Inference API · flat rate

The model API your product
can ship on.

OpenAI-shaped chat completions. One monthly price. Capacity we operate. Credentials only after you subscribe.

Model legia-maxNo per-token invoiceFair-use limits
Scroll

Product

Built for backends that already speak OpenAI

Three rules. Same request shape. We own the hardware path so you do not rewire when capacity grows.

Drop-in shape

chat/completions, streaming, the client libraries you already use. Point base URL and key. No new SDK.

Flat monthly rate

$297/mo for text. You are not metered per token. Fair-use caps keep shared capacity stable for every seat.

Stable surface

Public model id and key stay the same when we add GPUs. Your integration does not change with our rack.

Access

How you get in

01

Subscribe

Account + Stripe checkout. No key before 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. Not public credentials.

Placeholder only. Your real base URL and key appear in the member 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 resale scrapers.

Pro

$297/mo

Flat rate for chat completions. Personal key, usage counters, member guide.

Stripe checkout. Cancel in the customer portal anytime.

  • OpenAI-compatible chat 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.

OpenAI-compatible?

Yes. Same chat completions shape. Full examples live in the member guide, not here.

What does flat rate mean?

No invoice by token count. Fair-use rate limits protect capacity for every subscriber.

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.