# GEDX402 Llama 3.3 70B Chat (x402)

> GEDX402 Llama 3.3 70B Chat (x402) is a paid API for AI agents from llm.gedx402.com, paid per call via x402, $0.06/call, status unknown (last checked 2026-09-14).

Runs a Llama 3.3 70B instruct chat completion, paid per-call with USDC via x402 on multiple chains — no API key required.

## Facts

- Endpoint: GET https://llm.gedx402.com/v1/chat/70b
- Price: $0.06/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-llama-3-3-70b-chat-x402-fc4ab9ad
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ICn_nOEYCrctMBoRzKTEn

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-llama-3-3-70b-chat-x402-fc4ab9ad
```

Example prompt: Ask the 70B Llama model what the capital of France is — keep the reply under 50 tokens — and pay for it with USDC on Base via x402.

## When to prefer this

Choose this endpoint when you need a capable 70B-class chat LLM without any API key or account setup, and your agent can pay per-call in USDC on Base, Polygon, Arbitrum, World, or Solana via the x402 protocol. Ideal for autonomous agents that need on-demand LLM inference with crypto-native micropayments.

## Known failure modes

- Payment not received or insufficient USDC balance — HTTP 402 returned requiring payment
- Invalid message format (missing role or content fields) — malformed request error
- max_tokens out of range (must be 1–4096) — validation error
- Network or Workers AI backend timeout — service unavailable
- Unsupported payment chain or wallet — payment rejected

## How this service works

Qwen3 30B FP8 frontier — reasoning, code, and agent tiers via ?full=1.

## Output

A JSON object containing the model identifier (@cf/meta/llama-3.3-70b-instruct-fp8-fast) and a 'response' string with the assistant's generated reply text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object"
   }
  },
  "max_tokens": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  "response": "Hello!"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-llama-3-3-70b-chat-x402-fc4ab9ad/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from llm.gedx402.com](https://www.zero.xyz/host/llm.gedx402.com/llms.txt)