The Aria API

Getting a key

Keys are issued by our team. Tell us your expected monthly volume and we will send you a key that starts with ak_live_, along with your monthly quota and per-minute rate limit. Keep the key on your server — never in browser code.

Endpoint

POST /api/public/aria/chat

• messages — array of { role, content } with roles user, assistant or system.
• model — optional; defaults to Aria (Gemini Flash).
• system — optional instructions to shape Aria for your brand.
• stream — optional; true returns server-sent events with { delta } chunks, ending with [DONE].

cURL

curl -X POST https://theremoteus.com/api/public/aria/chat \
  -H "Authorization: Bearer ak_live_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Write a polite follow-up email to a client." }
    ]
  }'

JavaScript

const res = await fetch("https://theremoteus.com/api/public/aria/chat", {
  method: "POST",
  headers: {
    Authorization: "Bearer ak_live_your_key",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "google/gemini-3.7-flash",
    messages: [{ role: "user", content: "Fix the grammar: we is going tomorrow" }],
  }),
});

const { reply } = await res.json();

Available models

• google/gemini-3.7-flash — Aria (Gemini Flash): Fast, balanced — the default
• google/gemini-3.1-pro-preview — Gemini Pro: Deeper reasoning, slower
• openai/chat-latest — ChatGPT: Natural conversational style
• openai/gpt-5.6-terra — GPT-5.6: OpenAI reasoning model

Limits and errors

• 401 — missing or invalid key. 403 — key revoked or model not enabled.
• 429 — per-minute rate limit reached; retry shortly.
• 402 — monthly quota used up; contact us to upgrade.