llmrelay
// pricing

One rate. Everyone.

Every user pays the same. No enterprise-only tiers, no volume gates. Top up when you need credit, use it when you need it, no expiry.

Model
Input / M tokens
Output / M tokens
vs list
claude-opus-4-7
flagship reasoning
$3.04
$15.19
−80%
claude-sonnet-4-7
fast, cost-efficient
soon
soon
gpt-4o / gpt-5
OpenAI models
soon
soon
gemini-2.5-pro
Google models
soon
soon

Prices in USD, billed per-token from your prepaid credit. Cached input reads at 0.10× rate; cache writes at 1.25×. All other major models are on their way — join the waitlist to be notified when they go live.

How billing works

01 — Top up

Pay $10, $50, $200 or any custom amount by card. Credit is added instantly. There is no monthly bill and no auto-charge.

02 — Use

Every API call is metered per-token at the rate above. Remaining balance is visible in the dashboard and via GET /v1/balance.

03 — Refill or leave

When credit runs low, top up again. Unused credit stays available with no expiration. Refunds available within 14 days per our refund policy.

$0.20 to start

Every new account gets $0.20 in free credit. Enough for a real Opus test call, no card required.

Join waitlist →