Reducto
"The agentic document platform for leading AI teams who demand enterprise performance at scale." [1]
Reducto is a REST API for document parsing, structured data extraction, and classification, targeting AI engineering teams building agentic pipelines in industries such as insurance, healthcare, legal, and accounts payable. Pricing is usage-based starting at $0.015 per credit, with a 15,000-credit free tier and self-serve signup; Growth and Enterprise plans unlock higher rate limits, EU and AU data residency, and HIPAA BAAs. The platform is SOC 2 Type 2 certified, GDPR compliant, and offers SDKs for Python, Node.js, and Go alongside an MCP server for agent integration.
Best for / Avoid if
Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box
Avoid if: You want to try it free before paying
Scores
- 70 / 100Agent friendliness
- 85 / 100Pricing transparency
- 60 / 100Setup speed
- 65 / 100Docs quality
- 85 / 100Procurement ease
- 55 / 100Trust readiness
Pricing & procurement
- Pricing model
- Usage-based [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✗ No [4]
- Self-serve signup
- ✓ Yes [5]
- Requires sales call
- ✗ No [6]
- Enterprise plan
- ✓ Yes [7]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Standard | First 15,000 credits (one-time onboarding allotment) | 15,000 credits | $0 | source |
| Standard | Credit (after first 15K) | credit | $0.015 | source |
| Standard | Parse – standard document/image page | page | $0.015 | source |
| Standard | Parse – complex document/image page | page | $0.03 | source |
| Standard | Parse – agentic standard page | page | $0.03 | source |
| Standard | Parse – agentic complex page | page | $0.06 | source |
| Standard | Parse – advanced chart agent add-on | chart | $0.06 | source |
| Standard | Parse – spreadsheet accurate mode | 1,000 cells | $0.015 | source |
| Standard | Parse – spreadsheet fast mode | 5,000 cells | $0.015 | source |
| Standard | Parse – spreadsheet disabled mode | 5,000 cells | $0.015 | source |
| Standard | Parse – text file page | page | $0.0075 | source |
| Standard | Extract – standard page | page | $0.03 | source |
| Standard | Extract Deep (Beta) – per page | page | $0.06 | source |
| Standard | Extract Deep (Beta) – per field extracted | field | $0.0015 | source |
| Standard | Extract Deep (Beta) – minimum per document | document | $0.45 | source |
| Standard | Split – standard page | page | $0.03 | source |
| Standard | Split Deep – page | page | $0.06 | source |
| Standard | Classify – standard page | page | $0.0075 | source |
| Standard | Edit (Beta) – page | page | $0.06 | source |
| Growth | Custom pricing (volume discounts) | - | source | |
| Enterprise | Custom pricing (VPC/on-prem, custom rate limits, custom SLA) | - | source |
Capabilities
- Supported actions
- parse_document, extract_data, split_document, classify_document, edit_document, upload_file, run_pipeline, cancel_job, retrieve_job, monitor_job [8]
- Regions
- United States, European Union (EU data residency, Growth/Enterprise), Australia (AU data residency, Growth/Enterprise) [9]
- Languages
- 100+ languages (multilingual OCR with automatic language detection) [10]
- Input types
- PDF, image/png, image/jpeg, XLSX, PPTX, DOCX, scanned documents, fax, handwritten content, CSV [11]
- Output types
- JSON, Markdown, edited PDF, edited DOCX [12]
- Webhooks
- ✓ Yes [13]
- Sandbox / test mode
- ✗ No [14]
- SDK languages
- Python, Node.js, Go [15]
- MCP server
- ✓ Yes [16]
Trust & compliance
- SOC 2
- SOC 2 Type II [17]
- HIPAA
- ✓ Yes [18]
- GDPR
- ✓ Yes [19]
- ISO 27001
- ✗ No
- PCI DSS
- ✗ No
- Published SLA
- ✗ No [20]
- Rate limits
- Standard: 1 API call/second; Growth: 10 API calls/second; Enterprise: 100+ API calls/second. Job status polling: 200 requests/second. Sync endpoint concurrency limit: 200 concurrent calls. Returns HTTP 429 with exponential backoff recommendation on limit breach. [21]
- Known restrictions
- Password-protected PDFs are not processed, Standard plan limited to 1 API call/second and up to 5 Studio seats, Zero data retention (ZDR) agreements only available on Growth and Enterprise plans, BAA (HIPAA) only available on Growth and Enterprise plans, EU/AU data residency only available on Growth and Enterprise plans, VPC/on-prem deployment only available on Enterprise plan, SSO/SAML only available on Enterprise plan, Growth and Enterprise pricing requires contacting sales, First 15,000 credits are a one-time onboarding allotment, not a recurring free tier [22]
Developer surface
Integration
Adoption & maturity
- Launched
- 2024-02-27
- Notable customers
- Harvey, Scale AI, Vanta, Toast, JLL, Medallion
Other OCR & Document Parsing APIs
Amazon Textract
"Automatically extract printed text, handwriting, layout elements, and data from any document"
Veryfi
"Documents into Data - securely, in seconds"
Google Document AI
"A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume."
Azure AI Document Intelligence
"Azure Document Intelligence in Foundry Tools is a machine-learning based OCR and intelligent document processing service to automate extraction of key data from forms and documents."
Nanonets
"AI Agents for Enterprise Data Processing."
Extend
"Turn documents into high quality data"
References
- ↑Description: llms.reducto.ai · reducto.ai
- ↑Pricing model: docs.reducto.ai · reducto.ai
- ↑Published pricing: docs.reducto.ai · reducto.ai
- ↑Free tier: reducto.ai
- ↑Self-serve signup: docs.reducto.ai · reducto.ai
- ↑Requires sales call: reducto.ai
- ↑Enterprise plan: llms.reducto.ai · reducto.ai
- ↑Supported actions: docs.reducto.ai · docs.reducto.ai
- ↑Regions: docs.reducto.ai · llms.reducto.ai · reducto.ai
- ↑Languages: llms.reducto.ai · reducto.ai
- ↑Input types: llms.reducto.ai · docs.reducto.ai
- ↑Output types: docs.reducto.ai · docs.reducto.ai
- ↑Webhooks: docs.reducto.ai · docs.reducto.ai
- ↑Sandbox: reducto.ai
- ↑SDK languages: docs.reducto.ai · docs.reducto.ai
- ↑MCP server: docs.reducto.ai · docs.reducto.ai
- ↑SOC 2: llms.reducto.ai · docs.reducto.ai · reducto.ai
- ↑HIPAA: docs.reducto.ai · llms.reducto.ai
- ↑GDPR: llms.reducto.ai · reducto.ai
- ↑Published SLA: reducto.ai · reducto.ai
- ↑Rate limits: docs.reducto.ai · reducto.ai
- ↑Known restrictions: reducto.ai · docs.reducto.ai
Change history
- 2026-06-15 Score Docs Quality: 25 → 65
- 2026-06-15 Score Agent Friendliness: 45 → 70
- 2026-06-14 Openapi Spec URL: (none) → https://docs.reducto.ai/openapi.json
- 2026-06-14 Robots Allows Agents: (none) → Yes
- 2026-06-14 Has Structured Data: (none) → No
- 2026-06-14 API Reference URL: (none) → https://docs.reducto.ai/api-reference/parse
- 2026-06-14 Llms Txt URL: https://reducto.ai/llms.txt → https://docs.reducto.ai/llms.txt
- 2026-06-14 Capabilities: {} → {"agentic_output":true,"receipts_invoices":true}
- 2026-06-14 Summary Md: (none) → Reducto is a REST API for document parsing, structured data extraction, and cla…
- 2026-06-14 Score Docs Quality: 0 → 25
- 2026-06-14 Score Agent Friendliness: 30 → 45
- 2026-06-14 Rendering: (none) → static
- 2026-06-14 Llms Txt Present: (none) → Yes
- 2026-06-14 Llms Txt URL: (none) → https://reducto.ai/llms.txt
- 2026-06-14 Status Page URL: (none) → https://status.reducto.ai
- 2026-06-14 Docs URL: (none) → https://docs.reducto.ai
- 2026-06-14 Score Agent Friendliness: (none) → 30
- 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-14 Avoid If: (none) → You want to try it free before paying
- 2026-06-14 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
- 2026-06-14 Score Trust Readiness: (none) → 55
- 2026-06-14 Score Procurement Friction: (none) → 85
- 2026-06-14 Score Docs Quality: (none) → 0
- 2026-06-14 Score Setup Speed: (none) → 60
- 2026-06-14 Score Pricing Transparency: (none) → 85
- 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
- 2026-06-14 SDK Packages: Python, Node.js, Go → Python, Node.js, Go
- 2026-06-14 Starting Price Usd: 0.015 → 0.015
- 2026-06-13 Data Retention Policy URL: set to https://docs.reducto.ai/security/policies
- 2026-06-13 Documented Rate Limits: set to Standard: 1 API call/second; Growth: 10 API calls/second; Enterprise: 100+ API …
- 2026-06-13 Rate Limit Requests: set to 1000
- 2026-06-13 Rate Limit Window: set to second
- 2026-06-13 Known Restrictions: set to Password-protected PDFs are not processed, Standard plan limited to 1 API call/…
- 2026-06-13 Auth Methods: set to api_key
- 2026-06-13 Auth Docs URL: set to https://docs.reducto.ai/studio-account
- 2026-06-13 API Style: set to rest
- 2026-06-13 Base URL: set to https://platform.reducto.ai
- 2026-06-13 Versioning Scheme: set to none
- 2026-06-13 Stability: set to ga
- 2026-06-13 Deprecation Policy URL: set to https://docs.reducto.ai/reference/model-versions
- 2026-06-13 MCP URL: set to https://mcp.reducto.ai/mcp
- 2026-06-13 Quickstart URL: set to https://docs.reducto.ai/quickstart
- 2026-06-13 Idempotency Supported: set to No
- 2026-06-13 Error Format: set to vendor-specific
- 2026-06-13 Webhook Signing: set to hmac_sha256
- 2026-06-13 Webhook Events URL: set to https://docs.reducto.ai/recipes/svix-webhooks
- 2026-06-13 Requires Verification: set to No
- 2026-06-13 Starting Price Usd: set to 0.015
- 2026-06-13 Price Basis: set to credit
- 2026-06-13 Free Tier Limit: set to 15,000 credits
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/reducto \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/reducto/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'