GetCheapAI

llama-4-maverick-17b-128e-instruct-fp8

Last Update: 08/05/2026, 22:13 UTC

llama-4-maverick-17b-128e-instruct-fp8 is currently listed on 1 API relay (third-party platforms), with pay-as-you-go input pricing from about $11.09 per 1M tokens.

Budget
$
PlatformPrice / CreditsExchange RatioInput / Output (per M tokens)
ApilioNew1 plans × 1 groups
$0.74 (¥5) / $5$0.15/USD$11.09/$11.09
These platforms do not support this model: Yunwu (shutting down soon)·Packy·Qianduoduo·OpenLux

Data is for reference only. Listing does not imply endorsement or guarantee.View Disclaimer