Novita AI

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

A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.

Pricing

$0.2
Input tokens per million
$0.85
Output tokens per million

Technical Specifications

Context Window
1.0M tokens
Max Output Tokens
1.0M tokens
Global Availability
Last Updated
N/A

Provider

Novita AI
Location
πŸ‡ΊπŸ‡Έ US
Visit Website β†’

Privacy & Data

Data Retention
No
Used for Training
No
Novita AI Privacy Policy β†’
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 - AI Model Details | Requesty | Requesty