Llama 4 Maverick
by Meta · chat
Meta's first natively multimodal open-weight model using MoE architecture (17B active / 400B total, 128 experts). Beats GPT-4o and Gemini 2.0 Flash across broad benchmarks.
Pricing
Input: $0.372/M tokens · Output:
by Meta · chat
Meta's first natively multimodal open-weight model using MoE architecture (17B active / 400B total, 128 experts). Beats GPT-4o and Gemini 2.0 Flash across broad benchmarks.
Input: $0.372/M tokens · Output:
Vision, Function Calling, JSON Mode, Streaming
Context: 1000K tokens
Max output: 16K tokens
Routes: 2/2 healthy