Amux

Choose how you pay

One API for every major model. Inference is billed at the provider's own rates — we add no markup and no fees.

Pay as you go

Pay as you go

Pay for what you use

  • No top-up fees, no markup on inference
  • Compare every provider's price for the same model
  • Token-level usage detail; cost returned in the response body

Best for

Production workloads, commercial products, teams that need cost attribution

Explore pay as you go

Subscription

Subscription

Coming soon

A flat monthly fee

  • Flat monthly fee, predictable cost
  • Quota-based; falls back to pay as you go when the quota runs out
  • Built for individual development and learning

Best for

Individual development, learning, non-production exploration

Explore subscription

Detailed comparison

FeaturePay as you goSubscriptionComing soon
Billing modelBilled on actual usageFlat monthly fee + quota
Best forProduction, commercial productsIndividual development, learning
Cost predictabilityTracks usageHigh (flat fee)
Platform markupNone — provider list priceTo be decided
Top-up feeNoneNot applicable
Provider comparisonYes — pin a provider or use auto routingTo be decided
Usage detailToken level, including cache and reasoning tokensTo be decided
RefundsUnused credit refundable to the original method — see the refund policyTo be decided

Frequently asked questions