Providers

Endpoint: GET /api/v1/providers

Authentication: Optional (public endpoint)
Required Scopes (OAuth): None (public)

Quick Start

const response = await fetch('https://hypery.ai/api/v1/providers', {
  headers: { 'Authorization': `Bearer ${apiKey}` }
})
 
const providers = await response.json()

Response Format

[
  {
    "id": "vercel",
    "name": "Vercel AI Gateway",
    "description": "The default chat provider — 200+ language models across OpenAI, Anthropic, Google, and more",
    "baseUrl": "https://ai-gateway.vercel.sh/v1/ai",
    "supportedFeatures": [
      "chat",
      "streaming",
      "function_calling"
    ],
    "modelCount": 200,
    "status": "active"
  },
  {
    "id": "openrouter",
    "name": "OpenRouter",
    "description": "Access 200+ models through a unified API",
    "baseUrl": "https://openrouter.ai/api/v1",
    "supportedFeatures": [
      "chat",
      "streaming",
      "function_calling",
      "vision"
    ],
    "modelCount": 250,
    "status": "active"
  },
  {
    "id": "replicate",
    "name": "Replicate",
    "description": "Run ML models in the cloud",
    "baseUrl": "https://api.replicate.com/v1",
    "supportedFeatures": [
      "predictions",
      "image_generation",
      "async"
    ],
    "modelCount": 50,
    "status": "active"
  }
]

Provider Details

Vercel AI Gateway

Best For: Chat completions, streaming, function calling (the default provider)
Model Count: 200+ language models
Features:

• Aggregates chat models from OpenAI, Anthropic, Google, Mistral, Cohere, and more
• Multi-provider routing and fallbacks
• Competitive, list-price pricing — the basis for metered billing
• Synced live from the public Vercel AI Gateway catalog

Example Models:

• anthropic/claude-sonnet-4.6
• openai/gpt-5.1-codex-mini
• google/gemini-2.5-pro
• alibaba/qwen-3-14b

OpenRouter

Best For: Chat completions, function calling, vision
Model Count: 200+
Features:

• Unified access to models from Anthropic, OpenAI, Google, Meta, etc.
• Automatic failover and load balancing
• Pay-per-use pricing
• Provider routing controls

Example Models:

• anthropic/claude-3.5-sonnet
• openai/gpt-4o
• google/gemini-pro
• meta-llama/llama-3-70b

Replicate

Best For: Image generation, async predictions
Model Count: 50+
Features:

• Async prediction execution
• Image generation (Flux, Stable Diffusion)
• Video generation
• Custom model hosting

Example Models:

• black-forest-labs/flux-schnell
• stability-ai/stable-diffusion-3
• ideogram-ai/ideogram-v2

Code Examples

// List all providers
const response = await fetch('https://hypery.ai/api/v1/providers')
const providers = await response.json()
 
// Find provider by ID
const openrouter = providers.find(p => p.id === 'openrouter')
 
// Check supported features
if (openrouter.supportedFeatures.includes('function_calling')) {
  console.log('OpenRouter supports function calling')
}

import requests
 
response = requests.get('https://hypery.ai/api/v1/providers')
providers = response.json()
 
for provider in providers:
    print(f"{provider['name']}: {provider['modelCount']} models")

curl https://hypery.ai/api/v1/providers

Specifying Providers

You can explicitly specify which provider to use:

const response = await client.chat.completions.create({
  model: 'anthropic/claude-3.5-sonnet',
  provider: 'openrouter',  // Explicitly use OpenRouter
  messages: [{ role: 'user', content: 'Hello' }]
})

Next Steps