# GEDX402 Qwen3-30B-A3B-FP8 LLM

> GEDX402 Qwen3-30B-A3B-FP8 LLM is a paid API for AI agents from llm.gedx402.com, paid per call via x402, $0.008/call, status unknown (last checked 2026-09-14).

Runs inference on Cloudflare Workers AI's Qwen3-30B-A3B-FP8 model, billed per call in USDC via x402 with no API key required

## Facts

- Endpoint: GET https://llm.gedx402.com/v1/llm/qwen3-30b-a3b-fp8
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-qwen3-30b-a3b-fp8-llm-2387b8e6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_d3N1MIXcIzNLtU9uvq9V7

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-qwen3-30b-a3b-fp8-llm-2387b8e6
```

Example prompt: Ask the Qwen3-30B model: 'You are a helpful assistant. Explain the concept of entropy in thermodynamics in plain English.' — use up to 512 tokens for the reply and pay with USDC on Base.

## When to prefer this

Choose this endpoint when you need a capable 30B-parameter instruction-following LLM without signing up for an API key, and you are comfortable paying per call in USDC via the x402 protocol on Base, Polygon, Arbitrum, World, or Solana. It is ideal for agents that need on-demand, permissionless LLM inference with crypto-native micropayments, especially when avoiding centralized API key management is a priority.

## Known failure modes

- Payment not received or insufficient USDC balance returns HTTP 402
- Invalid message role (not system/user/assistant) causes schema validation error
- max_tokens exceeds 4096 returns a parameter error
- Network timeout if model inference takes too long
- Empty messages array may return an error or empty response
- Unsupported payment network causes payment failure

## How this service works

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

## Output

A JSON object containing the model name (@cf/qwen/qwen3-30b-a3b-fp8) and a 'response' string with the assistant's generated text reply, capped at the requested max_tokens.

## 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/qwen/qwen3-30b-a3b-fp8",
  "response": "Hello!"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-qwen3-30b-a3b-fp8-llm-2387b8e6/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)