DeepRequest API Reference

API Reference

This document provides detailed information about the Machine Learning API endpoints, authentication, and usage.

Authentication

All API requests must include an API key in the request headers. Our API is designed to be fully compatible with OpenAI’s authentication method, making it easy to migrate existing applications. You can generate and manage your API keys from the DeepRequest Dashboard.

Authorization: Bearer sk-your-api-key

Rate Limits & Usage

Rate limits and credit costs are specific to your account tier and can be viewed in your DeepRequest Dashboard. Please check your dashboard for:

• Current rate limits
• Credit balance and usage
• API key status and permissions
• Usage statistics and analytics

Models

The API currently supports the following machine learning models:

DeepSeek-32B

• State-of-the-art language model for code and text generation
• Best for: Code completion, technical writing, and natural language processing
• Visit DeepRequest Dashboard for your specific rate limits and pricing

Whisper Large v3

• Latest version of Whisper model for speech recognition
• Best for: High-quality transcription and translation across multiple languages
• Visit DeepRequest Dashboard for your specific rate limits and pricing

Error Handling

The API uses conventional HTTP response codes to indicate success or failure of requests:

• 200 OK: Request succeeded
• 201 Created: Resource was successfully created
• 204 No Content: Request succeeded with no response body
• 400 Bad Request: Invalid request format
• 401 Unauthorized: Missing or invalid API key
• 403 Forbidden: Valid API key but insufficient permissions
• 404 Not Found: Requested resource doesn’t exist
• 429 Too Many Requests: Rate limit exceeded
• 500 Internal Server Error: Server-side error

Error responses will include a JSON body with additional details:

{
  "error": {
    "message": "Detailed error message",
    "code": "ERROR_CODE",
    "type": "invalid_request_error"
  }
}