Claude (OpenAI Format) - PDF Analysis

Use Claude models via OpenAI format with PDF support

Claude (OpenAI Format) - PDF Analysis

Claude models support both OpenAI request format and native Anthropic format. When using OpenAI format, it’s fully compatible with all OpenAI libraries.

If you need prompt caching, use the Claude native format (see the next page in the sidebar) instead. OpenAI format does not support PDF caching.

Request

Headers

Header	Required	Description
Content-Type	Yes	application/json
Authorization	Yes	Bearer sk-xxx

Request Body

Parameter	Type	Required	Description
model	string	Yes	Claude model name (e.g. claude-sonnet-4-6)
messages	array	Yes	Array of message objects
messages[].role	string	Yes	Role: user or assistant
messages[].content	string/array	Yes	Text or multimodal content array
max_tokens	number	No	Maximum tokens to generate
temperature	number	No	Sampling temperature (0-2)
stream	boolean	No	Enable streaming
thinking	object	No	Enable extended thinking (claude-sonnet-5 only)
thinking.type	string	No	Must be enabled
thinking.budget_tokens	integer	No	Max thinking tokens (min 1024, must be < max_tokens)

Content Types for PDF/File Analysis

The content array supports:

Type	Fields	Description
text	text	Text prompt
file	file.filename, file.file_data	PDF file (URL or base64)
file_url	file_url.url	File URL (supports images and PDFs)
image_url	image_url.url	Image URL (base64 or web URL)

For base64, use format: data:application/pdf;base64,JVBERi0xLjQK.... Claude recommends base64 for faster results.

Example Request - Chat

curl https://kiosapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {
        "role": "user",
        "content": "Hello, who are you?"
      }
    ],
    "max_tokens": 1688,
    "temperature": 0.5,
    "stream": false
  }'

Example Request - PDF Analysis

curl https://kiosapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Summarize this document"
          },
          {
            "type": "file_url",
            "file_url": {
              "url": "https://example.com/document.pdf"
            }
          }
        ]
      }
    ],
    "max_tokens": 1000,
    "stream": false
  }'

Python Example - PDF Analysis

import openai

openai.api_key = "sk-xxx"
openai.base_url = "https://kiosapi.com/v1/"

response = openai.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize this document"},
                {
                    "type": "file",
                    "file": {
                        "filename": "document.pdf",
                        "file_data": "https://example.com/document.pdf"
                    }
                }
            ]
        }
    ],
    max_tokens=1000,
    stream=False
)

print(response.choices[0].message.content)

Example - Extended Thinking

response = openai.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Solve this complex problem..."}],
    max_tokens=8000,
    thinking={
        "type": "enabled",
        "budget_tokens": 4000
    }
)

Response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1724972230,
  "model": "claude-sonnet-4-6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm Claude, an AI assistant..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 38,
    "total_tokens": 50
  }
}