Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
For $1, you can send approximately:
~143messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.20/M = $0.001400
Output cost per message7,000 x $0.80/M = $0.005600
Total cost per message$0.007000
Messages for $1142.86
Context window
1.0M
tokens
Max response
16k
tokens
Input price
$0.20
per million tokens
Output price
$0.80
per million tokens
Modalities
Input:textInput:imageOutput:text
Description
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...