PDF to Text
Convert PDF to text for AI and LLMs
Turn any PDF, scanned or digital, into clean, LLM-ready text with one API call. Layout, reading order, and tables preserved.
For coding agents
Using Claude Code, Cursor, or other coding agents?
Prefer a native integration? Add the Reducto MCP server and your agent can parse documents inline, no SDK code required.
# Authenticate once
uvx mcp-server-reducto --login
# Add to Claude Code
claude mcp add reducto -- uvx mcp-server-reductoQuickstart
Convert a PDF to text in minutes
From sign-up to clean, LLM-ready text. No OCR to configure, no infrastructure to manage.
01
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"02
Install the SDK
pip install reducto03
Convert your PDF to text
Pass a file or URL to /parse. Reducto runs OCR, detects layout, and returns clean text in reading order.
from reducto import Reducto
client = Reducto()
result = client.parse.run(
input="https://cdn.reducto.ai/samples/fidelity-example.pdf"
)
text = "\n\n".join(chunk.content for chunk in result.result.chunks)
print(text)04
Use the text output
Every chunk returns clean Markdown text plus a vector-optimized embed field and bounding boxes, ready for RAG, embeddings, and agents.
{
"job_id": "5df31070-...",
"usage": { "num_pages": 3, "credits": 4.0 },
"result": {
"chunks": [{
"content": "## Your Portfolio Value: $274,222.20\n...",
"embed": "Your Portfolio Value: $274,222.20 ...",
"blocks": [{ "type": "Text", "bbox": { "page": 1 } }]
}]
},
"studio_link": "https://studio.reducto.ai/job/..."
}FAQ
PDF to text questions
Start converting
Turn your PDFs into clean text
Drop a PDF in Studio, or hit the API with a single call. No setup, no credit card.
