Llama 4 Maverick

Meta· released 5 Apr 2025

meta-llama/llama-4-maverick

Input / 1M tokens: $0.188
Output / 1M tokens: $0.653

Context window1M tokens

Longest answer: 16K tokens

reads textreads imageopen weightstool callingvision

About

Llama 4 Maverick is Meta’s multimodal model with text and image input and text output. Its context window is 1,048,576 tokens, with a maximum output of 16,384 tokens. The model supports tools and has open weights. The supplied summary describes it as an Instruct model using a mixture-of-experts architecture, with 128 experts and 17 billion active parameters per forward pass. Its model ID is meta-llama/llama-4-maverick, and its Hugging Face ID is meta-llama/Llama-4-Maverick-17B-128E-Instruct. It was released on 2025-04-05. Listed pricing is USD 0.1875 per 1M input tokens and USD 0.6525 per 1M output tokens. The official page is on OpenRouter. Those details give teams concrete limits and token rates to weigh against their existing model stack.

Who it is for

It suits teams needing image and text inputs, tool support, and a large context window. The open weights and per-token prices are relevant to builders planning model access and cost.

What is good

Open weights are available.
Accepts text and image inputs.
Context window is 1,048,576 tokens.
Supports tools.
Input costs USD 0.1875 per 1M tokens.

What to know first

Maximum output is 16,384 tokens.
Output costs USD 0.6525 per 1M tokens.
No video input is listed.

Verdict

Llama 4 Maverick combines a million-token context window with image input and tools. Its listed output rate is higher than its input rate, so account for both when estimating usage.

Details

Lab: Metaopenrouter.ai · 3 Oct 2026
Context: 1,049Kopenrouter.ai · 3 Oct 2026
Input price: $0.188 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.653 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 16,384 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, imageopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash ctx262KinFreeoutFree inclusionAI Apodex 1.1 Mini (free) ctx262KinFreeoutFree Apodex Pareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiased GPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI GPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI Claude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed
Meta Models: Pricing per 1M Tokens and Context (2026)14 listed

Sources

openrouter.ai/meta-llama/llama-4-maverick· checked 3 Oct 2026