claim-grounding.prospectintel.workers.dev
Extract claims. Splits text into atomic, checkable claims with character spans, grounding_required, claim_type (number|date|quantity|quote|named_entity_fact|comparison|opinion|prediction|other) and check_worthiness (high|medium|low). Strips hedges, resolves pronouns across sentences, and splits compound sentences. $0.05 USDC.
- Category
- Other services
- Starting price
- $0.05
- Paid calls · 30 days
- 13
- Unique payers · 30 days
- 8
Paid endpoints
4 endpoints, sorted by usage. Prices are per request.
- POST/v1/extract_claims
Extract claims. Splits text into atomic, checkable claims with character spans, grounding_required, claim_type (number|date|quantity|quote|named_entity_fact|comparison|opinion|prediction|other) and check_worthiness (high|medium|low). Strips hedges, resolves pronouns across sentences, and splits compound sentences. $0.05 USDC.
$0.05Base6calls / 30d - POST/v1/check_answer
Check answer. Splits an AI answer into claims and checks each against Wikipedia, Wikidata and (for current claims) news. Returns per-claim verdict, confidence, quote, source URL and sentence, a source-quoted suggested_correction for wrong claims, and an answer summary with problem_sentences. $1.00 USDC.
$1.00Base3calls / 30d - POST/v1/deep_verify
Deep verify. Use when a claim is high-stakes, or when Check answer or Extract claims marks it unsure (next_step). Checks it against Wikipedia, Wikidata, Google News, Europe PMC studies, FRED economic data and SEC EDGAR filings, and flags contradiction when sources disagree. Async: returns a job_id; poll GET /v1/jobs/{id} free for verdict, evidence for and against, citations. $0.75 USDC.
$0.75Base3calls / 30d - POST/v1/verify_claim
Verify claim. Checks one factual claim against public sources (Wikipedia) and returns a verdict (supported, contradicted, outdated, mixed or insufficient_evidence) with confidence, a short reason, the quote and source URL, and a receipt. $1.00 USDC.
$1.00Base1calls / 30d