Introduction
Welcome to InferHood. Build and scale AI applications across multiple providers with a single API.
What is InferHood?
InferHood is a unified AI inference gateway that gives developers and autonomous agents access to every major AI model through one API, one key, and one endpoint. No more juggling separate accounts across OpenAI, Anthropic, Google, xAI, Meta, DeepSeek, and Mistral.
Note
Access is token-gated - hold
$INFER tokens on Robinhood Chain to generate API keys and start making requests.Key Features
One API - OpenAI-compatible endpoints. Use the same SDK you already know.
One Key - A single API key grants access to every supported model.
Token-Gated - Hold $INFER tokens to unlock access. No credit cards needed.
Agent Payments - x402 protocol lets AI agents pay per-request on-chain.
Model Routing - Automatic provider selection, failover, and load balancing.
Streaming - Full SSE streaming support for real-time responses.
How It Works
Point any OpenAI-compatible SDK at InferHood and specify the model you want. We route the request to the correct provider, handle auth, and stream the response back.
cURL
curl https://api.inferhood.xyz/v1/chat/completions \
-H "Authorization: Bearer ih_live_xxx" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'The model ID follows the format provider/model-name. For example, anthropic/claude-sonnet-4 or google/gemini-2.5-pro.