{ "name": "Mistral Document AI (Mistral OCR)", "slug": "mistral-document-ai", "website_url": "https://mistral.ai/news/mistral-ocr", "vendor_description": "\"The world's best document extraction and understanding model.\"", "categories": [ "ocr" ], "summary": "Mistral Document AI (Mistral OCR) is a REST API for extracting text, tables, images, and structured data from PDFs and scanned documents, with support for multilingual content, mathematical notation, and custom-prompt document annotation. Pricing is usage-based at $2.00 per 1,000 pages with self-serve signup and no sales call required, plus enterprise plans for larger volumes. The API carries SOC 2 Type 2, ISO 27001, and GDPR certifications, and counts BNP Paribas, HSBC, BMW, SAP, and Snowflake among its customers. Python and TypeScript SDKs are available, and processing can be directed to either EU or US infrastructure.", "capabilities": { "supported_actions": [ "ocr_process (POST /v1/ocr)", "extract_text_markdown", "extract_images_base64", "extract_tables_markdown_or_html", "extract_headers_footers", "extract_bounding_boxes", "confidence_scoring_per_word_or_page", "structured_json_annotation", "document_annotation_with_custom_prompt", "batch_ocr (via /v1/batch)", "page_selection", "document_qna (via /v1/chat/completions with OCR model)" ], "supported_regions": [ "European Union (default)", "United States" ], "supported_languages": [ "Russian", "French", "Hindi", "Chinese", "Portuguese", "German", "Spanish", "Turkish", "Ukrainian", "Italian", "Romanian", "40+ languages total (multilingual, thousands of scripts and fonts)" ], "input_types": [ "PDF", "PNG", "JPG", "JPEG", "TIFF", "BMP", "GIF", "WEBP", "AVIF", "PPTX", "DOCX", "document_url", "base64_encoded_document", "image_url" ], "output_types": [ "JSON", "Markdown", "HTML (for tables)" ], "webhooks_supported": false, "sandbox_available": false, "sdk_languages": [ "Python", "TypeScript" ], "mcp_server_available": false }, "integration": { "api_style": "rest", "base_url": "https://api.mistral.ai/v1", "api_version": "v1", "versioning_scheme": "url", "stability": "ga", "deprecation_policy_url": "https://docs.mistral.ai/getting-started/models", "auth_methods": [ "api_key" ], "auth_docs_url": "https://docs.mistral.ai/getting-started/quickstarts/studio/activate-and-generate-api-key", "idempotency_supported": null, "error_format": "vendor-specific", "webhook_signing": null, "webhook_events_url": null, "rate_limit_requests": null, "rate_limit_window": null, "sdk_packages": [ { "package": "mistralai", "language": "Python", "official": true, "repo_url": "https://github.com/mistralai/client-python" }, { "package": "@mistralai/mistralai", "language": "TypeScript", "official": true, "repo_url": "https://github.com/mistralai/client-ts" } ], "mcp_url": null, "quickstart_url": "https://docs.mistral.ai/getting-started/quickstarts/developer/first-api-request" }, "pricing": { "pricing_model": "usage_based", "has_published_pricing": true, "starting_price_usd": "2.0000", "price_basis": "1,000 pages", "free_tier_available": false, "free_tier_limit": null, "free_tier_details": null, "minimum_commitment": null, "self_serve_signup": true, "requires_sales_call": false, "requires_verification": false, "enterprise_plan_available": true, "price_points": [ { "plan": null, "item": "Document extraction (OCR) — standard", "amount_usd": "2.0000", "amount_percent": null, "per": "1,000 pages", "currency": "USD", "source_url": "https://mistral.ai/pricing/" }, { "plan": null, "item": "Annotated pages (structured JSON extraction)", "amount_usd": "3.0000", "amount_percent": null, "per": "1,000 annotated pages", "currency": "USD", "source_url": "https://mistral.ai/pricing/" }, { "plan": "Batch API", "item": "Document extraction (OCR) — batch (50% discount)", "amount_usd": "1.0000", "amount_percent": null, "per": "1,000 pages", "currency": "USD", "source_url": "https://mistral.ai/news/mistral-ocr-3/" } ] }, "compliance": { "soc2": "type_2", "hipaa": false, "gdpr": true, "iso_27001": true, "pci_dss": null, "sla_published": false, "sla_url": null, "data_retention_policy_url": "https://legal.mistral.ai/terms/privacy-policy", "documented_rate_limits": "Rate limits are applied at the Workspace level and vary by usage tier. They include: Requests per second (RPS), Tokens per minute, Tokens per month. Tiers advance based on cumulative billing: Free mode (default, limited, evaluation/prototyping), Tier 2 (>$20), Tier 3 (>$100), Tier 4 (>$500), Custom (>$2,000, contact support).", "known_restrictions": [ "Maximum file size for uploads: 512 MB", "Maximum image size: 20 MB per image", "Uploaded files are retained for 30 days unless deleted earlier", "Batch jobs support up to 1 million requests per batch", "Rate limits vary by subscription tier", "On-premises and cloud partner deployment available for self-hosting use cases" ] }, "developer": { "docs_url": "https://docs.mistral.ai", "api_reference_url": "https://docs.mistral.ai/api", "openapi_spec_url": "https://docs.mistral.ai/openapi.yaml", "postman_collection_url": null, "changelog_url": null, "status_page_url": "https://status.mistral.ai", "llms_txt_url": "https://docs.mistral.ai/llms.txt", "markdown_docs_url": null, "rendering": "static" }, "adoption": { "launched_at": "2025-03-06", "ga_date": "2025-03-06", "github_stars": null, "github_stars_at": null, "notable_customers": [ "BNP Paribas", "HSBC", "ASML", "CMA CGM", "BMW", "IBM", "SAP", "Stellantis", "Snowflake", "AXA", "Cisco", "Ericsson", "Orange", "TotalEnergies" ] }, "scores": { "agent_friendliness": 50, "pricing_transparency": 85, "setup_speed": 55, "docs_quality": 65, "procurement_friction": 85, "trust_readiness": 55, "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" ] }, "sources": [ { "field": "vendor_description", "url": "https://mistral.ai/news/mistral-ocr/", "excerpt": "Optical Character Recognition API that sets a new standard in document understanding", "confidence": "high" }, { "field": "vendor_description", "url": "https://mistral.ai/pricing/", "excerpt": "The world's best document extraction and understanding model.", "confidence": "high" }, { "field": "primary_use_cases", "url": "https://mistral.ai/news/mistral-ocr/", "excerpt": "Digitizing scientific research, Preserving historical and cultural heritage, Streamlining customer service, converting technical literature, engineering drawings, lecture notes, presentations, regulatory filings", "confidence": "high" }, { "field": "primary_use_cases", "url": "https://mistral.ai/news/mistral-ocr-3/", "excerpt": "Automated parsing of forms, invoices, and operational documents; End-to-end document understanding pipelines; Digitization of handwritten or historical documents", "confidence": "high" }, { "field": "supported_actions", "url": "https://docs.mistral.ai/studio-api/document-processing/basic_ocr", "excerpt": "confidence_scores_granularity … \"word\" … \"page\" … extract_header and extract_footer: Enable separate header/footer extraction (OCR 2512+) … table_format: Control table output as null, markdown, or HTML", "confidence": "high" }, { "field": "supported_languages", "url": "https://mistral.ai/news/mistral-ocr/", "excerpt": "Natively multilingual … parse, understand, and transcribe thousands of scripts, fonts, and languages", "confidence": "high" }, { "field": "input_types", "url": "https://docs.mistral.ai/studio-api/document-processing/basic_ocr", "excerpt": "Images: PNG, JPEG/JPG, AVIF, and more … Documents: PDF, PPTX, DOCX, and additional formats", "confidence": "high" }, { "field": "supported_actions", "url": "https://docs.mistral.ai/api/endpoint/ocr", "excerpt": "POST /v1/ocr … bbox_annotation_format … confidence_scores_granularity … extract_header, extract_footer … pages … table_format … image_limit … include_image_base64", "confidence": "high" }, { "field": "supported_regions", "url": "https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data", "excerpt": "By default, your data is hosted in the European Union. You may, however, explicitly use our US API endpoint and in such case your data is hosted in the United States.", "confidence": "high" }, { "field": "supported_languages", "url": "https://docs.mistral.ai/studio-api/document-processing/basic_ocr", "excerpt": "Strong performance across 40+ languages", "confidence": "high" }, { "field": "input_types", "url": "https://docs.mistral.ai/resources/known-limitations", "excerpt": "OCR … PDF, PNG, JPG, JPEG, TIFF, BMP, GIF, WEBP", "confidence": "high" }, { "field": "output_types", "url": "https://docs.mistral.ai/api/endpoint/ocr", "excerpt": "{\"pages\": [{\"index\": integer, \"markdown\": string, \"images\": array, \"dimensions\": {\"dpi\": integer, \"height\": integer, \"width\": integer}}], \"model\": string, \"usage_info\": {\"pages_processed\": integer}}", "confidence": "high" }, { "field": "sdk_languages", "url": "https://docs.mistral.ai/getting-started/quickstarts/developer/first-api-request", "excerpt": "Python … pip install mistralai … TypeScript … import { Mistral } from \"@mistralai/mistralai\"", "confidence": "high" }, { "field": "pricing_model", "url": "https://mistral.ai/news/mistral-ocr-3/", "excerpt": "$2 per 1,000 pages … 50% Batch-API discount, reducing the cost to $1 per 1,000 pages", "confidence": "high" }, { "field": "has_published_pricing", "url": "https://docs.mistral.ai/models/ocr-3-25-12", "excerpt": "$2 per 1,000 pages (standard OCR) … $3 per 1,000 annotated pages (with structured annotations)", "confidence": "high" }, { "field": "self_serve_signup", "url": "https://mistral.ai/technology/", "excerpt": "Start building", "confidence": "high" }, { "field": "enterprise_plan_available", "url": "https://mistral.ai/pricing/", "excerpt": "Private deployments powered by custom models, UI, and tools … audit logs, SAML SSO, and white label options", "confidence": "high" }, { "field": "soc2", "url": "https://help.mistral.ai/en/articles/347638-do-you-have-soc-2-or-iso-27001-certification", "excerpt": "Yes, Mistral complies with both SOC 2 Type II and ISO 27001/27701 frameworks.", "confidence": "high" }, { "field": "gdpr", "url": "https://legal.mistral.ai/terms/privacy-policy", "excerpt": "We prioritize selecting providers within the European Union that strictly adhere to the GDPR … We attach the most recent version of the European Commission's Standard Contractual Clauses to all such contracts.", "confidence": "high" }, { "field": "iso_27001", "url": "https://help.mistral.ai/en/articles/347638-do-you-have-soc-2-or-iso-27001-certification", "excerpt": "Yes, Mistral complies with both SOC 2 Type II and ISO 27001/27701 frameworks.", "confidence": "high" }, { "field": "documented_rate_limits", "url": "https://help.mistral.ai/en/articles/698531-why-am-i-hitting-api-rate-limits-and-how-do-i-increase-them", "excerpt": null, "confidence": "high" }, { "field": "known_restrictions", "url": "https://docs.mistral.ai/api/endpoint/files", "excerpt": "The size of individual files can be a maximum of 512 MB.", "confidence": "high" }, { "field": "auth_methods", "url": "https://docs.mistral.ai/getting-started/quickstarts/developer/first-api-request", "excerpt": "export MISTRAL_API_KEY=\"your_api_key_here\"", "confidence": "high" }, { "field": "base_url", "url": "https://docs.mistral.ai/api", "excerpt": "https://api.mistral.ai/v1", "confidence": "high" }, { "field": "error_format", "url": "https://docs.mistral.ai/getting-started/quickstarts/developer/first-api-request", "excerpt": "401 Unauthorized: Verify the environment variable is correctly set … 402 Payment Required: Add a payment method … 429 Too Many Requests: Implement exponential backoff retry logic", "confidence": "medium" }, { "field": "starting_price_usd", "url": "https://docs.mistral.ai/models/ocr-3-25-12", "excerpt": "$2 per 1,000 pages (standard OCR)", "confidence": "high" }, { "field": "notable_customers", "url": "https://mistral.ai/customers/", "excerpt": "HSBC boosts productivity with Mistral … BNP Paribas … AXA empowers employees … ASML accelerates advanced semiconductor lithography … CMA CGM streamlines global maritime operations … BMW … IBM … SAP … Stellantis … Snowflake … Cisco … Ericsson … Orange … TotalEnergies", "confidence": "high" }, { "field": "output_types", "url": "https://docs.mistral.ai/studio-api/document-processing/basic_ocr", "excerpt": "The main output and raw markdown content … Tables can be returned as HTML via table_format=\"html\" parameter … Available when table_format=\"markdown\"", "confidence": "high" }, { "field": "sdk_languages", "url": "https://docs.mistral.ai/resources/sdks", "excerpt": "We strongly recommend using the official SDKs to interact with our APIs. … pip install mistralai", "confidence": "high" }, { "field": "pricing_model", "url": "https://mistral.ai/pricing/", "excerpt": "OCR $2 / 1000 pages … Annotations $3 / 1000 pages", "confidence": "high" }, { "field": "has_published_pricing", "url": "https://mistral.ai/pricing/", "excerpt": "OCR $2 / 1000 pages … Annotations $3 / 1000 pages", "confidence": "high" }, { "field": "free_tier_available", "url": "https://mistral.ai/pricing/", "excerpt": "OCR $2 / 1000 pages … Annotations $3 / 1000 pages", "confidence": "medium" }, { "field": "self_serve_signup", "url": "https://docs.mistral.ai/getting-started/quickstarts/developer/first-api-request", "excerpt": "Open Studio›API keys, click Create new key, give the key a name and click Create.", "confidence": "high" }, { "field": "enterprise_plan_available", "url": "https://mistral.ai/news/mistral-ocr-3/", "excerpt": "Mistral OCR offers a self-hosting option … interested parties directed to contact sales", "confidence": "high" }, { "field": "soc2", "url": "https://trust.mistral.ai/resources", "excerpt": null, "confidence": "high" }, { "field": "gdpr", "url": "https://help.mistral.ai/en/collections/789670-regulatory-compliance-and-certification", "excerpt": null, "confidence": "high" }, { "field": "documented_rate_limits", "url": "https://docs.mistral.ai/deployment/ai-studio/tier", "excerpt": "Requests per second (RPS): the maximum number of concurrent API requests … Tokens per minute … Monthly token consumption caps … Tier 2 (> $20 / €20) … Tier 3 (> $100 / €100) … Tier 4 (> $500 / €500) … Custom (> $2,000 / €2,000)", "confidence": "high" }, { "field": "known_restrictions", "url": "https://docs.mistral.ai/resources/known-limitations", "excerpt": "Maximum file size: 512 MB … Maximum image size: 20 MB per image … Maximum requests per batch: 100,000 … Uploaded files are retained for 30 days unless deleted earlier", "confidence": "high" }, { "field": "auth_methods", "url": "https://docs.mistral.ai/api", "excerpt": "Authorization: Bearer YOUR_APIKEY_HERE", "confidence": "high" }, { "field": "api_style", "url": "https://docs.mistral.ai/api/endpoint/ocr", "excerpt": "POST /v1/ocr … Required: model (string) … document (object)", "confidence": "high" }, { "field": "api_version", "url": "https://docs.mistral.ai/api", "excerpt": "https://api.mistral.ai/v1 … /v1/chat/completions … /v1/ocr", "confidence": "high" }, { "field": "starting_price_usd", "url": "https://mistral.ai/pricing/", "excerpt": "OCR $2 / 1000 pages", "confidence": "high" }, { "field": "launched_at", "url": "https://mistral.ai/news/mistral-ocr/", "excerpt": "March 6, 2025", "confidence": "high" }, { "field": "notable_customers", "url": "https://mistral.ai/solutions/", "excerpt": "BNP Paribas leverages our models across global markets, sales, and customer support … AXA empowers 140,000+ employees with secure AI capabilities … CMA CGM deployed MAIA … serving 155,000+ employees across 160 countries", "confidence": "high" } ], "fields_not_found": [ "pci_dss", "exact per-model rate limits (RPS/TPM numbers not published)", "maximum pages per OCR request", "sla_url", "rate_limit_requests", "rate_limit_window", "idempotency_supported", "webhook_signing", "webhook_events_url", "mcp_url", "free_tier_limit", "deprecation_policy_url" ], "source_confidence": "high", "last_verified_at": "2026-06-14T00:00:00.000Z", "contribute": { "note": "This data is crowd-editable. Suggest corrections or leave a review via these endpoints - no auth required, requests are rate-limited, and every submission is reviewed before it goes live. For a field edit, {field} is any key in this response and a citation is required.", "endpoints": [ { "action": "review", "label": "Leave a review or comment", "method": "POST", "url": "https://apio.sh/api/feedback/mistral-document-ai", "example_body": { "kind": "review", "rating": 5, "body": "Your experience with this API…" } }, { "action": "field_edit", "label": "Suggest a correction to a field (cite a source)", "method": "POST", "url": "https://apio.sh/api/suggest/mistral-document-ai/{field}", "example_body": { "value": "corrected value", "citations": [ { "url": "https://source.example/page", "excerpt": "supporting quote" } ], "note": "what changed and why" } }, { "action": "new_api", "label": "Suggest a new API to add", "method": "POST", "url": "https://apio.sh/api/suggest/api", "example_body": { "value": { "name": "Acme API", "website_url": "https://acme.example" }, "citations": [ { "url": "https://acme.example" } ] } }, { "action": "token", "label": "Optional - raise your rate limit", "method": "GET", "url": "https://apio.sh/api/feedback/token" } ] } }