Pomelo API
The Pomelo API provides access to multiple AI services including text generation, image creation, and speech processing. Get started by exploring our endpoints below.
💡 Tip: Use the search function (⌘K or Ctrl+K) to quickly find specific endpoints, guides, or examples.
Tasks API
Process text, images, and audio with AI models. Support for OpenAI, Claude, ElevenLabs, and more.
Models
Browse available AI models, their capabilities, pricing, and performance characteristics.
API Keys
Generate and manage API keys for secure access to all endpoints.
Quick Start
Get started with the Pomelo API in minutes. Create an API key and make your first request.
1. Get your API key
2. Make your first request
Pomelo API Documentation
Welcome to the Pomelo API documentation. This API provides access to various AI services including text generation, image generation, speech synthesis, and more.
Base URL
https://www.pomeloapi.com/api
Authentication
All API endpoints (except status checks) require authentication using API keys. Include your API key in the request headers:
Authorization: Bearer YOUR_API_KEY
API Versions
- v1: Current stable version (
/api/v1/
)
Quick Start
- Get your API key
- Check the status endpoint to verify API availability
- Review the task endpoint for AI operations
- Monitor your billing and credits
Endpoints Overview
Core Endpoints
- Tasks (
/api/v1/task
) - Main AI processing endpoint - Models (
/api/v1/models
) - Model information and pricing
Management Endpoints
- API Keys (
/api/keys
) - Manage your API keys - Billing (
/api/billing
) - Credits and payment management
System Endpoints
- Status (
/api/status
) - API health checks - Authentication (
/api/auth
) - User authentication
Supported AI Services
Text Generation
- OpenAI GPT Models: GPT-4, GPT-3.5-turbo, and other OpenAI models
- Claude Models: Anthropic's Claude family of models
- Mixtral: Open-source language models
Image Generation
- Black Forest Labs: High-quality image generation models
Speech Services
- ElevenLabs:
- Text-to-speech synthesis
- Speech-to-speech conversion
- Speech-to-text transcription
Rate Limits
API requests are subject to rate limiting based on your subscription plan. Rate limit information is included in response headers.
Error Handling
All errors follow a consistent format:
{
"error": {
"message": "Error description",
"type": "error_type",
"code": "error_code"
}
}
Common error types:
invalid_request_error
: Request format or parameters are invalidauthentication_error
: Invalid or missing API keyrate_limit_error
: Rate limit exceededinsufficient_credits_error
: Not enough credits for the operation
SDKs and Libraries
Coming soon - official SDKs for popular programming languages.
Support
For API support, please contact our support team or check the documentation for specific endpoints.