Fix PDF support documentation for Anthropic integration

integrations/llms/anthropic.mdx

@@ -1,11 +1,11 @@
 ---
 title: "Anthropic"
 description: "Integrate Anthropic's Claude models with Portkey's AI Gateway"
 ---
 
 Portkey provides a robust and secure gateway to integrate various Large Language Models (LLMs) into applications, including [Anthropic's Claude APIs](https://docs.anthropic.com/claude/reference/getting-started-with-the-api).
 
 With Portkey, take advantage of features like fast AI gateway access, observability, prompt management, and more, while securely managing API keys through [Model Catalog](/product/model-catalog).
 
 
 <CardGroup cols={3}>
@@ -225,7 +225,7 @@
 
 ### System Prompts
 
 Anthropic handles system prompts differently than OpenAI. With Portkey, you can use the OpenAI-compatible format:
 
 <CodeGroup>
 ```python Python icon="python"
@@ -251,7 +251,7 @@
 ```
 </CodeGroup>
 
 Portkey automatically formats this for Anthropic's API.
 
 ### Streaming
 
@@ -289,9 +289,9 @@
 
 ## Advanced Features
 
 ### Vision (Multimodal)
 
 Portkey supports Anthropic's vision models including `claude-sonnet-4-5-20250929`, `claude-3-5-sonnet`, `claude-3-haiku`, `claude-3-opus`, and `claude-3.7-sonnet`. Use the same format as OpenAI:
 
 <Note>
 Anthropic **only accepts base64-encoded images** and does not support image URLs. Use the same base64 format to send images to both Anthropic and OpenAI models.
@@ -359,7 +359,7 @@
 
 ### PDF Support
 
 Anthropic Claude processes PDFs to extract text, analyze charts, and understand visual content. PDF support is available on:
 - Claude 3.7 Sonnet (`claude-3-7-sonnet-20250219`)
 - Claude 3.5 Sonnet (`claude-3-5-sonnet-20241022`, `claude-3-5-sonnet-20240620`)
 - Claude Sonnet 4-5 (`claude-sonnet-4-5-20250929`)
@@ -380,7 +380,7 @@
 
 # Fetch and encode the PDF
 pdf_url = "https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf"
-pdf_data = "data:application/pdf;base64," + base64.standard_b64encode(httpx.get(pdf_url).content).decode("utf-8")
+pdf_data = base64.standard_b64encode(httpx.get(pdf_url).content).decode("utf-8")
 
 response = portkey.chat.completions.create(
     model="@anthropic/claude-sonnet-4-5-20250929",
@@ -412,7 +412,6 @@
 const pdfUrl = "https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf"
 const pdfResponse = await axios.get(pdfUrl, { responseType: 'arraybuffer' })
 const pdfBase64 = Buffer.from(pdfResponse.data).toString('base64')
-const pdfData = `data:application/pdf;base64,${pdfBase64}`
 
 const response = await portkey.chat.completions.create({
     model: "@anthropic/claude-sonnet-4-5-20250929",
@@ -423,7 +422,7 @@
             role: "user",
             content: [
                 { type: "text", text: "What are the key findings in this document?" },
-                { type: "file", file: { mime_type: "application/pdf", file_data: pdfData } }
+                { type: "file", file: { mime_type: "application/pdf", file_data: pdfBase64 } }
             ]
         }
     ]
@@ -497,9 +496,9 @@
 
 ### Using /messages Route
 
 Portkey supports Anthropic's `/messages` endpoint, allowing you to use either Anthropic's native SDK or Portkey's SDK with full gateway features.
 
 #### Using Anthropic's Native SDK
 
 <CodeGroup>
 ```python Anthropic Py
@@ -537,7 +536,7 @@
 ```
 </CodeGroup>
 
 #### Using Portkey's SDK
 
 ```sh cURL icon="square-terminal"
 curl --location 'https://api.portkey.ai/v1/messages' \
@@ -563,7 +562,7 @@
 
 ### Prompt Caching
 
 Portkey works with Anthropic's prompt caching feature to save time and money. Refer to this guide:
 
 <Card title="Prompt Caching" href="/integrations/llms/anthropic/prompt-caching">
   Learn how to enable prompt caching for Anthropic requests
@@ -571,7 +570,7 @@
 
 ### Beta Features
 
 Portkey supports Anthropic's beta features through headers. Pass the beta feature name as the value:
 
 <CodeGroup>
 ```python Python icon="python"