← all models

Llama 4 Maverick

meta · 17B active

openrouter
Parameters 17B openrouter api · from the Hugging Face repo
Context 512K 524288 tokens
Input $0.35 OpenRouter
Output $1.00 OpenRouter
Cache read $0.17 OpenRouter

Accepts

text image

Capabilities

frequency_penalty logit_bias logprobs max_tokens presence_penalty repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_k top_logprobs top_p

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter meta-llama/llama-4-maverick huggingface meta-llama/Llama-4-Maverick-17B-128E-Instruct version slug meta-llama/llama-4-maverick-17b-128e-instruct name Meta: Llama 4 Maverick display name Llama 4 Maverick

Identifiers

Vendor
meta
OpenRouter
meta-llama/llama-4-maverick
Hugging Face
meta-llama/Llama-4-Maverick-17B-128E-Instruct
Version slug
meta-llama/llama-4-maverick-17b-128e-instruct
Active parameters
17B
Released
2025-04-05T19:37:02.000Z
First seen
59 d ago
Last crawled
20 min ago