meta-llama: Meta Llama 4 Maverick 17B 128E

llama-4-maverick
Context: 131k
Max Output: 8k
Input: $0.150/1M
Output: $0.600/1M
Llama 4 instruction-tuned MoE (17B, 128 experts) targeting tougher reasoning and long-form tasks, trading more compute for higher response diversity and robustness.
Input: Text, Image
Output: Text

Providers

deepinfra
Credits
Context131k
Max Output8k
Input$0.150/1M
Output$0.600/1M
Cache Read—
Cache Write—
groq
Credits
Context131k
Max Output8k
Input$0.200/1M
Output$0.600/1M
Cache Read—
Cache Write—
novita
Credits
Context131k
Max Output8k
Input$0.170/1M
Output$0.850/1M
Cache Read—
Cache Write—
openrouter
Credits
Context131k
Max Output8k
Input (Max)$0.660/1M
Output (Max)$1.90/1M
Cache Read—
Cache Write—

Quick Start

Use Meta Llama 4 Maverick 17B 128E through Helicone's AI Gateway with automatic logging and monitoring.