Pricing

Plans that scale with you

Placeholder pricing page. The plans below mirror the home page; the FAQ uses native, zero-JS disclosure.

Pricing

Simple plans. Hard limits.

Start free and scale when you need to. Your plan is a flat platform fee — provider usage is always billed at cost from your prepaid balance.

Save 20%

Evaluate the gateway and ship side projects.

$0/mo$0/mobilled annually

For solo builders shipping to production.

$19/mo$15/mobilled annually

For teams that need real control.

$99/mo$79/mobilled annually

For high volume and compliance needs.

Custombilled annually

All plans include access to every provider. Usage is metered per token and billed at provider cost — never marked up.

How does billing actually work?

Your plan is a flat platform fee. On top of that, model usage is metered per token and billed at provider cost from your prepaid balance — no markup.

What stops costs from running away?

Every request is pre-authorized against your balance and caps. Prepaid plus a defined overdraft means a runaway loop is rejected, not billed.

Can I use my existing OpenAI code?

Yes. Omniflare is OpenAI-compatible — point the base URL at api.omniflare.com and keep your current SDK and calls.

Do you mark up provider pricing?

No. You pay provider rates for usage. The plan fee covers the gateway, controls, analytics and unified billing.

Start free

One key, every model, and budgets that can't be blown. Create an account and make your first call in minutes — no credit card required.