Chat API · flat monthly rate

One key. One endpoint. No token invoice.

Scroll

Product

Built for product backends

One key, one model id. Call chat completions from your server. Capacity grows underneath without changing your integration.

Standard requests

chat/completions, streaming, curl / Python / Node. Set base URL and key. No custom SDK.

Flat monthly rate

$297/mo for text. Same bill every month. No token invoice, no surprise overage line.

Stable surface

Model id and key stay put when we add hardware. You keep shipping product; we run capacity.

Access

How you get in

01

Subscribe

Stripe checkout. No credentials until payment clears.

02

Open the dashboard

Base URL, model, limits, and key in one place. Member guide included.

03

Call from your backend

Use model legia-max. Keep the key on the server, never in a public frontend.

Request shape

Familiar calls. Private credentials.

Placeholder only. Real base URL and key appear in the dashboard after subscribe.

chat/completions
curl YOUR_BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "legia-max",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Add-on

Optional voice

Spoken replies for +$100/mo. Toggle in the dashboard. Same account, separate speech path.

audio/speech · placeholder
curl YOUR_BASE_URL/v1/audio/speech -H "Authorization: Bearer YOUR_KEY" -d '{"input":"Welcome back.","voice":"ana"}' --output reply.wav

Pricing

One plan. No metering.

Limited seats on shared capacity. Built for product traffic, not bulk scrapers.

Pro

$297/mo

Flat rate for chat. Personal key, usage counters, and the full member guide.

Stripe checkout. Cancel in the customer portal anytime.

  • Chat completions API
  • Model legia-max · streaming
  • Base URL + key after checkout
  • No per-token billing
  • Voice add-on +$100/mo
  • Stripe portal for card and invoices

FAQ

Short answers

Where is the base URL?

Only in your dashboard after subscribe. Marketing pages never show production endpoints.

What client libraries work?

Any HTTP client that can call chat completions: curl, Python, Node, and most SDKs that accept a custom base URL.

What does flat rate mean?

One monthly price for chat. Rate limits protect shared capacity so every seat stays usable.

Can end users hit the API from a browser?

Keep the key on your server. Cap max tokens. Handle 401, 429, and 5xx with backoff.