AI APIs
OpenAI-compatible APIs for chat, images, and more
Hypery provides OpenAI-compatible APIs that work as a drop-in replacement for OpenAI, Anthropic, and other providers.
Available APIs
Chat API
Build conversational AI applications with support for:
- Multiple models - GPT-4, Claude, Gemini, and 200+ more
- Streaming - Real-time token streaming
- Function calling - Tool use and agent capabilities
- Vision - Analyze images with multi-modal models
Image
Generate images using state-of-the-art models:
- Multiple formats - OpenAI and Replicate formats
- Async generation - Poll for results
- Various models - DALL-E, Flux, Stable Diffusion
Embeddings
POST /api/v1/embeddings — OpenAI-compatible vector embeddings. Scope: ai:embeddings. Billed like other AI routes (VAG Stripe meters or credit ledger).
Audio
TTS (/audio/speech), STT (/audio/transcriptions), and realtime session minting (/realtime/sessions). Scope: ai:audio. Charged via credit ledger or Stripe invoice items (not free under passthrough).
Models
List and query available models:
- Filter by capabilities - Function calling, vision, etc.
- Search models - Find the right model for your use case
- Provider info - See which provider hosts each model
Why Use Hypery?
Drop-in Replacement
Use the official OpenAI SDK without changes:
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.GATEWAY_API_KEY,
baseURL: 'https://hypery.ai/api/v1' // Only change needed
})Multiple Providers
Access models from multiple providers through one API:
- OpenRouter (200+ models)
- Replicate (image generation)
- And more coming soon
Unified Billing
One credit system for all providers. No need to manage multiple API keys and billing systems.
Built-in Analytics
Track usage, costs, and performance across all your AI API calls.
Spending Limits
Set limits at team and app levels to control costs.
Getting Started
Get an API Key
Create an API key in your dashboard.
Install SDK & Set Base URL
npm install openaiConfigure the client with Hypery's base URL:
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.GATEWAY_API_KEY,
baseURL: 'https://hypery.ai/api/v1'
})Make Your First Request
const response = await client.chat.completions.create({
model: 'anthropic/claude-3.5-sonnet',
messages: [{ role: 'user', content: 'Hello!' }]
})Base URL: https://hypery.ai/api/v1 - This is the only change needed to use Hypery instead of OpenAI.
Model ID Format
Models are identified by provider/model-name format:
anthropic/claude-3.5-sonnet
openai/gpt-4o
google/gemini-pro
meta-llama/llama-3-70b
The first part is the model creator/organization, NOT the hosting provider. The provider is specified separately or defaults to OpenRouter.