One API for
every document
Parse, extract, classify, split, and edit 30+ file types. Production-ready structured JSON in minutes, not months.
from reducto import Reducto
client = Reducto()
result = client.parse.run(
input="https://cdn.reducto.ai/samples/fidelity-example.pdf"
)
for chunk in result.result.chunks:
print(chunk.content)Get started in five minutes
From sign-up to structured JSON output. No infrastructure to set up, no models to manage.
Get your API key
Sign up at studio.reducto.ai and create an API key. Set it as an environment variable.
export REDUCTO_API_KEY="your_api_key_here"Install the SDK
pip install reductoParse your first document
A few lines of code to convert any document into structured JSON with text, tables, and figures.
from reducto import Reducto
client = Reducto()
result = client.parse.run(
input="https://cdn.reducto.ai/samples/fidelity-example.pdf"
)
print(f"Processed {result.usage.num_pages} pages")
for chunk in result.result.chunks:
print(chunk.content)Use the structured output
Every response returns chunks with typed blocks (Title, Table, Text, Figure) plus bounding box coordinates and a link to inspect results in Studio.
{
"job_id": "5df31070-...",
"usage": { "num_pages": 3, "credits": 4.0 },
"result": {
"chunks": [{
"content": "## Your Portfolio Value: $274,222.20\n...",
"blocks": [{
"type": "Table",
"bbox": { "page": 1, "left": 0.516 }
}]
}]
},
"studio_link": "https://studio.reducto.ai/job/..."
}The full document lifecycle
Five API endpoints plus a visual Studio for building, testing, and deploying workflows. Supports 30+ file types.
/parseConvert any document into structured JSON with text, tables, and figures. Layout-aware chunking optimized for LLMs.
/extractDefine a JSON schema and pull specific fields from documents. Get exactly the data you need, nothing more.
/classifyRoute documents by type before processing. Define categories in natural language, no training data required.
/splitDivide documents into logical sections using natural language descriptions for targeted downstream processing.
/editFill PDF forms and modify DOCX files programmatically with natural language instructions.
/studioBuild, test, and deploy document workflows visually. Inspect results with bounding-box-level citations.
Build your way
SDKs, CLI, and MCP integrations. Pick the tools that fit your workflow.
SDKs
First-class clients for Python, Node.js, and Go with full type safety. Install and authenticate in seconds.
View SDK docsCLI
Parse, extract, and manage documents from your terminal. Pipe output into other tools or scripts.
View CLI docsMCP Server
Connect AI agents to Reducto via the Model Context Protocol. Works with Claude, Cursor, VS Code, and more.
View MCP docsBuilt for production
3B+ pages processed. Autoscaling infrastructure with dedicated support for enterprise customers.
SOC 2 Type II & HIPAA
Audited security controls with BAA available on Growth and Enterprise tiers.
Deploy anywhere
SaaS, hybrid VPC, full VPC, or air-gapped on-premises. EU and AU regional endpoints available.
Zero data retention
Zero data retention policy available. 99.9%+ uptime SLA with dedicated enterprise support.
Everything you need
Documentation
Comprehensive guides, API references, and configuration options for every endpoint.
Browse docsAPI Reference
Full OpenAPI spec with request/response schemas, error codes, and rate limits.
View API referenceCookbooks
Step-by-step guides for invoice extraction, contract review, multilingual processing, RAG pipelines, and more.
Explore cookbooksBlog
Engineering deep dives, product announcements, benchmarks, and best practices from the Reducto team.
Read the blog