AI Model Radar

Groq-Llama-4-Maverick-17B-128E-Instruct

Llama first-party · 128,000 ctx · from $0 input / $0 output per 1M tokens

ProviderLlama
Familyllama
Context window128,000
Max output4,096
Input price$0
Output price$0
Cache read
Cache write
ReasoningNo
Tool callingYes
VisionNo
Open weightsYes
Knowledge cutoff2025-01
Released2025-04-05
Last updated2025-04-05

Identity: Llama; data via models.dev + OpenRouter public APIs. Always confirm on the provider's official pricing page.