API Reference

PDF Inputs

SIRAYA Model Router supports PDF processing through the /v1/chat/completions API. PDFs can be sent as base64-encoded data URLs or, on models that accept them, direct URLs in the messages array, via the file content type. Base64 data URLs work on every document-capable model.

Always set filename on the file part. Some models do not read a PDF sent without one.

GPT models

GPT models accept only base64-encoded data URLs in file_data. A plain https:// URL is not supported for them; use Base64 Encoded PDFs instead.

Sending PDFs

Using PDF URLs

PythonTypeScript

import requests
import json

url = "https://llm.siraya.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer <API_KEY>",
    "Content-Type": "application/json"
}

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Summarize this document."
            },
            {
                "type": "file",
                "file": {
                    "filename": "document.pdf",
                    "file_data": "https://example.com/document.pdf"
                }
            }
        ]
    }
]

payload = {
    "model": "claude-sonnet-4.5",
    "messages": messages
}

response = requests.post(url, headers=headers, json=payload)
print(response.json()["choices"][0]["message"]["content"])

const response = await fetch('https://llm.siraya.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer <API_KEY>`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'claude-sonnet-4.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          { type: 'file', file: { filename: 'document.pdf', file_data: 'https://example.com/document.pdf' } },
        ],
      },
    ],
  }),
});

const data = await response.json();
console.log(data);

Using Base64 Encoded PDFs

For locally stored PDFs, and for GPT models, encode them as base64 data URLs:

Python

import requests
import json
import base64

def encode_pdf_to_base64(pdf_path):
    with open(pdf_path, "rb") as pdf_file:
        return base64.b64encode(pdf_file.read()).decode('utf-8')

url = "https://llm.siraya.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer <API_KEY>",
    "Content-Type": "application/json"
}

pdf_path = "path/to/your/document.pdf"
base64_pdf = encode_pdf_to_base64(pdf_path)
data_url = f"data:application/pdf;base64,{base64_pdf}"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What are the key points in this document?"
            },
            {
                "type": "file",
                "file": {
                    "filename": "document.pdf",
                    "file_data": data_url
                }
            }
        ]
    }
]

payload = {
    "model": "claude-sonnet-4.5",
    "messages": messages
}

response = requests.post(url, headers=headers, json=payload)
print(response.json()["choices"][0]["message"]["content"])

Using the Messages API (Claude)

On POST /v1/messages, send a PDF as a native Anthropic document block:

curl https://llm.siraya.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "claude-sonnet-4.5",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "document",
            "source": {
              "type": "base64",
              "media_type": "application/pdf",
              "data": "<BASE64_PDF>"
            }
          },
          {"type": "text", "text": "Summarize this document."}
        ]
      }
    ]
  }'

Supported Document Formats

Supported document formats depend on the model you select. PDFs are supported across all document-capable models; depending on the model, additional formats such as csv, doc, docx, xls, xlsx, html, txt, and md may also be accepted.