llm-proxy

Active

declared in 4.82.0

LLM inference proxy — pay USDC, get AI responses without managing API keys. Accepts a prompt and optional system instruction, forwards to OpenAI, returns the completion. Supports gpt-4o-mini (default, fast and cost-efficient) or gpt-4o (more capable). Agents that already hold USDC on Base can call this to run one-off LLM tasks without onboarding to OpenAI. Max 2,000 output tokens per call.

Parameters schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model to use. Default: gpt-4o-mini (fast, cost-efficient). Use gpt-4o for complex multi-step reasoning."
    },
    "prompt": {
      "type": "string",
      "description": "The user message / task to send to the LLM."
    },
    "system": {
      "type": "string",
      "description": "Optional system prompt. Sets the persona or role for the model."
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum output tokens. Default: 500. Increase for longer outputs."
    }
  },
  "additionalProperties": false
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

The Stall

1/7 registries

View full server →