Meta2 providers available

Llama 4 Maverick

Meta's open multimodal MoE model. Available for free on Groq and Cloudflare Workers AI, or self-hosted on any hardware.

Best price

$0.270

per 1M input tokens

Best benchmark

—

top score across benchmarks

Providers

APIs serving this model

Compare providers

Provider / Variant	Input $/1M	Output $/1M	Latency	Context
BEST PRICE meta-llama Llama 4 Maverick Instruct (17Bx128E) FP8	$0.270	$0.850	—	1049k	Details
meta-llama Meta: Llama 4 Maverick	—	—	24ms	1049k	Details

Compare with another model

See how Llama 4 Maverick stacks up side-by-side.

Looking for alternatives?

Find cheaper or faster models in the same class.