MetaLlama 4balancedVisionTool use

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 pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interact

1.0M context·~786K words·16K max output
Context window1.0Mtokens
Max output16Ktokens

Context window

This model accepts 1.0M tokens in one request (~786K words of text).

Context window size1.0M tokens
4K32K128K1M10M

What fits in one request

  • Short document
    About 1,500 words of text
    Fits
  • Long document
    About 37K words of text
    Fits
  • Small codebase
    About 150K words of text
    Fits
  • Full novel
    About 375K words of text
    Fits

Specifications

Context size, pricing, and release info in one place.

Context window
1,048,576 tokens (1.0M)
Max output tokens
16,384 tokens (16K)
Speed tier
balanced
Provider
Meta
Model family
Llama 4
Release date
Apr 2025

Capabilities

See which features this model supports, such as vision, tools, and streaming.

Supported (4)
Vision
Supported
Tool use
Supported
Function calling
Supported
Streaming
Supported
Not supported (4)
Extended thinking
Not supported
Web search
Not supported
Batch API
Not supported
Prompt caching
Not supported

Best for

Jump to a guide or ranking that matches each workload.

Compare Llama 4 Maverick

Open a side-by-side comparison with one click.

Frequently asked questions

Short answers about context size and how this model behaves.

Llama 4 Maverick has a context window of 1M tokens (1,048,576 tokens). This million-token window can process entire codebases, long legal documents, or book-length texts in a single pass.

More from Meta

Other models by Meta in our catalog.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model