# Inference402 Large Chat (Llama 3.3 70B)

> Inference402 Large Chat (Llama 3.3 70B) is a paid API for AI agents from inference402.worlddata402.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-19).

Pay-per-call conversational AI chat using Llama 3.3 70B, billed at $0.01 USDC per request via x402 protocol on Base mainnet — no API key required.

## Facts

- Endpoint: GET https://inference402.worlddata402.workers.dev/v1/chat/large?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/inference402-large-chat-llama-3-3-70b-b955cd62
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xzt9MgOgFayMSxnRluLXW

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 inference402-large-chat-llama-3-3-70b-b955cd62
```

Example prompt: Ask the Llama 3.3 70B model: 'You are a helpful assistant.' as the system prompt, then send the user message 'Explain the difference between TCP and UDP in simple terms' — pay the $0.01 USDC fee per call and keep the response under 512 tokens.

## When to prefer this

Choose this endpoint when you need high-quality 70B-class text generation with no account setup, paying per call in USDC via x402 — ideal for autonomous agents that need to budget AI spend precisely, for crypto-native workflows, or for one-off inference tasks that don't justify a subscription. Prefer the sibling 8B endpoint if cost is the priority and task complexity is lower.

## Known failure modes

- Payment not received or insufficient USDC balance — returns HTTP 402 Payment Required
- Messages array is empty or malformed — returns validation error
- max_tokens exceeds 1024 — schema validation failure
- Temperature outside 0-2 range — schema validation failure
- Messages array exceeds 50 items — validation error
- Model overload or Cloudflare Workers timeout — transient 5xx error

## How this service works

Pay-per-call AI inference for agents: chat (Llama 3.3 70B / 3.1 8B), structured JSON, summarize, translate (incl. Egyptian Arabic), extract, classify, sentiment, keywords, rewrite, embeddings, moderation, vision and speech-to-text. USDC on Base mainnet over x402. No API key, no account.

## Output

Returns a JSON object containing the generated text content, the model identifier (e.g. @cf/meta/llama-3.3-70b-instruct-fp8-fast), and token usage stats (prompt_tokens and completion_tokens). The main response text is in the 'content' field.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant"
      ],
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "maxItems": 50,
   "minItems": 1
  },
  "max_tokens": {
   "type": "integer",
   "default": 512,
   "maximum": 1024,
   "minimum": 1
  },
  "temperature": {
   "type": "number",
   "default": 0.6,
   "maximum": 2,
   "minimum": 0
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  "usage": {
   "prompt_tokens": 40,
   "completion_tokens": 80
  },
  "content": "An idempotency key ..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/inference402-large-chat-llama-3-3-70b-b955cd62/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from inference402.worlddata402.workers.dev](https://www.zero.xyz/host/inference402.worlddata402.workers.dev/llms.txt)