---
id: "meta-llama/llama-4-maverick"
also: ["meta-llama/llama-4-maverick-17b-128e-instruct", "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "vercel/meta/llama-4-maverick"]
cheapest_list_usd_per_m: "0.1875 in, 0.6525 out, at digitalocean on openrouter"
cheapest_effective_usd_per_m: "0.1872 in, 0.6491 out, at digitalocean on openrouter"
context: 524288
max_output: 32768
input: ["text", "image"]
output: ["text"]
released: "2025-04-05"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 7
gateways: "openrouter (5), vercel (2)"
no_training: 7
trains: 0
retains_prompts: 0
coding: 16.3000
agentic: 0.6000
---
# Meta: Llama 4 Maverick

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...