Skip to content
llmprice

Llama 4 Maverick 17B 128E Instruct FP8

Updated Sep 11, 2026

llama1.0M context16k max outputreleased Apr 5, 2025Open weightsTool calling
Cheapest input
$0.25
Cheapest output
$1
Official
output per 1M tokens
Providers
5
offering this model
Spread
1.5×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
AzureopenCheapest$0.25Cheapest$11.0M
Azure Cognitive Servicesopen$0.25$11.0M
watsonx.aiopen$0.371$1.484131k
Llamafreefreefree128k
Vercel AI Gatewayfreefreefree128k

Other llama models