invokeable()
← directory / models / llama-4-maverick

Llama 4 Maverick

model llama-4-maverick

Draft entry — numbers not yet verified against primary sources.

1M
context
8K
max output
—
input
—
output
2024-08
knowledge cutoff
3
providers

01Providers

ProviderProvider model IDIn $/MOut $/MContextStatus
Groq meta-llama/llama-4-maverick-17b-128e-instruct — — 1M live
Together AI meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 — — 1M live
OpenRouter meta-llama/llama-4-maverick — — 1M live

02Invoke

provider
language

  

  



03Related
Llama 3.3 Nemotron Super 49B v1.52025-07Llama 3.1 Nemotron 70B Instruct2025-04Llama 3.1 Nemotron Ultra 253B2025-04Llama 3.3 Nemotron Super 49B v12025-04Llama 4 Maverick 17B Instruct2025-04Llama 4 Scout2025-04


04Sources · where these numbers come from
  1. https://www.llama.com/docs/overview/
  2. https://huggingface.co/meta-llama
  3. https://console.groq.com/docs
  4. https://docs.together.ai
  5. https://openrouter.ai/docs
  6. https://openrouter.ai/meta-llama/llama-4-maverick