AI model proxy: GPT, Claude and Llama with no API key

Published on 2 min read

MyBotCloud injects the AI proxy's key and URL into your agent automatically — call GPT-4o mini, Claude 3.5 Haiku or free models without managing any API key.

Every AI agent hosted on MyBotCloud can call a language model without you ever creating an account with OpenAI, Anthropic or any other provider. The platform holds its own OpenRouter key and proxies the call — that's the AI model proxy.

How it works

Three environment variables are injected automatically into every agent, on its first deploy:

VariableWhat it's for
MYBOTCLOUD_AI_URLthe proxy's endpoint, which your code calls instead of going straight to a provider
MYBOTCLOUD_AI_KEYthis app's own credential, write-only — never your account key, never reused by another app
MYBOTCLOUD_AI_MODELthe model picked when the app was created (you can change it later)

Your code only needs one POST:

const res = await fetch(process.env.MYBOTCLOUD_AI_URL, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.MYBOTCLOUD_AI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: process.env.MYBOTCLOUD_AI_MODEL, // optional — without it, the free default model is used
    messages: [{ role: "user", content: "hi" }],
  }),
});
const { content } = await res.json();

Which model to pick

The catalog is curated on purpose — this is our own OpenRouter balance that every agent spends from, so "every model that exists" would not be a safe default:

ModelCostPlans
Nemotron UltrafreeStart, Pulse, Orbit
Llama 3.3 70BfreeStart, Pulse, Orbit
GPT-4o minipaid (our balance)Pulse, Orbit
Claude 3.5 Haikupaid (our balance)Orbit

The agent-creation screen already shows a picker with exactly which models your plan unlocks (locked ones are marked with the plan that unlocks them). To switch later without recreating the app, edit MYBOTCLOUD_AI_MODEL under Manage → Variables and redeploy.

Limits, on purpose

  • 20 calls per minute per app — a floor against a runaway loop, until a configurable spend cap exists.
  • Up to 20 messages per call, 8,000 characters each.
  • Without OPENROUTER_API_KEY configured on the server, the proxy answers 503 (turned off), never a generic network error.

Every call is logged (model, prompt/completion tokens, estimated cost) — today that's internal only, but it's the foundation for a future "runs" and cost tab, without you having to instrument anything in your own code.

Still stuck? Open a ticket in Support in the dashboard.

  • ai
  • openrouter
  • gpt
  • claude
  • ai agents

← Back to the blog