Sold by: Cohere
Deployed on AWS
Cohere Parse 5 is a high-performance document vision parser.
Overview
Cohere Parse 5 is a high-performance, cost-effective document vision parser that delivers market-leading document understanding at its size and price range. The gateway to enterprise document intelligence, Parse 5 transforms complex, multilingual documents into structured, machine-readable content for high-throughput AI workloads.
Primary use case: parse document images into structured, machine-readable content (Markdown or content blocks) for downstream AI workloads such as retrieval, grounding, and document automation.
Known limitations: image input only; PDF and file URL inputs are not supported and must be pre-rendered to images; chart/graph extraction, confidence scores, citations, and JSON/plain-text/XLSX/HTML document output formats are not supported; on SageMaker, remote image URLs cannot be fetched, base64 data URIs only.
Highlights
- Best-in-class value: outperforms leading document parsers and hyperscaler services while remaining cost-effective at enterprise scale. Save over 60% of inference costs compared with competitors such as Mistral OCR 4, while achieving higher quality, agent-ready parsing.
- Beyond OCR: Understands tables, forms, diagrams, and images to extract richer semantic context across major global commercial languages.
- Spatially aware: Returns bounding boxes alongside extracted visual elements, enabling downstream retrieval, grounding, and automation use cases.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.xlarge Inference (Batch) Recommended | Model inference on the ml.g5.xlarge instance type, batch mode | $2.51 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.51 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $2.51 |
ml.p5.4xlarge Inference (Real-Time) | Model inference on the ml.p5.4xlarge instance type, real-time mode | $3.36 |
Dimensions summary
You pay by the hour for running Parse v5 on an AWS machine learning instance. Pricing depends on two choices: the instance type and the inference mode. Instance types range across ml.g5.xlarge, ml.g5.2xlarge, and ml.p5.4xlarge, which differ in compute power. Inference mode can be batch or real-time. The ml.g5.xlarge supports both batch and real-time modes. The ml.g5.2xlarge and ml.p5.4xlarge each support real-time mode only. Costs scale with how many host-hours you run and which instance you select. Larger instances carry different hourly rates than smaller ones.
Top-of-mind questions for buyers
You pay for each hour your chosen instance runs Parse v5, whether or not it actively processes documents. The software meter counts running time, not document volume. Stopping the instance halts software charges, though AWS may still bill underlying storage. Each instance type has its own hourly rate.
Both modes bill per host-hour on the running instance. Real-time mode serves live requests through a persistent endpoint. Batch mode processes documents in grouped jobs. Only ml.g5.xlarge offers both modes; ml.g5.2xlarge and ml.p5.4xlarge run in real-time mode only.
Parse v5 converts PDF, PPT, and Base64-encoded JPEG files into Markdown output. It handles a context length of 8192 tokens. The model is stable for nine input languages and can attempt others, though accuracy may be lower. These capabilities are the same across all instance types.
docs.cohere.com
Helpful?
Vendor refund policy
No refund
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
We’re thrilled to announce the release of Parser, the most recent entrant into the Embed family of enterprise-focused large language models (LLMs).
Parser is Cohere’s most performant search model to date - the model supports the following new features:
- Matryoshka Embeddings in the following dimensions: [256, 512, 1024, 1536]
- Unified Embeddings from mixed modality input (i.e. a single payload of image(s) and text(s))
- Context length of 128k
Parser is State of the Art in the following areas:
- Text to Text Retrieval
- Text to Image Retrieval
- Text to Mixed Modality Retrieval (e.g. PDFs)
Additional details
Inputs
- Summary
This model accepts JSON requests that specifies a content object which can contain a list of texts, a list of data urls of a base64 encoded images or combination. This model supports interleaved images and texts in the same request.
{ ""content"": [ { ""type"": ""text"", ""text"": ""Look at my awesome car!"" }, { ""type"": ""image_url"", ""image_url"": f""data:image/png;base64,{base64_image}"" }, { ""type"": ""text"", ""text"": ""Do you want to buy it?"" }, ]
- Input MIME type
- application/json
"{
""content"": [
{ ""type"": ""text"", ""text"": ""Look at my awesome car!"" },
{ ""type"": ""image_url"", ""image_url"": ""data:image/png;base64,{base64_image}"" },
{ ""type"": ""text"", ""text"": ""Do you want to buy it?"" }
],
""input_type"": ""search_document"",
“embedding_types”: [""int8”],
""max_tokens"":8000,
“output_dimensions”: 1024
}"
N/a batch job unavailable
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | "A list of dicts with the key: “content” which is a list with type which is either text or image_url and then if type='text' then there is a text key with a string. If type=image_url then its a data url formatted base64 encoded image and an image key.
The max pixels per image is 2,458,624, the max memory size of a single request is 20mb, and then inputs objects can have at most 96 inputs.
The inputs object can have a maximum of 800,000 tokens which is calculated as follows:
1) For each image: image pixels / 784 (pixels per token) = tokens
2) For each text: text tokens
3) Total inputs object = For each input, summation of (1) and (2)" | - | No |
texts | An array of strings for the model to embed. Maximum number of texts per call is 96. If you are using the texts parameter you cannot use the images parameter in the same call. | - | No |
images | An array of base 64 encoded data url as strings to embed. Maximum number of images per call is 96. You cannot send both an array of texts and images at the same time, | - | No |
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Embed 5 is Cohere's most powerful embedding family yet, delivering frontier retrieval on complex enterprise data that matches or exceeds the competition and makes major gains on Embed 4.
Cohere provides a representative AI model: Embed that translates text into numerical vectors that models can understand.
Embed 5 is Cohere's most powerful embedding family yet, delivering frontier retrieval on complex enterprise data that matches or exceeds the competition and makes major gains on Embed 4.
Rerank 5 Fast is Cohere's speed-optimized reranking model, built for high-volume, latency-sensitive search and agents. It outperforms our previous flagship, Rerank 4 Pro, and returns the passages that matter within each document, so your LLM gets the right context with fewer tokens.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.