Semantic Scholar API
AI2's academic paper search API with citation graphs, author data, full-text search, and paper embeddings for semantic similarity — free with optional API key for higher limits.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Simple API key with no scopes. Read-only public academic data. No sensitive data exposure risk.
⚡ Reliability
Best When
Building research agents that need citation graph traversal, author tracking, and semantic similarity search beyond simple keyword matching.
Avoid When
You specifically need arXiv preprints (use arXiv API directly) or medical/clinical literature (use PubMed).
Use Cases
- • Finding semantically similar papers using Semantic Scholar's embedding-based recommendations
- • Tracing citation networks to understand the influence and lineage of research papers
- • Building research agents that fetch paper metadata, abstracts, and author information
- • Monitoring an author's or institution's publication output via author API
- • Automated literature reviews using full-text keyword + semantic ranking for relevance
Not For
- • Full paper text extraction for bulk processing (Semantic Scholar provides metadata/abstracts, not full PDFs)
- • Real-time paper detection — new papers appear with 1-2 day delay
- • Papers not indexed by Semantic Scholar (strong in CS/AI, weaker in humanities)
Interface
Authentication
No auth required for basic access (100 requests/5min). Free API key registration unlocks 1000 requests/5min. Key passed as x-api-key header.
Pricing
Completely free. API key registration is free and recommended for production agents.
Agent Metadata
Known Gotchas
- ⚠ fields parameter controls which fields are returned — default returns minimal fields; must explicitly request abstract, citations, references, embeddings
- ⚠ Bulk paper retrieval via /paper/batch accepts up to 500 paper IDs — more efficient than individual requests for agent pipelines
- ⚠ Citation/reference traversal is paginated with 1000 max per page — deep citation trees require many requests
- ⚠ Paper embeddings (specter2) are available but require explicit fields=embedding parameter — useful for semantic similarity
- ⚠ External paper IDs (arXiv, DOI, PubMed) can be used as identifiers with prefix: ArXiv:2301.00001, DOI:10.xxx
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Semantic Scholar API.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-07.