Llama 4 Maverick Instruct by NovitaAI — Specs, Pricing & Capabilities | whichllm

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

Provider NovitaAI

Family -

Status -

Knowledge Cutoff -

Release Date 2025-04-06

Input Modalities text, image

Output Modalities text

Context Window 1048576

Input Limit -

Output Limit 8192

Tool Calling No

Reasoning No

Structured Output -

Temperature Control Yes

Open Weights Yes

Input Cost / 1M tokens $0.27

Output Cost / 1M tokens $0.85

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -