Cohere Parse 5
Cohere's compact document parser for turning enterprise PDFs, presentations, and scans into retrieval-ready Markdown and layout metadata.
Cohere's compact document parser for turning enterprise PDFs, presentations, and scans into retrieval-ready Markdown and layout metadata.
Plain-English overview
Cohere Parse 5 extracts text in reading order along with lists, forms, key-value pairs, HTML tables, image descriptions, and the locations of visual elements. The result is designed to feed search, RAG, and agent knowledge pipelines without building a separate OCR stack.
The model is especially easy to budget for large archives because the direct API uses a page-based price. Cohere also offers private and marketplace deployment routes for organizations that cannot send sensitive files to a general SaaS endpoint.
Category comparison
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
Pricing & comparisons
Set your usage. Your estimate updates as you type.
Counts pages, not files. A 10-page PDF counts as 10 pages. The estimate uses the document-processing rate available for each model.
Cohere Parse 5
Cohere
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Availability
Available through the Cohere API, Model Vault, Microsoft Foundry, and AWS SageMaker.
Private and third-party routes keep data in the chosen environment; Cohere SaaS processing location depends on the account and agreement.
Check live availabilityData and training
Cohere enterprise customers can opt out of training; SaaS prompts and generations are generally deleted after 30 days. Private and third-party deployments do not expose customer inputs or outputs to Cohere.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Cohere's compact document parser for turning enterprise PDFs, presentations, and scans into retrieval-ready Markdown and layout metadata. Cohere Parse 5 extracts text in reading order along with lists, forms, key-value pairs, HTML tables, image descriptions, and the locations of visual elements. The result is designed to feed search, RAG, and agent knowledge pipelines without building a separate OCR stack.
Cohere Parse 5 was released on August 27, 2026 according to the cited provider materials.
Available through the Cohere API, Model Vault, Microsoft Foundry, and AWS SageMaker. The access routes listed in this guide are Cohere.
$1.50 / 1,000 pages. Cohere's direct API list price in the Parse launch announcement. Private and third-party deployments use their own pricing.
Available through the Cohere API, Model Vault, Microsoft Foundry, and AWS SageMaker. Private and third-party routes keep data in the chosen environment; Cohere SaaS processing location depends on the account and agreement.
Cohere enterprise customers can opt out of training; SaaS prompts and generations are generally deleted after 30 days. Private and third-party deployments do not expose customer inputs or outputs to Cohere. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Mistral's current Document AI OCR model for preserving reading order, tables, structure, locations, and confidence across multilingual files.
Open full comparisonGoogle Cloud's Gemini-assisted parser for preserving document hierarchy and creating context-rich chunks for enterprise search and RAG.
Open full comparisonGoogle Cloud's Gemini-powered Document AI processor for extracting the exact fields and derived values defined in a business schema.
Open full comparison