Llama 4 Maverick
Meta馃嚭馃嚫
meta-llama/llama-4-maverickLlama 4 Maverick is Meta's high-capability open-weight Mixture-of-Experts model, offering strong multimodal (text and image) understanding, reasoning, and coding at efficient inference cost. It targets general-purpose assistant and agentic use cases needing frontier-adjacent quality in an open model.
Cost rate
0.1x
Context
524K
Released
Apr 5, 2025
Input
TextImage
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Image understanding
#119 路 top 72%
Writing, Literature, & Language
#238 路 top 57%
Legal & Government
#238 路 top 61%
Medicine & Healthcare
#238 路 top 62%
Performance
Median latency and throughput measured across recent requests.
Throughput45 tok/s
Latency