meta-llama: Meta Llama 4 Scout 17B 16E

llama-4-scout
Context: 131k
Max Output: 8k
Input: $0.080/1M
Output: $0.300/1M
Llama 4 instruction-tuned MoE (17B, 16 experts) for fast, high-quality chat, tool use, and multilingual reasoning with balanced latency and cost.
Input: Text, Image
Output: Text

Providers

deepinfra
Credits
Context131k
Max Output8k
Input$0.080/1M
Output$0.300/1M
Cache Read—
Cache Write—
groq
Credits
Context131k
Max Output8k
Input$0.110/1M
Output$0.340/1M
Cache Read—
Cache Write—
Image$367.62
novita
Credits
Context131k
Max Output8k
Input$0.100/1M
Output$0.500/1M
Cache Read—
Cache Write—
openrouter
Credits
Context131k
Max Output8k
Input (Max)$0.690/1M
Output (Max)$0.900/1M
Cache Read—
Cache Write—

Quick Start

Use Meta Llama 4 Scout 17B 16E through Helicone's AI Gateway with automatic logging and monitoring.