ActionMistral AIUpdated June 2026

How do I OCR a document with Mistral?

Short answer: You can mistral ocr (document → markdown) in Mistral AI by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Mistral AI Mistral OCR (Document → Markdown) action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Mistral OCR (Document → Markdown) in Mistral AI — start free
Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

FieldTypeRequiredDescription
Model
model
optionsRequiredModel. Options: Mistral OCR (latest)
Document URL
document_url
stringRequiredPublic URL to a PDF or image
Include Image Base64
include_image_base64
optionsOptionalInclude Image Base64. Options: No, Yes (returns extracted images)
Sample request
{
"model": "{{trigger.model}}",
"document_url": "https://example.com/report.pdf",
"include_image_base64": "{{trigger.include_image_base64}}"
}
Returns
{
"model": "mistral-ocr-latest",
"pages": [
{
"index": 0,
"images": [],
"markdown": "# Report\n\nSection 1...",
"dimensions": {
"width": 1224,
"height": 1584
}
}
],
"usage_info": {
"doc_size_bytes": 50000,
"pages_processed": 1
}
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Mistral OCR (Document → Markdown).

Any of these apps can fire this action as part of a workflow.

FAQ

Questions about Mistral OCR (Document → Markdown).

What does the Mistral OCR (Document → Markdown) action do in Mistral AI?
Mistral's specialised OCR model — converts PDFs/images to clean Markdown preserving headings, tables, multi-column layout. Better than general vision-LLM OCR for structured document processing.
What inputs does Mistral OCR (Document → Markdown) require?
Required: Model, Document URL. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Mistral AI returns an error?
The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.
Does Mistral OCR (Document → Markdown) support batch operations?
Yes. Run Mistral OCR (Document → Markdown) inside a Loop node to process arrays. TinyCommand handles Mistral AI's rate limits automatically so you don't have to throttle manually.
More actions

Other Mistral AI actions.

Action
Mistral Chat Completion
Runs chat completion against Mistral's hosted models (Small, Medium, Large, Codestral, Mixtral variants, Pixtral). OpenAI-compatible shape. EU-hosted inference for data-residency-conscious workflows.
Action
Mistral Chat with Tools
Chat completion with function-calling enabled. OpenAI-compatible tools array. Response includes tool_calls when the model decides to call one. Parallel tool calls supported.
Action
Mistral Embedding
Generates embeddings with mistral-embed. For RAG-pipeline vector generation when you want EU-hosted embedding inference.
Action
List Mistral Models
Returns the Mistral model catalog. Pin specific versions for reproducibility; "latest" aliases float as Mistral ships new generations.
Action
Mistral Moderate Text
Returns category scores across harm types (violence, hate, sexual, self-harm, etc.). For pre-filter step before higher-cost LLM calls or for content-moderation workflows in user-generated content.
Mistral OCR (Document → Markdown) in Mistral AI — start free