# 70B Chat Completion

> 70B Chat Completion is a paid API for AI agents from llmrt-companion.manhliemcn4euwlu.workers.dev, paid per call via x402, $0.000973/call, status unknown (last checked 2026-11-19).

Sends a prompt to a 70B large language model and returns the text completion, model name, and token budget used — no API key or signup required.

## Facts

- Endpoint: GET https://llmrt-companion.manhliemcn4euwlu.workers.dev/llm-70b-402?utm_source=zero.xyz
- Price: $0.000973/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/70b-chat-completion-6e5e3371
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1ZJbDuFVtY_kiugLCJq1n

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 70b-chat-completion-6e5e3371
```

Example prompt: Use the 70B chat completion endpoint to answer this question with up to 500 tokens: 'What are the key differences between transformer and RNN architectures in deep learning?'

## When to prefer this

Choose this endpoint when you need a powerful 70B-scale LLM completion with zero setup — no API key registration, no OAuth flow, and pay-per-call via x402 microtransactions. Ideal for agents that need on-demand text generation without maintaining LLM provider credentials, or when you want a large model for one-off completions at a predictable per-call price.

## Known failure modes

- Missing required 'prompt' query parameter returns an error or empty response
- max_tokens value too large may be truncated or rejected
- Model may time out on very long prompts or complex completions
- Payment failure via x402 protocol will block the request
- Non-GET HTTP methods will be rejected by the endpoint

## How this service works

One prompt in, one 70B completion out, plus model name and token budget. No API key, no signup.

## Output

Returns the generated text completion from the 70B model along with the model name and the token budget consumed. The response includes the raw completion string ready for downstream use.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "order_id"
     ],
     "properties": {
      "prompt": {
       "type": "string"
      },
      "system": {
       "type": "string"
      },
      "order_id": {
       "type": "string"
      },
      "max_tokens": {
       "type": "string"
      }
     },
     "additionalProperties": false
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/70b-chat-completion-6e5e3371/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from llmrt-companion.manhliemcn4euwlu.workers.dev](https://www.zero.xyz/host/llmrt-companion.manhliemcn4euwlu.workers.dev/llms.txt)
