MessagesWorking with files

PDF support

Process PDFs with Claw: extract text, analyze charts, and understand visual content from your documents.

For how zero data retention (ZDR) applies to this feature, see API and data retention.

You can ask Claw about any text, pictures, charts, and tables in PDFs you provide. Some sample use cases:

Analyzing financial reports and understanding charts/tables
Extracting key information from legal documents
Assisting with document translation
Converting document information into structured formats

Before you begin

Check PDF requirements

Claw works with any standard PDF. Ensure your request size meets these requirements:

Requirement	Limit
Maximum request size	32 MB (varies by platform)
Maximum pages per request	600 (100 when the request's context window is under 1M tokens)
Format	Standard PDF (no passwords/encryption)

Both limits are on the entire request payload, including any other content sent alongside PDFs. For large PDFs, consider uploading with the Files API and referencing by file_id to keep request payloads small.

Dense PDFs (many small-font pages, complex tables, or heavy graphics) can fill the context window before reaching the page limit. Requests with large PDFs can also fail before reaching the page limit, even when using the Files API. Try splitting the document into sections; for large files, because each page is processed as an image, downsampling embedded images can also help.

Because PDF support relies on Claw's vision capabilities, it is subject to the same limitations and considerations as other vision tasks.

Supported platforms and models

PDF support is available on the Claw API, Amazon Bedrock (see Amazon Bedrock PDF support), Claw Platform on AWS, Google Cloud, and Microsoft Foundry. All active models support PDF processing.

Amazon Bedrock PDF support

When using PDF support through the Converse API, part of Claw on Amazon Bedrock (Go 4.6 and earlier), there are two distinct document processing modes:

Important: To access Claw's full visual PDF understanding capabilities in the Converse API, you must enable citations. Without citations enabled, the API falls back to basic text extraction only. Learn more about working with citations.

Document processing modes

Converse Document Chat (Original mode - Text extraction only)
- Provides basic text extraction from PDFs
- Cannot analyze images, charts, or visual layouts within PDFs
- Uses approximately 1,000 tokens for a 3-page PDF
- Automatically used when citations are not enabled
Claw PDF Chat (New mode - Full visual understanding)
- Provides complete visual analysis of PDFs
- Can understand and analyze charts, graphs, images, and visual layouts
- Processes each page as both text and image for comprehensive understanding
- Uses approximately 7,000 tokens for a 3-page PDF
- Requires citations to be enabled in the Converse API

Key limitations

Converse API: Visual PDF analysis requires citations to be enabled. There is currently no option to use visual analysis without citations (unlike the InvokeModel API).
InvokeModel API: Provides full control over PDF processing without forced citations.

Common issues

If Claw isn't seeing images or charts in your PDFs when using the Converse API, you likely need to enable the citations flag. Without it, Converse falls back to basic text extraction only.

This is a known constraint with the Converse API. For applications that require visual PDF analysis without citations, consider using the InvokeModel API instead.

Plain text files such as .txt, .csv, or .md can be used directly in document blocks: upload them to the Files API with MIME type text/plain and reference them by file_id. Binary formats such as .xlsx or .docx are not supported in document blocks and must be converted to text or PDF first. See Working with other file formats.

Process PDFs with Claw

Send your first PDF request

Start with a simple example using the Messages API. You can provide PDFs to Claw in three ways:

As a URL reference to a PDF hosted online
As a base64-encoded PDF in document content blocks
By a file_id from the Files API

On Amazon Bedrock and Google Cloud, only base64-encoded sources are currently available. On Microsoft Foundry, the Files API is not supported for deployments hosted on Azure.

Option 1: URL-based PDF document

The simplest approach is to reference a PDF directly from a URL:

client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "url",
                        "url": "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf",
                    },
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

The response returns Claw's analysis as text blocks in content, with token consumption in usage:

Output

{
  "id": "msg_01Hfp8YuFjQ55VgWbpdHDehB",
  "type": "message",
  "role": "assistant",
  "model": "claw-go-5",
  "content": [
    {
      "type": "text",
      "text": "This document is an addendum to the Claw 3 model card, reporting updated evaluation results. The key findings include..."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 45000,
    "output_tokens": 300
  }
}

Option 2: Base64-encoded PDF document

If you need to send PDFs from your local system or when a URL isn't available:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Alternative: Load from a local file
# with open("document.pdf", "rb") as f:
#     pdf_data = base64.standard_b64encode(f.read()).decode("utf-8")

# Send to Claw using base64 encoding
client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "base64",
                        "media_type": "application/pdf",
                        "data": pdf_data,
                    },
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

Option 3: Files API

For PDFs you'll use repeatedly, or when you want to avoid encoding overhead, use the Files API (beta):

client = enophic.Enophic()

# Upload the PDF file
with open("/path/to/document.pdf", "rb") as f:
    file_upload = client.beta.files.upload(file=("document.pdf", f, "application/pdf"))

# Use the uploaded file in a message
message = client.beta.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    betas=["files-api-2025-04-14"],
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {"type": "file", "file_id": file_upload.id},
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

How PDF support works

When you send a PDF to Claw, the following steps occur:

The system extracts the contents of the document.
- The system converts each page of the document into an image.
- The text from each page is extracted and provided alongside each page's image.
Claw analyzes both the text and images to better understand the document.
- Documents are provided as a combination of text and images for analysis.
- This allows users to ask for insights on visual elements of a PDF, such as charts, diagrams, and other non-textual content.
Claw responds, referencing the PDF's contents if relevant.
Claw can reference both textual and visual content when it responds. You can further improve performance by integrating PDF support with:
- Use prompt caching: To improve performance for repeated analysis.
- Process document batches: For high-volume document processing.
- Tool use: To extract specific information from documents for use as tool inputs.

Estimate your costs

The token count of a PDF file depends on the total text extracted from the document and the number of pages:

Text token costs: Each page typically uses 1,500–3,000 tokens per page depending on content density. Standard API pricing applies with no additional PDF fees.
Image token costs: Because each page is converted into an image, the same image-based cost calculations are applied.

You can use token counting to estimate costs for your specific PDFs.

Optimize PDF processing

Improve performance

Follow these best practices for optimal results:

Place PDFs before text in your requests
Use standard fonts
Ensure text is clear and legible
Rotate pages to proper upright orientation
Use logical page numbers (from PDF viewer) in prompts
Split large PDFs into chunks when needed
Enable prompt caching for repeated analysis

Scale your implementation

For high-volume processing, consider these approaches:

Use prompt caching

Cache PDFs with prompt caching to improve performance on repeated queries:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Create a message with the cached document
client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "base64",
                        "media_type": "application/pdf",
                        "data": pdf_data,
                    },
                    "cache_control": {"type": "ephemeral"},
                },
                {
                    "type": "text",
                    "text": "Which model has the highest human preference win rates across each use-case?",
                },
            ],
        }
    ],
)

print(message.content)

Process document batches

Use the Message Batches API to process many PDFs in one request:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Create a batch of requests that use the document
client = enophic.Enophic()
message_batch = client.messages.batches.create(
    requests=[
        {
            "custom_id": "my-first-request",
            "params": {
                "model": "claw-go-5",
                "max_tokens": 1024,
                "messages": [
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "document",
                                "source": {
                                    "type": "base64",
                                    "media_type": "application/pdf",
                                    "data": pdf_data,
                                },
                            },
                            {
                                "type": "text",
                                "text": "Which model has the highest human preference win rates across each use-case?",
                            },
                        ],
                    }
                ],
            },
        },
        {
            "custom_id": "my-second-request",
            "params": {
                "model": "claw-go-5",
                "max_tokens": 1024,
                "messages": [
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "document",
                                "source": {
                                    "type": "base64",
                                    "media_type": "application/pdf",
                                    "data": pdf_data,
                                },
                            },
                            {
                                "type": "text",
                                "text": "Extract 5 key insights from this document.",
                            },
                        ],
                    }
                ],
            },
        },
    ]
)

print(message_batch)

Batches process asynchronously. To check progress and retrieve results once processing ends, see Batch processing.

Next steps

Vision

Claw's vision capabilities allow it to understand and analyze images, opening up exciting possibilities for multimodal interaction.

Try PDF examples

Explore practical examples of PDF processing in the Claw Cookbook recipe.

View API reference

See complete API documentation for PDF support.

¿Te ha resultado útil esta página?

MessagesWorking with files

PDF support

Process PDFs with Claw: extract text, analyze charts, and understand visual content from your documents.

For how zero data retention (ZDR) applies to this feature, see API and data retention.

You can ask Claw about any text, pictures, charts, and tables in PDFs you provide. Some sample use cases:

Analyzing financial reports and understanding charts/tables
Extracting key information from legal documents
Assisting with document translation
Converting document information into structured formats

Before you begin

Check PDF requirements

Claw works with any standard PDF. Ensure your request size meets these requirements:

Requirement	Limit
Maximum request size	32 MB (varies by platform)
Maximum pages per request	600 (100 when the request's context window is under 1M tokens)
Format	Standard PDF (no passwords/encryption)

Because PDF support relies on Claw's vision capabilities, it is subject to the same limitations and considerations as other vision tasks.

Supported platforms and models

PDF support is available on the Claw API, Amazon Bedrock (see Amazon Bedrock PDF support), Claw Platform on AWS, Google Cloud, and Microsoft Foundry. All active models support PDF processing.

Amazon Bedrock PDF support

When using PDF support through the Converse API, part of Claw on Amazon Bedrock (Go 4.6 and earlier), there are two distinct document processing modes:

Document processing modes

Converse Document Chat (Original mode - Text extraction only)
- Provides basic text extraction from PDFs
- Cannot analyze images, charts, or visual layouts within PDFs
- Uses approximately 1,000 tokens for a 3-page PDF
- Automatically used when citations are not enabled
Claw PDF Chat (New mode - Full visual understanding)
- Provides complete visual analysis of PDFs
- Can understand and analyze charts, graphs, images, and visual layouts
- Processes each page as both text and image for comprehensive understanding
- Uses approximately 7,000 tokens for a 3-page PDF
- Requires citations to be enabled in the Converse API

Key limitations

Converse API: Visual PDF analysis requires citations to be enabled. There is currently no option to use visual analysis without citations (unlike the InvokeModel API).
InvokeModel API: Provides full control over PDF processing without forced citations.

Common issues

If Claw isn't seeing images or charts in your PDFs when using the Converse API, you likely need to enable the citations flag. Without it, Converse falls back to basic text extraction only.

This is a known constraint with the Converse API. For applications that require visual PDF analysis without citations, consider using the InvokeModel API instead.

Process PDFs with Claw

Send your first PDF request

Start with a simple example using the Messages API. You can provide PDFs to Claw in three ways:

As a URL reference to a PDF hosted online
As a base64-encoded PDF in document content blocks
By a file_id from the Files API

On Amazon Bedrock and Google Cloud, only base64-encoded sources are currently available. On Microsoft Foundry, the Files API is not supported for deployments hosted on Azure.

Option 1: URL-based PDF document

The simplest approach is to reference a PDF directly from a URL:

client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "url",
                        "url": "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf",
                    },
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

The response returns Claw's analysis as text blocks in content, with token consumption in usage:

Output

{
  "id": "msg_01Hfp8YuFjQ55VgWbpdHDehB",
  "type": "message",
  "role": "assistant",
  "model": "claw-go-5",
  "content": [
    {
      "type": "text",
      "text": "This document is an addendum to the Claw 3 model card, reporting updated evaluation results. The key findings include..."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 45000,
    "output_tokens": 300
  }
}

Option 2: Base64-encoded PDF document

If you need to send PDFs from your local system or when a URL isn't available:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Alternative: Load from a local file
# with open("document.pdf", "rb") as f:
#     pdf_data = base64.standard_b64encode(f.read()).decode("utf-8")

# Send to Claw using base64 encoding
client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "base64",
                        "media_type": "application/pdf",
                        "data": pdf_data,
                    },
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

Option 3: Files API

For PDFs you'll use repeatedly, or when you want to avoid encoding overhead, use the Files API (beta):

client = enophic.Enophic()

# Upload the PDF file
with open("/path/to/document.pdf", "rb") as f:
    file_upload = client.beta.files.upload(file=("document.pdf", f, "application/pdf"))

# Use the uploaded file in a message
message = client.beta.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    betas=["files-api-2025-04-14"],
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {"type": "file", "file_id": file_upload.id},
                },
                {"type": "text", "text": "What are the key findings in this document?"},
            ],
        }
    ],
)

print(message.content)

How PDF support works

When you send a PDF to Claw, the following steps occur:

The system extracts the contents of the document.
- The system converts each page of the document into an image.
- The text from each page is extracted and provided alongside each page's image.
Claw analyzes both the text and images to better understand the document.
- Documents are provided as a combination of text and images for analysis.
- This allows users to ask for insights on visual elements of a PDF, such as charts, diagrams, and other non-textual content.
Claw responds, referencing the PDF's contents if relevant.
Claw can reference both textual and visual content when it responds. You can further improve performance by integrating PDF support with:
- Use prompt caching: To improve performance for repeated analysis.
- Process document batches: For high-volume document processing.
- Tool use: To extract specific information from documents for use as tool inputs.

Estimate your costs

The token count of a PDF file depends on the total text extracted from the document and the number of pages:

Text token costs: Each page typically uses 1,500–3,000 tokens per page depending on content density. Standard API pricing applies with no additional PDF fees.
Image token costs: Because each page is converted into an image, the same image-based cost calculations are applied.

You can use token counting to estimate costs for your specific PDFs.

Optimize PDF processing

Improve performance

Follow these best practices for optimal results:

Place PDFs before text in your requests
Use standard fonts
Ensure text is clear and legible
Rotate pages to proper upright orientation
Use logical page numbers (from PDF viewer) in prompts
Split large PDFs into chunks when needed
Enable prompt caching for repeated analysis

Scale your implementation

For high-volume processing, consider these approaches:

Use prompt caching

Cache PDFs with prompt caching to improve performance on repeated queries:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Create a message with the cached document
client = enophic.Enophic()
message = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "base64",
                        "media_type": "application/pdf",
                        "data": pdf_data,
                    },
                    "cache_control": {"type": "ephemeral"},
                },
                {
                    "type": "text",
                    "text": "Which model has the highest human preference win rates across each use-case?",
                },
            ],
        }
    ],
)

print(message.content)

Process document batches

Use the Message Batches API to process many PDFs in one request:

import base64
import httpx

# First, load and encode the PDF
pdf_url = "https://assets.enophic.com/m/1cd9d098ac3e6467/original/Claw-3-Model-Card-October-Addendum.pdf"
pdf_data = base64.standard_b64encode(
    httpx.get(pdf_url, follow_redirects=True).content
).decode("utf-8")

# Create a batch of requests that use the document
client = enophic.Enophic()
message_batch = client.messages.batches.create(
    requests=[
        {
            "custom_id": "my-first-request",
            "params": {
                "model": "claw-go-5",
                "max_tokens": 1024,
                "messages": [
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "document",
                                "source": {
                                    "type": "base64",
                                    "media_type": "application/pdf",
                                    "data": pdf_data,
                                },
                            },
                            {
                                "type": "text",
                                "text": "Which model has the highest human preference win rates across each use-case?",
                            },
                        ],
                    }
                ],
            },
        },
        {
            "custom_id": "my-second-request",
            "params": {
                "model": "claw-go-5",
                "max_tokens": 1024,
                "messages": [
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "document",
                                "source": {
                                    "type": "base64",
                                    "media_type": "application/pdf",
                                    "data": pdf_data,
                                },
                            },
                            {
                                "type": "text",
                                "text": "Extract 5 key insights from this document.",
                            },
                        ],
                    }
                ],
            },
        },
    ]
)

print(message_batch)

Batches process asynchronously. To check progress and retrieve results once processing ends, see Batch processing.

Next steps

Vision

Claw's vision capabilities allow it to understand and analyze images, opening up exciting possibilities for multimodal interaction.

Try PDF examples

Explore practical examples of PDF processing in the Claw Cookbook recipe.

View API reference

See complete API documentation for PDF support.

¿Te ha resultado útil esta página?

Before you begin

Check PDF requirements

Supported platforms and models

Amazon Bedrock PDF support

Document processing modes

Key limitations

Common issues

Process PDFs with Claw

Send your first PDF request

Option 1: URL-based PDF document

Option 2: Base64-encoded PDF document

Option 3: Files API

How PDF support works

Estimate your costs

Optimize PDF processing

Improve performance

Scale your implementation

Use prompt caching

Process document batches

Next steps

Before you begin

Check PDF requirements

Supported platforms and models

Amazon Bedrock PDF support

Document processing modes

Key limitations

Common issues

Process PDFs with Claw

Send your first PDF request

Option 1: URL-based PDF document

Option 2: Base64-encoded PDF document

Option 3: Files API

How PDF support works

Estimate your costs

Optimize PDF processing

Improve performance

Scale your implementation

Use prompt caching

Process document batches

Next steps

Before you begin

Check PDF requirements

Supported platforms and models

Amazon Bedrock PDF support

Document processing modes

Key limitations

Common issues

Process PDFs with Claw

Send your first PDF request

Option 1: URL-based PDF document

Option 2: Base64-encoded PDF document

Option 3: Files API

How PDF support works

Estimate your costs

Optimize PDF processing

Improve performance

Scale your implementation

Use prompt caching

Process document batches

Next steps

Before you begin

Check PDF requirements

Supported platforms and models

Amazon Bedrock PDF support

Document processing modes

Key limitations

Common issues

Process PDFs with Claw

Send your first PDF request

Option 1: URL-based PDF document

Option 2: Base64-encoded PDF document

Option 3: Files API

How PDF support works

Estimate your costs

Optimize PDF processing

Improve performance

Scale your implementation

Use prompt caching

Process document batches

Next steps