API Overview

The DocsRouter API is fully compatible with OpenAI and OpenRouter SDKs. You can use existing SDKs by simply changing the base URL. The API also provides DocsRouter-specific extensions for enhanced OCR functionality.

Base URL

All API requests should be made to the following base URL:

https://api.docsrouter.com/v1

For testing and development, you can also use:

https://api.docsrouter.com/v1  (Production)

Authentication

All API requests (except /v1/models and /v1/health) require authentication via the Authorization header using a Bearer token:

Authorization: Bearer YOUR_API_KEY

Obtaining an API Key

Sign up at docsrouter.com
Navigate to Dashboard → API Keys
Click Create New Key
Copy and securely store your key (it's only shown once)

Security Best Practices:

Never expose API keys in client-side code or public repositories
Use environment variables to store keys
Rotate keys periodically
Use separate keys for development and production

SDK Compatibility

DocsRouter works with any OpenAI-compatible SDK. Here are examples for popular languages:

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.docsrouter.com/v1",
    api_key="YOUR_DOCSROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="google/gemini-2.0-flash-001",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Extract all text from this document"},
            {"type": "image_url", "image_url": {"url": "https://example.com/invoice.png"}}
        ]
    }]
)

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

JavaScript/TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.docsrouter.com/v1',
  apiKey: 'YOUR_DOCSROUTER_API_KEY',
});

const response = await client.chat.completions.create({
  model: 'google/gemini-2.0-flash-001',
  messages: [{
    role: 'user',
    content: [
      { type: 'text', text: 'Extract all text from this document' },
      { type: 'image_url', image_url: { url: 'https://example.com/invoice.png' } }
    ]
  }]
});

console.log(response.choices[0].message.content);

cURL

curl -X POST https://api.docsrouter.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-001",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Extract all text"},
        {"type": "image_url", "image_url": {"url": "https://example.com/doc.png"}}
      ]
    }]
  }'

Other SDKs

DocsRouter is compatible with:

LangChain - Use the OpenAI integration with custom base URL
LlamaIndex - Configure OpenAI LLM with DocsRouter endpoint
Vercel AI SDK - Use OpenAI provider with custom configuration
Any OpenAI-compatible library - Just change the base URL

Response Format

All responses follow the OpenAI standard format with DocsRouter extensions:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1734567890,
  "model": "google/gemini-2.0-flash-001",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "INVOICE #001\nDate: December 15, 2024\n..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 1200,
    "completion_tokens": 150,
    "total_tokens": 1350
  },
  "docsrouter": {
    "confidence": 95,
    "detected_language": "en",
    "pages_processed": 1,
    "tables_detected": 2,
    "provider": "openrouter",
    "provider_cost_cents": 1.2,
    "platform_fee_cents": 0.4,
    "total_cost_cents": 1.6,
    "processing_time_ms": 1850
  }
}

DocsRouter Extensions

The docsrouter object in responses contains OCR-specific metadata:

Field	Type	Description
`confidence`	number	OCR confidence score (0-100)
`detected_language`	string	ISO 639-1 language code
`pages_processed`	number	Number of pages/images processed
`tables_detected`	number	Number of tables found
`tables`	array	Extracted table data (if enabled)
`provider`	string	Upstream provider used
`provider_cost_cents`	number	Cost charged by provider
`platform_fee_cents`	number	DocsRouter platform fee
`total_cost_cents`	number	Total cost for the request
`processing_time_ms`	number	Processing time in milliseconds

Endpoints Overview

Core Endpoints

Method	Endpoint	Auth	Description
`POST`	`/v1/chat/completions`	Required	OpenAI-compatible OCR ⭐ Recommended
`POST`	`/v1/ocr`	Required	Native OCR endpoint
`GET`	`/v1/models`	Optional	List available models
`GET`	`/v1/models/{id}`	Optional	Get specific model details

Management Endpoints

Method	Endpoint	Auth	Description
`GET`	`/v1/api-keys`	Required	List API keys
`POST`	`/v1/api-keys`	Required	Create new API key
`DELETE`	`/v1/api-keys/{id}`	Required	Revoke API key
`GET`	`/v1/usage`	Required	Get usage logs
`GET`	`/v1/usage/summary`	Required	Get usage summary
`GET`	`/v1/account`	Required	Get account details
`GET`	`/v1/account/balance`	Required	Get account balance

Utility Endpoints

Method	Endpoint	Auth	Description
`GET`	`/v1/health`	None	Check API status
`GET`	`/v1/models/stats`	Optional	Get model statistics
`GET`	`/v1/models/recommended`	Optional	Get recommended models

Rate Limits

The API implements rate limiting to ensure fair usage and system stability:

Tier	Requests/Minute	Requests/Day	Concurrent
Free	10	100	2
Starter	60	1,000	5
Pro	300	10,000	20
Enterprise	Custom	Custom	Custom

Rate Limit Headers

Every response includes rate limit information:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 58
X-RateLimit-Reset: 1734567890

Header	Description
`X-RateLimit-Limit`	Maximum requests allowed in the window
`X-RateLimit-Remaining`	Requests remaining in current window
`X-RateLimit-Reset`	Unix timestamp when the window resets
`Retry-After`	Seconds to wait (only on 429 responses)

Request Limits

Limit	Value
Maximum request body size	50 MB
Maximum image size	20 MB
Maximum PDF size	50 MB
Maximum pages per PDF	100
Maximum images per request	10
Request timeout	120 seconds

Supported File Formats

Images

Format	MIME Type	Notes
PNG	`image/png`	Recommended for documents
JPEG	`image/jpeg`	Good for photos
WebP	`image/webp`	Efficient compression
GIF	`image/gif`	First frame only
TIFF	`image/tiff`	High-quality scans
BMP	`image/bmp`	Uncompressed

Documents

Format	MIME Type	Notes
PDF	`application/pdf`	Use `mistral-ocr` engine for scanned PDFs

Pricing

DocsRouter pricing is 5% above OpenRouter rates, covering our unified API, OCR extensions, and platform services.

Per-Request Costs

Costs are calculated based on:

Input tokens - Text and image tokens sent to the model
Output tokens - Generated text tokens
PDF processing - Additional fee for PDF engine (if used)
Document conversion - Additional fee for office documents (if needed)

PDF Engine Pricing

Engine	Cost	Best For
`pdf-text`	Free	Digital PDFs with selectable text
`mistral-ocr`	$0.105/1,000 pages	Scanned documents, images in PDFs
`native`	Model token cost	Models with native PDF support

Document Conversion Pricing

For office documents (DOCX, PPTX, DOC, ODT, RTF, TXT) that need to be converted to images before processing with Vision LLMs:

Document Type	Estimated Cost	Notes
Simple documents	~1-2¢	DOCX, DOC, TXT, RTF
Presentations	~1-3¢	PPTX (10-50 slides)
Complex documents	~2-5¢	Large documents with many pages

Minimum charge: 1¢ per conversion

Tip: Mistral OCR (mistral-ocr-latest) natively supports DOCX and PPTX without conversion fees. Use it for the most cost-effective office document processing.

Cost Transparency

Every response includes detailed cost breakdown:

{
  "docsrouter": {
    "provider_cost_cents": 1.2,
    "platform_fee_cents": 0.4,
    "conversion_cost_cents": 1.0,
    "total_cost_cents": 2.6
  }
}

Versioning

The API is versioned via the URL path (/v1/). We maintain backward compatibility within major versions.

v1 (current) - Stable, production-ready
Breaking changes will be announced 90 days in advance
Deprecation notices are included in response headers

Support

Documentation: docs.docsrouter.com
Status Page: status.docsrouter.com
Email: [email protected]
Discord: Join our community

API Overview

On this page