post or video. It accepts only `gt` and `gte`, and is skipped on the first run. \"New\" means absent from the previous successful run's stored rows (capped at `max_rows`, default 100), so a row that drops off and returns later counts as new again. An empty-page run is refunded and is not a baseline, so on a sparse feed the first run that holds rows has no baseline and stays silent: the first new post after a quiet period may not alert. Use a daily cadence or leave `max_rows` headroom.", "type": "string" }, "op": { "enum": [ "gt", "lt", "gte", "lte", "abs_change_gt", "pct_change_gt", "pct_change_lt" ], "type": "string" }, "value": { "type": "number" }, "window": { "description": "Accepted and stored, but ignored: a change op always compares against the immediately preceding comparable run, whatever the value.", "enum": [ "1d", "1w" ], "type": "string" } }, "required": [ "metric", "op", "value" ], "type": "object" }, "EventEnvelope": { "description": "One event, identical in the feed and in every webhook batch. `id` is stable for one fact, so deduplicate on it.", "properties": { "id": { "description": "Deterministic event id: the same fact never mints a second event.", "example": "evt_k3m7q2xwcbvd4nph6trz5ycgda", "type": "string" }, "type": { "description": "Dot-delimited lower-case type. Types written today: `discover.progress`, `discover.accounts_ready`, `discover.completed`, `discover.partial`, `discover.paused`, `discover.failed`, `discover.new_rows`, `discover.new_accounts`, `discover.new_items`, `discover.run_skipped`, `discover.run_failed`, `endpoint.disabled`, `mention.created`, `mention.deleted`, `stream.baseline.established`, `stream.coverage_gap`, `stream.paused`, `stream.resumed`, `stream.deleted`, `stream.budget.warning`, `stream.health`.", "example": "discover.completed", "type": "string" }, "api_version": { "example": "2026-10-01", "type": "string" }, "created_at": { "format": "date-time", "type": "string" }, "cursor": { "description": "The feed position right after this event. Send it as `cursor` to read what came after; an event id works too.", "example": "c_MS4xMi4xNzkyNDA0OTA0", "type": "string" }, "subject": { "description": "The object the event is about, for example `{ kind: \"discover_run\", id: \"run_…\" }`.", "properties": { "id": { "type": "string" }, "kind": { "type": "string" }, "metadata": { "type": [ "object", "null" ] }, "name": { "type": [ "string", "null" ] } }, "required": [ "kind", "id" ], "type": [ "object", "null" ] }, "data": { "description": "The event's facts. Discover events carry counts and ids, never keywords or row text.", "type": "object" }, "links": { "additionalProperties": { "type": "string" }, "description": "Absolute URLs to the subject, such as `run` and `results` (for example `https://www.socialcrawl.dev/v1/prism/discover/runs/run_...`), the same in the feed and in webhook batches. Events served before 26/10/2026 carried relative paths.", "type": "object" } }, "required": [ "id", "type", "api_version", "created_at", "cursor", "subject", "data", "links" ], "type": "object" }, "WebhookEndpoint": { "description": "A registered receiver. The signing secret is never part of it: it is returned once, by create and by rotate-secret.", "properties": { "id": { "example": "we_V1StGXR8Z5jdHi6BmyT", "type": "string" }, "url": { "example": "https://example.com/hooks/socialcrawl", "type": "string" }, "description": { "type": [ "string", "null" ] }, "types": { "description": "Subscribed event types: exact types, `ns.*` wildcards, or `*` for every type.", "items": { "type": "string" }, "type": "array" }, "subject_ids": { "description": "Only events about these subjects (a run or schedule id); null for every subject.", "items": { "type": "string" }, "type": [ "array", "null" ] }, "status": { "enum": [ "enabled", "disabled" ], "type": "string" }, "disabled_reason": { "description": "`gone` (the receiver answered 410), `failing` (5 consecutive days of failed deliveries), `key_revoked` (the creating key was revoked or deleted) or `user` (set with PATCH). Null while enabled.", "enum": [ "gone", "failing", "key_revoked", "user", null ], "type": [ "string", "null" ] }, "failing_since": { "description": "Start of the current run of failed deliveries; null while healthy.", "format": "date-time", "type": [ "string", "null" ] }, "api_version": { "example": "2026-10-01", "type": "string" }, "secret_rotation": { "description": "Set during a rotation: until `previous_secret_expires_at` every delivery is signed with both secrets.", "properties": { "previous_secret_expires_at": { "format": "date-time", "type": "string" } }, "type": [ "object", "null" ] }, "created_at": { "format": "date-time", "type": "string" }, "updated_at": { "format": "date-time", "type": "string" }, "next": { "description": "Ready relative URLs for the next calls.", "properties": { "attempts_url": { "type": "string" }, "events_url": { "type": "string" }, "rotate_secret_url": { "type": "string" }, "self_url": { "type": "string" }, "test_url": { "type": "string" } }, "type": "object" } }, "required": [ "id", "url", "types", "status", "api_version", "created_at" ], "type": "object" }, "WebhookAttempt": { "description": "One delivery attempt. `response_excerpt` is at most 1 KB of your receiver's answer.", "properties": { "id": { "type": "string" }, "delivery_id": { "description": "The batch's `webhook-id`, the same on every retry.", "type": "string" }, "test": { "type": "boolean" }, "status": { "description": "Your receiver's HTTP status; null for a timeout, a refused host, a network error or a secret that could not be opened.", "type": [ "integer", "null" ] }, "outcome": { "enum": [ "delivered", "failed", "gone", "retry_after", "timeout", "redirect", "refused_host", "secret_unavailable", "network_error" ], "type": "string" }, "duration_ms": { "type": [ "integer", "null" ] }, "response_excerpt": { "type": [ "string", "null" ] }, "error": { "type": [ "string", "null" ] }, "created_at": { "format": "date-time", "type": "string" } }, "required": [ "id", "delivery_id", "test", "status", "outcome", "created_at" ], "type": "object" }, "EventBatch": { "description": "What every delivery carries, also for one event: at most 100 events or 256 KB. Each inner event keeps its own `id` and `cursor`; deduplicate on the inner ids. A test send marks its event `\"test\": true` with `\"cursor\": null`.", "properties": { "id": { "example": "bat_V1StGXR8Z5jdHi6BmyT", "type": "string" }, "type": { "const": "event.batch", "type": "string" }, "data": { "properties": { "events": { "items": { "$ref": "#/components/schemas/EventEnvelope" }, "maxItems": 100, "type": "array" } }, "required": [ "events" ], "type": "object" } }, "required": [ "id", "type", "data" ], "type": "object" }, "ListeningRuleAst": { "description": "A rule as a tree of `and`, `or`, `not`, `term`, `phrase` and `field` nodes, as the dry run returns it in `data.stream.groups[].ast`.", "anyOf": [ { "type": "object", "properties": { "and": { "minItems": 1, "type": "array", "items": { "$ref": "#/components/schemas/ListeningRuleAst" } } }, "required": [ "and" ], "additionalProperties": false }, { "type": "object", "properties": { "or": { "minItems": 1, "type": "array", "items": { "$ref": "#/components/schemas/ListeningRuleAst" } } }, "required": [ "or" ], "additionalProperties": false }, { "type": "object", "properties": { "not": { "$ref": "#/components/schemas/ListeningRuleAst" } }, "required": [ "not" ], "additionalProperties": false }, { "type": "object", "properties": { "term": { "type": "string", "minLength": 1 } }, "required": [ "term" ], "additionalProperties": false }, { "type": "object", "properties": { "phrase": { "type": "string", "minLength": 1 } }, "required": [ "phrase" ], "additionalProperties": false }, { "type": "object", "properties": { "field": { "type": "string", "enum": [ "lang", "country", "platform", "site", "community" ] }, "value": { "type": "string", "minLength": 1 } }, "required": [ "field", "value" ], "additionalProperties": false } ] } } }, "tags": [ { "name": "google_news", "description": "Google_news endpoints" } ], "paths": { "/google_news/search": { "get": { "summary": "Search Google News", "description": "Returns a unified NewsArticleList of the top Google News results for a keyword, right now: headline, source outlet, thumbnail, article URL, and absolute UTC publish time (a text snippet may be present on some results). Ranked results land in one list: `rank` is the 1-based position of the row in the list you were served, on every source, and `placement` distinguishes a Top Stories block when present. `source` is the outlet name where the provider supplies one and the article's domain otherwise; `domain` is always the hostname. The keyword supports quoted phrases and boolean operators (AND, OR, NOT). Localize with `location_name`/`location_code`/`location_coordinate` + `language_code` (non-Latin scripts supported). Filter by recency with `time_range`, by an exact date window with `from`/`to` (YYYY-MM-DD or Unix timestamp; overrides `time_range` when present), or by outlet with `publisher` (a bare domain like bbc.com). `publisher`/`from`/`to` cannot be combined with `location_coordinate` or `time_range=hour` (clear 400, never billed). There is no pagination beyond `depth`. This surface returns at most 100 articles per query (default 10). For the full article body, scrape the returned `url`. Served live from Google News: an ordinary synchronous request.", "tags": [ "google_news" ], "operationId": "get_google_news_search", "security": [ { "ApiKeyAuth": [] }, { "BearerAuth": [] } ], "x-credit-tier": "standard", "x-credit-cost": 1, "parameters": [ { "name": "keyword", "in": "query", "required": true, "description": "Search query (e.g. 'openai'). Supports any language; pass the matching language_code. Advanced operators (site:, intitle:, cache:, …) are not supported.", "schema": { "type": "string" }, "example": "openai" }, { "name": "depth", "in": "query", "required": false, "description": "Number of articles to retrieve (default 10, multiples of 10, max 100). The response is cut to exactly this many. No pagination beyond depth.", "schema": { "type": "integer" }, "example": 20 }, { "name": "location_code", "in": "query", "required": false, "description": "Google location code (e.g. 2840 = United States: the codes are 2000 + the ISO 3166 numeric code, so small integers are not valid and are rejected). Use one of location_code / location_name / location_coordinate.", "schema": { "type": "integer" } }, { "name": "location_name", "in": "query", "required": false, "description": "Google location name (e.g. 'South Korea').", "schema": { "type": "string" } }, { "name": "location_coordinate", "in": "query", "required": false, "description": "GPS target as 'latitude,longitude,radius_mm' (e.g. '40.7128,-74.0060,200') for local-news radius queries.", "schema": { "type": "string" } }, { "name": "language_code", "in": "query", "required": false, "description": "Google language code (e.g. 'en', 'ko'). Default 'en'. Without a location, en and es get the US edition and most other languages their home edition (bn = Bangladesh, ko = South Korea). Region codes such as pt-BR, zh-TW or zh-Hans are accepted and pick that edition.", "schema": { "type": "string" }, "example": "en" }, { "name": "time_range", "in": "query", "required": false, "description": "Only return articles published within this window: hour, day, week, month, or year. Ignored when from/to is present. Resolution is a calendar DAY on the primary source, so `day` means 'since yesterday', not the last 24 hours; only `hour` is a true rolling window, and it is served by the fallback.", "schema": { "type": "string", "enum": [ "hour", "day", "week", "month", "year" ] }, "example": "day" }, { "name": "publisher", "in": "query", "required": false, "description": "Limit results to a single outlet's domain (e.g. 'bbc.com'). Bare domain only, no scheme, no path. Not combinable with location_coordinate or time_range=hour.", "schema": { "type": "string" }, "example": "bbc.com" }, { "name": "from", "in": "query", "required": false, "description": "Start of an exact publish-date window, as YYYY-MM-DD or a Unix timestamp. Overrides time_range. Not combinable with location_coordinate or time_range=hour.", "schema": { "type": "string" }, "example": "2026-07-01" }, { "name": "to", "in": "query", "required": false, "description": "End of the publish-date window (inclusive), as YYYY-MM-DD or a Unix timestamp. Defaults to now when only from is set.", "schema": { "type": "string" }, "example": "2026-07-15" }, { "name": "since", "in": "query", "required": false, "description": "Only rows published on or after this date: YYYY-MM-DD (midnight UTC) or an ISO 8601 timestamp. Rows older than it are left off each page. This list is not in date order, so the walk does not stop at the date: keep following `next_cursor`, and each page costs what a page costs even when every row on it is filtered out. A row with no date is kept. `published_after`, `start_date`, `from_date`, `publish_time` (`yesterday`, `this-week`, `this-month`, `last-3-months`, `last-6-months`) and `max_age_days` are accepted and applied as `since`.", "schema": { "type": "string" } }, { "name": "until", "in": "query", "required": false, "description": "Only rows published on or before this date: YYYY-MM-DD (that whole UTC day is included) or an ISO 8601 timestamp. Newer rows are left off each page and the walk does not stop, so older pages follow. A row with no date is kept. `published_before`, `end_date` and `to_date` are accepted and applied as `until`.", "schema": { "type": "string" } }, { "name": "max_age_s", "in": "query", "required": false, "description": "The oldest cached copy you accept, in seconds. A copy that old or younger is served for 0 credits, with its age in `age_s` and the `X-Cache-Age` header. Without it a copy up to 300 seconds old is served. A lower value fetches fresh (billed) when the copy is older, and 0 always fetches live, like `Cache-Control: no-cache`.", "schema": { "type": "integer", "minimum": 0, "maximum": 300 } }, { "name": "Cache-Control", "in": "header", "required": false, "description": "Send `no-cache` to bypass the response cache and force a live fetch. Billed at the normal endpoint cost; the fresh result is written back to cache for the next caller. Only the `no-cache` directive triggers this. To accept an older cached copy, or to require a younger one, send the `max_age_s` query parameter instead. See the Response Schema guide for details.", "schema": { "type": "string" }, "example": "no-cache" }, { "name": "Idempotency-Key", "in": "header", "required": false, "description": "Optional UUID that makes the request safely retriable. The key is reserved atomically per account before billing. A concurrent retry receives `409 IDEMPOTENCY_IN_PROGRESS` with a `Retry-After` of 1 second while the original is young, growing to a quarter of the time it has been running (at most 30); a crashed reservation expires after 5 minutes. A replay keeps the cached payload immutable except for billing metadata: `credits_used` becomes 0, `idempotent_replay` becomes true, and `credits_remaining` is refreshed to the current balance. A known current balance appears in both the body and `X-Credits-Remaining` header; no balance row resolves to 0. On a transient lookup failure, body `credits_remaining` is null and `X-Credits-Remaining` is omitted. Completed outcomes expire after 24 hours. If the claim store is unavailable, the request fails closed before billing. GET endpoints do not combine idempotent replay with Server-Sent Events: use `Accept: application/json` when sending this header. The unsupported key-plus-SSE combination is rejected before billing.", "schema": { "type": "string" }, "example": "7a5e1b4c-2d8f-4a3b-9c1e-6e8b4d2a1f3c" }, { "name": "Prefer", "in": "header", "required": false, "description": "Send `respond-async` to run this GET in the background instead of waiting on the socket (or add `?async=true` to the query). The answer is 202 with `data.job_id`, a `Location` header and `Retry-After`; read the result free at `GET /v1/prism/jobs/{job_id}`, where `results[0].response` is exactly what this call returns. Nothing is held at submit: the call is validated now and billed as this call when it runs. Use it for calls that can outlast your client's timeout (MCP and many HTTP clients stop at 30 s). `Idempotency-Key` returns the same job on a retry.", "schema": { "type": "string" }, "example": "respond-async" } ], "responses": { "200": { "description": "Successful response", "headers": { "X-Credits-Used": { "description": "Net credits charged for this response. Idempotency replays report 0.", "schema": { "type": "integer", "minimum": 0 } }, "X-Credits-Remaining": { "description": "Current authoritative balance. Free cache hits and idempotency replays omit this header when the balance cannot be determined; body `credits_remaining` is null instead.", "schema": { "type": "integer", "minimum": 0 } }, "X-Key-Credits-Remaining": { "description": "Only when the API key has a credit limit: the credits this key may still spend under that limit, after this call (never below 0). Absent for a key with no limit. `GET /v1/keys/current` has the limit and what is used.", "schema": { "type": "integer", "minimum": 0 } }, "X-Idempotent-Replay": { "description": "Present with value `true` only when this response replays a settled idempotency record.", "schema": { "type": "string", "enum": [ "true" ] } }, "Idempotent-Replayed": { "description": "Present with value `true` only when this response replays a settled idempotency record. Same meaning as `X-Idempotent-Replay`.", "schema": { "type": "string", "enum": [ "true" ] } } }, "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Whether the request succeeded", "example": true }, "platform": { "type": "string", "description": "Platform name", "example": "google_news" }, "endpoint": { "type": "string", "description": "API endpoint path", "example": "/v1/google_news/search" }, "data": { "type": "object", "description": "Platform-specific response data", "properties": { "items": { "type": "array", "description": "Array of canonical news article wrappers ({ article })", "items": { "type": "object", "description": "Canonical news article wrapper", "properties": { "article": { "type": "object", "description": "Canonical NewsArticle object (unified across news sources)", "properties": { "id": { "type": "string", "description": "Stable article ID (hash of the url)" }, "title": { "type": [ "string", "null" ], "description": "Article headline" }, "url": { "type": [ "string", "null" ], "description": "Direct URL to the article" }, "source": { "type": [ "string", "null" ], "description": "Publishing outlet name (falls back to the domain)" }, "domain": { "type": [ "string", "null" ], "description": "Host domain of the article" }, "snippet": { "type": [ "string", "null" ], "description": "Article excerpt (news_search items only; null on top_stories)" }, "image_url": { "type": [ "string", "null" ], "description": "Thumbnail image URL" }, "published_at": { "type": [ "string", "number", "null" ], "description": "Absolute UTC publish time" }, "rank": { "type": [ "number", "null" ], "description": "Result rank (news_search items only; null on top_stories)" }, "placement": { "type": [ "string", "null" ], "description": "Source list: \"news_search\" or \"top_stories\"" } } } } } }, "next_cursor": { "type": [ "string", "null" ], "description": "Opaque cursor for the next page. Pass it back as a query parameter on endpoints that support pagination. Present only when the upstream reports more results." }, "total": { "type": [ "integer", "null" ], "description": "Total number of matching results, when the upstream provides a count. Omitted otherwise." }, "dropped": { "type": "integer", "description": "Number of upstream list items dropped because they could not be repaired to the endpoint schema. Valid list responses include 0.", "example": 0 }, "empty_reason": { "type": "string", "enum": [ "no_matches", "end_of_list", "nothing_new_since", "window_filtered", "relevance_filtered", "row_filtered", "already_seen", "source_empty_unverified" ], "description": "Present only when `items` is empty: why this page has no rows. Read it with `pagination.has_more`, which still says whether to keep paging. `no_matches`: The source answered and has no rows for this request. The same call returns the same answer, so change the query or the filters to get rows. `end_of_list`: This page was requested with a cursor and the list has no more rows. Stop paging. `nothing_new_since`: The walk reached your since or stop_at_id boundary before any newer row, so nothing was published after it. Poll again later with the same boundary. `window_filtered`: Every row on this page fell outside your date window (since, until, recent_days) or was a pinned post you excluded. Keep paging while pagination.has_more is true, or widen the window. `relevance_filtered`: relevance=filter judged every row on this page off-topic, and their ids are in data.relevance.dropped_ids. Keep paging while pagination.has_more is true, or send relevance=score to keep every row. `row_filtered`: A row filter you sent (such as country or min_views) kept no row on this page, and the report beside items counts what it dropped. Keep paging while pagination.has_more is true, or loosen the filter. `already_seen`: Every row on this page was one already returned to you on this walk, so there is nothing new here. Keep paging while pagination.has_more is true. `source_empty_unverified`: The source returned no rows and nothing confirmed it: no second source agreed, a source failed on the way, or a page mid-list came back empty. Retry later or with Cache-Control: no-cache, and keep paging while pagination.has_more is true.", "example": "nothing_new_since" }, "empty_reason_note": { "type": "string", "description": "Present only beside `empty_reason`: one or two sentences for a person or an agent saying what the code means and what to do next. The wording can improve; branch on `empty_reason`.", "example": "The walk reached your since or stop_at_id boundary before any newer row, so nothing was published after it. Poll again later with the same boundary." }, "_warnings": { "type": "array", "description": "Non-fatal notices about this response (field-map drift, clamped computed values). Advisory only: its presence never means the request failed. Omitted entirely when there is nothing to report, so treat absent as 'no warnings'.", "items": { "type": "string", "description": "One advisory notice." } } }, "required": [ "dropped" ] }, "credits_used": { "type": "integer", "description": "Number of credits consumed", "example": 1 }, "credits_remaining": { "type": [ "integer", "null" ], "description": "Current account balance, or null when this response could not establish one. Free cache hits always return null because they do not establish an authoritative post-request balance. An idempotency replay also returns null when its current-balance lookup fails. It is never a fabricated zero, so a zero here means the account really is empty. The authoritative reading is the one on a billed response, which comes straight from the deduction.", "example": 4999 }, "credits_remaining_note": { "type": "string", "description": "Present only when `credits_remaining` is null by design, as on a free cache hit: says why the balance was not read and where to read it.", "example": "not read on cache hits (credits_used is 0); call GET /v1/credits/balance for the current balance" }, "request_id": { "type": "string", "description": "Unique request identifier for support", "example": "req-abc123" }, "cached": { "type": "boolean", "description": "Whether the response was served from cache", "example": false }, "age_s": { "type": [ "integer", "null" ], "description": "Present only on a cache hit (`cached: true`): whole seconds since this copy was fetched, also sent as the `X-Cache-Age` header. Null for a copy stored before ages were recorded. Send `max_age_s` to set how old a copy you accept: a profile or post copy up to an hour old is served for 0 credits, and a lower value fetches fresh.", "example": 340 }, "idempotent_replay": { "type": "boolean", "description": "True only when this response is an idempotency replay", "example": true }, "meta": { "type": "object", "description": "Optional. Present only when this call completed a pattern that one other call does more cheaply or in one step, at most once per pattern per API key per day. Send the header `X-SocialCrawl-Hints: off` to never receive it.", "properties": { "hint": { "type": "object", "description": "One suggestion: what to call instead and why, with the price when the suggested call costs more than the calls it replaces.", "properties": { "code": { "type": "string", "description": "creator_card | batch_profiles | search_multi | incremental_sync | comment_labels | search_repeat | batch_comments | batch_jobs", "example": "search_multi" }, "message": { "type": "string", "description": "One sentence for a person or an agent to read.", "example": "You searched \"matcha\" on 3 platforms one call at a time; /v1/search/multi returns each platform's own search rows in one call at the same price per platform, and a platform with no rows is not charged." }, "method": { "type": "string", "description": "GET or POST.", "example": "GET" }, "path": { "type": "string", "description": "The call the hint points to.", "example": "/v1/search/multi?query=matcha&platforms=instagram,tiktok,youtube" } } } } }, "pagination": { "type": "object", "description": "Cursor state for this page. Present on every list response.", "properties": { "next_cursor": { "type": [ "string", "null" ], "description": "Opaque token to send back as `cursor` for the next page, or null at end-of-list. Pass it back verbatim; never decode or trim it.", "example": "sc.eyJ2IjoyLCJjIjoiMiIsInAiOiJwYWdlIn0" }, "has_more": { "type": "boolean", "description": "Explicit stop signal. Prefer this over inspecting next_cursor or comparing against total.", "example": true }, "page_size": { "type": "integer", "description": "Number of items in THIS page.", "example": 30 }, "stopped_at": { "type": [ "string", "null" ], "enum": [ "since", "known_id", "end", null ], "description": "Present only when the request sent `since` or `stop_at_id`. Why the walk stopped: `since` (this page reached a post older than the date), `known_id` (this page reached the post you already hold), `end` (the list ran out first), or null (not yet, keep walking with `next_cursor`).", "example": "known_id" }, "typical_page_size": { "type": [ "integer", "null" ], "description": "How many items a full page of this endpoint usually holds for this request, or null when it has not been verified, as on a source whose page changes with the request's parameters. An endpoint that merges several sources can return more. A page_size below it while has_more is true is a short page from the source, not the end of the list.", "example": 10 }, "next_page_credits": { "type": [ "integer", "null" ], "description": "Credits the next page costs: what sending next_cursor back holds up front, priced from that request by the same pricer that charges it. Flat endpoints charge exactly this; metered endpoints refund what the page does not use; a cached page is free. Null when there is no next page.", "example": 1 } }, "required": [ "next_cursor", "has_more", "page_size" ] } }, "required": [ "success", "platform", "endpoint", "data", "credits_used", "credits_remaining", "request_id", "cached", "pagination" ] }, "example": { "success": true, "platform": "google_news", "endpoint": "/v1/google_news/search", "data": { "items": [ { "article": { "id": "gn_2bb22cdb", "title": "Parents warned not to publicly share children’s images amid AI abuse risks", "url": "https://www.bbc.com/news/articles/cd7wj7d0jzzo", "source": "BBC", "domain": "www.bbc.com", "snippet": null, "image_url": "https://ichef.bbci.co.uk/news/480/cpsprodpb/fef8/live/2a1f8cf0-76f2-11f1-b9cc-bd5880081b3f.jpg.webp", "published_at": "2026-07-03T07:00:00Z", "rank": 1, "placement": "news_search" } }, { "article": { "id": "gn_ef3fe380", "title": "See if you can spot an AI deepfake with our test", "url": "https://www.bbc.com/news/articles/c9d2wgvg55jo", "source": "BBC", "domain": "www.bbc.com", "snippet": null, "image_url": "https://ichef.bbci.co.uk/news/480/cpsprodpb/6cc3/live/e3048a10-7b7d-11f1-9510-1546718f668b.jpg.webp", "published_at": "2026-07-11T07:00:00Z", "rank": 2, "placement": "news_search" } } ], "total": 20, "dropped": 0 }, "credits_used": 1, "request_id": "req_example000000", "cached": false, "pagination": { "next_cursor": null, "has_more": false, "page_size": 20 }, "credits_remaining": 9999 } } } }, "400": { "description": "Invalid request - missing or malformed parameters", "x-error-codes": [ "INVALID_REQUEST", "COHORT_MEMBER_LIMIT_EXCEEDED", "COHORT_LIMIT_EXCEEDED", "COHORT_IDENTITY_PLATFORM_UNSUPPORTED" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "INVALID_REQUEST", "message": "Invalid request - missing or malformed parameters", "status": 400, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "401": { "description": "Unauthorized - missing or invalid API key", "x-error-codes": [ "MISSING_API_KEY", "INVALID_API_KEY" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "MISSING_API_KEY", "message": "Unauthorized - missing or invalid API key", "status": 401, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "402": { "description": "Payment required - the account balance is too low, or the calling key has spent its own per-key credit limit", "x-error-codes": [ "INSUFFICIENT_CREDITS", "KEY_BUDGET_EXCEEDED" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "INSUFFICIENT_CREDITS", "message": "Payment required - the account balance is too low, or the calling key has spent its own per-key credit limit", "status": 402, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "404": { "description": "Not found - the endpoint does not exist, or the requested resource was not found upstream", "x-error-codes": [ "ENDPOINT_NOT_FOUND", "RESOURCE_NOT_FOUND", "RUN_NOT_FOUND", "SCHEDULE_NOT_FOUND", "STREAM_NOT_FOUND" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "ENDPOINT_NOT_FOUND", "message": "Not found - the endpoint does not exist, or the requested resource was not found upstream", "status": 404, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "405": { "description": "Method not allowed - wrong HTTP verb for this endpoint", "x-error-codes": [ "METHOD_NOT_ALLOWED" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "METHOD_NOT_ALLOWED", "message": "Method not allowed - wrong HTTP verb for this endpoint", "status": 405, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "409": { "description": "Conflict - an idempotent request is still in flight, its completed body exceeded the replay limit, or the cohort resource is not in a state that allows this operation", "x-error-codes": [ "IDEMPOTENCY_KEY_CONFLICT", "IDEMPOTENCY_IN_PROGRESS", "IDEMPOTENCY_REPLAY_UNAVAILABLE", "COHORT_IDENTITY_CONFLICT", "COHORT_QUERY_NOT_CANCELLABLE", "COHORT_QUERY_NOT_READY", "RUN_STATE_CONFLICT", "STREAM_STATE_CONFLICT" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "IDEMPOTENCY_KEY_CONFLICT", "message": "Conflict - an idempotent request is still in flight, its completed body exceeded the replay limit, or the cohort resource is not in a state that allows this operation", "status": 409, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "410": { "description": "Gone - the discover run's retention passed and its rows were deleted; start a new run. On the events feed, the cursor is older than the 30-day retention; restart from cursor=oldest", "x-error-codes": [ "RUN_EXPIRED", "CURSOR_EXPIRED" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "RUN_EXPIRED", "message": "Gone - the discover run's retention passed and its rows were deleted; start a new run. On the events feed, the cursor is older than the 30-day retention; restart from cursor=oldest", "status": 410, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "413": { "description": "Payload too large: the JSON request body exceeds the 1 MB size limit and is rejected before parsing, or a single cohort result cannot fit beneath the 1 MB response-page ceiling", "x-error-codes": [ "PAYLOAD_TOO_LARGE", "COHORT_RESULT_TOO_LARGE" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "PAYLOAD_TOO_LARGE", "message": "Payload too large: the JSON request body exceeds the 1 MB size limit and is rejected before parsing, or a single cohort result cannot fit beneath the 1 MB response-page ceiling", "status": 413, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "422": { "description": "Idempotency payload mismatch - this Idempotency-Key was already used with a different request payload; or a discover request with async=false is over what one call can answer (NEEDS_ASYNC)", "x-error-codes": [ "IDEMPOTENCY_KEY_PAYLOAD_MISMATCH", "NEEDS_ASYNC" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "IDEMPOTENCY_KEY_PAYLOAD_MISMATCH", "message": "Idempotency payload mismatch - this Idempotency-Key was already used with a different request payload; or a discover request with async=false is over what one call can answer (NEEDS_ASYNC)", "status": 422, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "429": { "description": "Rate or concurrency limit exceeded. `RATE_LIMITED`: more than 600 requests in a 1-minute sliding window on this API key (headers `X-RateLimit-Limit`/`Remaining`/`Reset`; `Retry-After` is seconds until the window resets). `CONCURRENCY_LIMIT`: more than 50 simultaneous in-flight requests (headers `X-Concurrency-Limit`/`Remaining`; short static `Retry-After`). Both are unbilled. Honor `Retry-After`, then back off with jitter. See /docs/rate-limits.", "x-error-codes": [ "RATE_LIMITED", "CONCURRENCY_LIMIT" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "RATE_LIMITED", "message": "Rate or concurrency limit exceeded. `RATE_LIMITED`: more than 600 requests in a 1-minute sliding window on this API key (headers `X-RateLimit-Limit`/`Remaining`/`Reset`; `Retry-After` is seconds until the window resets). `CONCURRENCY_LIMIT`: more than 50 simultaneous in-flight requests (headers `X-Concurrency-Limit`/`Remaining`; short static `Retry-After`). Both are unbilled. Honor `Retry-After`, then back off with jitter. See /docs/rate-limits.", "status": 429, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "500": { "description": "Internal server error - an immediate refund is attempted; credits_used reports the committed net charge and exact compensation is queued if that refund cannot commit", "x-error-codes": [ "INTERNAL_ERROR" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "INTERNAL_ERROR", "message": "Internal server error - an immediate refund is attempted; credits_used reports the committed net charge and exact compensation is queued if that refund cannot commit", "status": 500, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "502": { "description": "Upstream error - the platform returned an error; an immediate refund is attempted and credits_used reports the committed net charge", "x-error-codes": [ "UPSTREAM_ERROR" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "UPSTREAM_ERROR", "message": "Upstream error - the platform returned an error; an immediate refund is attempted and credits_used reports the committed net charge", "status": 502, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "503": { "description": "Service unavailable - the request is unbilled when rejected before deduction, otherwise an immediate refund is attempted and credits_used reports the committed net charge", "x-error-codes": [ "SERVICE_UNAVAILABLE" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "SERVICE_UNAVAILABLE", "message": "Service unavailable - the request is unbilled when rejected before deduction, otherwise an immediate refund is attempted and credits_used reports the committed net charge", "status": 503, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } }, "504": { "description": "Gateway timeout - the request was still running close to the platform time limit and is answered as UPSTREAM_ERROR, the same code as 502. An immediate refund is attempted and credits_used reports the committed net charge. When details.retry_with is set, retryable is false and there is no Retry-After", "x-error-codes": [ "UPSTREAM_ERROR" ], "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" }, "example": { "success": false, "error": { "type": "UPSTREAM_ERROR", "message": "Gateway timeout - the request was still running close to the platform time limit and is answered as UPSTREAM_ERROR, the same code as 502. An immediate refund is attempted and credits_used reports the committed net charge. When details.retry_with is set, retryable is false and there is no Retry-After", "status": 504, "doc_url": "https://www.socialcrawl.dev/docs/errors" }, "credits_used": 0, "credits_remaining": null, "request_id": "req-abc123" } } } } } } } }, "x-full-spec": "https://www.socialcrawl.dev/v1/openapi.json" }