Loading...
AI infrastructure for Robinhood Chain

One API.
Every model.

Access the world's leading AI models through a single developer interface. Token-gated API access for holders on Robinhood Chain.

npm install @inferhood/sdk
POSThttps://api.inferhood.xyz/v1/chat/completions
const response = await fetch(
"https://api.inferhood.xyz/v1/chat/completions",
{
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.INFERHOOD_API_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "anthropic/claude-sonnet-4",
messages: [
{
role: "user",
content: "Analyze this market."
}
]
})
}
);
Response200 OK
Model
anthropic/claude-sonnet-4
Latency
482ms
Tokens
1,247
Cost
$0.0038
Provider
Anthropic
Request ID
req_Z92kL8mN4...

One endpoint for the models you already use.

OpenAIOpenAI
AnthropicAnthropic
GoogleGoogle
xAIxAI
MetaMeta
DeepSeekDeepSeek
MistralMistral

Available through supported inference providers.

One API. Every provider.

Switch models without rebuilding your application.

model: "openai/gpt-4o"
model: "anthropic/claude-sonnet-4"
model: "google/gemini-2.5-pro"
Request
Router
Cost
Latency
Reliability
Provider
Response

Intelligent routing

Route requests based on cost, latency, availability, and capability.

Agent-native payments

Autonomous software can pay for model access using programmatic payment rails.

1. AgentInitiates Task
2. HTTP 402Payment Required
3. PaymentSettled on Chain
4. InferenceModel Executed
5. ResponseDelivered
Requests12,842
Cost$42.18
Tokens18.4M
Success Rate99.91%

Full observability

Every request accounted for.

01

Create an API key

Generate a secure key to authenticate your applications and autonomous agents.

02

Choose a model

Select from leading models across OpenAI, Anthropic, Google, and more.

03

Send inference

Make a standard OpenAI-compatible HTTP request to the unified endpoint.

import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.INFERHOOD_API_KEY,
baseURL: "https://api.inferhood.xyz/v1",
});

const completion = await client.chat.completions.create({
model: "anthropic/claude-sonnet-4",
messages: [{ role: "user", content: "Execute trade strategy." }],
});

Built for machine commerce.

InferHood is designed for software that needs to purchase intelligence autonomously.

AI Agent
InferHood
Payment req.
Robinhood Chain
Receipt & Inference
Mainnet Chain ID
4663
Testnet Chain ID
46630
Gas Token
ETH

Built on Robinhood Chain

Frequently Asked Questions

Everything you need to know about InferHood.

InferHood is a unified AI model gateway that lets developers and autonomous AI agents access leading text, reasoning, coding, image, and audio models through one API, one API key, and one billing layer — powered by Robinhood Chain.

We support models from OpenAI, Anthropic, Google, xAI, Meta, DeepSeek, Mistral, Qwen, and FLUX — including GPT-4o, Claude Sonnet 4, Gemini 2.5 Pro, Grok 3, Llama 4, and more. Check the Models page for the full directory.

To access the InferHood API, you need to hold $INFER tokens in your wallet on Robinhood Chain. Once you connect your wallet and we verify your token balance, you can generate API keys and start making requests.

Yes. InferHood exposes OpenAI-compatible endpoints (/v1/chat/completions, /v1/models, etc.), so you can use the official OpenAI SDK or any compatible client — just point the base URL to InferHood and use your ih_ API key.

x402 is an agent-native payment protocol that lets autonomous AI agents pay for API calls directly on-chain using Robinhood Chain, without needing pre-provisioned API keys or credit card billing.

No. That's the whole point of InferHood. One account, one API key, one endpoint — we handle provider routing, authentication, and failover behind the scenes.

No. InferHood is an independent project building on the Robinhood Chain ecosystem. It is not affiliated with, endorsed by, or associated with Robinhood Markets, Inc.

Connect your wallet, ensure you hold $INFER tokens, generate an API key from the dashboard, and start making requests. Check the Docs for quickstart guides and code examples.

Start routing inference.

One API key gives your applications and agents access to every supported model.

$ npm install @inferhood/sdk