Meta model

Llama 4 Maverick 17B 128E Instruct FP8

Llama 4 Maverick 17B 128E Instruct FP8 is available through 4 providers and 4 concrete deployments tracked by ALLM.

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

imagetextOfficial lab notation

Deployments

4

Providers

4

Max context

1.05M

Input from

$0.05 / 1M

Llama 4 Maverick 17B 128E Instruct FP8 provider comparison

Pricing and compatibility are tracked per provider deployment, because the same model can expose different features depending on where it runs.

ProviderProvider model IDModeRegionInputOutputContextTools
Azure AILlama-4-Maverick-17B-128E-Instruct-FP8Chatglobal$1.41 / 1M$0.35 / 1M1Msupported
Lambda AIllama-4-maverick-17b-128e-instruct-fp8Chatglobal$0.05 / 1M$0.10 / 1M131.1Ksupported
Meta LlamaLlama-4-Maverick-17B-128E-Instruct-FP8Chatglobal1Msupported
Ocimeta.llama-4-maverick-17b-128e-instruct-fp8Chatglobal$0.72 / 1M$0.72 / 1M1.05Msupported

More models from Meta