Llama 4 Maverick 17B 128E Instruct

Frontier

Compare pricing across 5 providers. Cheapest: Groq at $0.300/1M tokens.

Family

meta-llama

Context Window

131K

Max Output

16K

Arena ELO

1290

Type

chat

Provider Pricing(5 providers)

Provider	Input/1M↑	Output/1M	Cached In	Speed	TTFT	Link
OpenRouter	$0.180	$0.720	—	—	—	Use model
GroqCheapest	$0.200	$0.600	—	—	—	Use model
Google Vertex AI	$0.350	$1.15	—	—	—	Use model
Deepinfra	$0.500	$0.500	—	—	—	Use model
SambaNova	$0.630	$1.80	—	—	—	Use model

Model Aliases

sambanova/Llama-4-Maverick-17B-128E-Instructmeta-llama-4-maverick-17b-128e-instruct-maasmeta/llama-4-maverick-17b-128e-instruct-maasmeta-llama-llama-4-maverick-17b-128e-instructmeta-llama/llama-4-maverick-17b-128e-instructllama-4-maverick-17b-16e-instructmeta/llama-4-maverick-17b-16e-instruct-maasllama-4-maverickMeta: Llama 4 Maverick

Try on Groq Compare with other models Estimate monthly cost

Frequently Asked Questions

The cheapest provider for Llama 4 Maverick 17B 128E Instruct is currently Groq at $0.3000 per million tokens (blended rate). Prices are verified every 6 hours. Check the provider comparison table below for all available options.

Prices in USD per 1M tokens. Updated every 6 hours.