# GEDX402 Unified Workers AI Gateway

> GEDX402 Unified Workers AI Gateway is a paid API for AI agents from gateway.gedx402.com, paid per call via x402, $1.852/call, status unknown (last checked 2026-09-13).

Runs inference on a unified catalog of AI models (e.g. Claude, GPT-4o) via Cloudflare Workers AI, paid per-call with USDC on multiple chains, no API key required.

## Facts

- Endpoint: GET https://gateway.gedx402.com/v1/unified/run
- Price: $1.852/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-unified-workers-ai-gateway-e1a11054
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_y6UU7JDIc9FE7_1XLNqRJ

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability gedx402-unified-workers-ai-gateway-e1a11054
```

Example prompt: Using the GEDX402 unified AI gateway, send this chat message to anthropic/claude-sonnet-4-6 and get a reply with up to 200 tokens: 'Explain blockchain in one paragraph.' — pay with USDC, no API key needed.

## When to prefer this

Choose this endpoint when you need LLM inference without API key registration, want to pay per-call in USDC on Base, Polygon, Arbitrum, World, or Solana, and are building an agent or pipeline that benefits from crypto-native, keyless access to a unified catalog of models including Claude and GPT-4o.

## Known failure modes

- Payment not received or insufficient USDC balance — 402 Payment Required returned
- Invalid model slug (e.g. unsupported author/model) — model not found error
- Malformed messages array (missing role or content fields) — 400 Bad Request
- max_tokens exceeds model limit — truncation or error response
- Network timeout on Cloudflare Workers side — 503 or timeout error

## How this service works

Frontier chat via env.AI.run(author/model) and unified billing credits — no operator BYOK keys. POST model slug (allowlisted) and messages[]; x402 wire priced per model worst-case (not max across allowlist).

## Output

A JSON object containing the model name, token usage (input and output counts), an array of content blocks with the generated text, and the service identifier ('cloudflare-unified').

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object"
   }
  },
  "max_tokens": {
   "type": "number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "openai/gpt-4o-mini",
  "usage": {
   "input_tokens": 12,
   "output_tokens": 8
  },
  "content": [
   {
    "text": "Hello!",
    "type": "text"
   }
  ],
  "service": "gedx402-unified"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-unified-workers-ai-gateway-e1a11054/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gateway.gedx402.com](https://www.zero.xyz/host/gateway.gedx402.com/llms.txt)