Llama 4 Maverick

Available
Meta logo
Meta
2025-04-05
32,000 tokens

Meta 开发的 AI 模型,适合多种 AI 应用场景。

Supported modalities:TextCode
Quick Overview
Text Generation2/10
Code Generation2/10
Reasoning2/10
Multimodal2/10
Benchmark Results
Scores from leading benchmark suites.
18.3%
artificial-analysis-intelligence
15.6%
artificial-analysis-coding
19.3%
artificial-analysis-math
Performance Metrics
Latency and throughput performance.
1000ms
P50 Latency
128.533
tokens/sec
Pricing Info
Input (1K tokens)$0.00031
Output (1K tokens)$0.00085
View detailed pricing
Feature support
Streaming
Tool calling
JSON mode
Llama 4 Maverick Model Review & Specs