Meta

Llama 4 Maverick 17B Instruct

Open multimodal Llama for strong reasoning with efficient everyday serving

meta/llama-4-maverick-17b-instruct

Context

1M

Output

16.4K

Released

2025-04-05

Knowledge cutoff

2024-08

Types

InputTextImage
OutputText

Reasoning

—

Tool use

Supported

Structured output

—

Attachments

Supported

Open weights

Supported

Provider pricing

No providers currently list this model.

Benchmarks

  • Aider Polyglot

    15.6 · percent correct

  • SWE-Bench Pro

    5.24 · resolve rate

From the same lab