Mistral OCR PDF

CLI tool to convert PDFs to markdown using Mistral OCR.

Installation

pip install mistral-ocr-pdf
# or with uv
uv pip install mistral-ocr-pdf

Usage

Convert a PDF to markdown:

mistral-ocr-pdf input.pdf
# Output will be saved as input.md

Specify output file:

mistral-ocr-pdf -o output.md input.pdf

Save raw OCR response JSON for debugging:

mistral-ocr-pdf --output-json response.json input.pdf

API Key Configuration

The Mistral API key can be configured in three ways:

Environment variable:

export MISTRAL_API_KEY="sk-xxxx"
mistral-ocr-pdf input.pdf

Config file:

mistral-ocr-pdf -sk api_key -sv "sk-xxxx"
# This saves the key to ~/.config/mistral_ocr_pdf/config.json

Direct config file editing: Create or edit ~/.config/mistral_ocr_pdf/config.json with:
```
{
  "api_key": "sk-xxxx"
}
```

Run with uv

You can also run the tool directly with uvx:

uvx mistral-ocr-pdf input.pdf

Metadata

Release files for mistral-ocr-pdf 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mistral-ocr-pdf 0.1.0
File	Size	Uploaded	Provenance
mistral_ocr_pdf-0.1.0.tar.gz	4.8 kB	Apr 30, 2025	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for mistral-ocr-pdf 0.1.0
File	Interpreter	ABI	Platform	Reset
mistral_ocr_pdf-0.1.0-py3-none-any.whl 5.5 kB Apr 30, 2025 Without provenance	Python 3	none	any	Details

Total release size: 10.3 kB

Release files / mistral_ocr_pdf-0.1.0.tar.gz

Download URL	mistral_ocr_pdf-0.1.0.tar.gz
Size	4.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`0c233c5e594d31dfeca04191d2f41ed94e48b9c069c59cf116d0d622d7ada47e`
BLAKE2b-256 checksum How to use checksums	`4a1f5ce85c79acfec35ef2a500f5cd3aba105bb25f1da971443680bba1ebdf76`
Upload date	Apr 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.7`

Release files / mistral_ocr_pdf-0.1.0-py3-none-any.whl

Download URL	mistral_ocr_pdf-0.1.0-py3-none-any.whl
Size	5.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`9caf329be2b6170b75c52760b33b7ad2fb40bee701798f3319c05fb59b7ba5b9`
BLAKE2b-256 checksum How to use checksums	`d1ec51b06fa23c35829a007f89d84da992edbe5055074cd685ebb561421d284f`
Upload date	Apr 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.7`

Security for mistral-ocr-pdf 0.1.0

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

Apr 30, 2025 2 release files No provenance

mistral-ocr-pdf 0.1.0