ZeroReader · Llama 3.2 3B Inference

Ideal buyer

Developers and agents needing fast, cost-effective LLM inference for simple tasks without premium model overhead.

Prompt for your agent

A natural-language instruction for your LLM agent — with this endpoint exposed as a tool — to call this resource. Not sent to the endpoint; the endpoint consumes the JSON body below.

Endpoint request body

The JSON payload your agent sends to the endpoint.

{
  "messages": [
    {
      "role": "user",
      "content": "Summarize this customer feedback in one sentence: 'The app crashes when I try to upload photos, but the design is beautiful and intuitive otherwise.'"
    }
  ],
  "max_tokens": 256,
  "temperature": 0.7
}

Endpoint URL

curl fallback

curl https://api.zeroreader.com/v1/ai/llama-3b \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: [signed_payment_envelope]" \
  -d '{"messages":[{"role":"user","content":"Summarize this customer feedback in one sentence: 'The app crashes when I try to upload photos, but the design is beautiful and intuitive otherwise.'"}],"max_tokens":256,"temperature":0.7}'

Payment & settlement details

Raw on-chain settlement parameters. AXON above handles these automatically through quote / test-buy / governed fetch.