Model pricing

Llama 4 Scout API pricing

Get Llama 4 Scout API rates: $0.08/MTok input, $0.3/MTok output. Compare cache pricing, context limits, and API capabilities.

Input / 1M tokens $0.08

Output / 1M tokens $0.3

Cache read / 1M $0

Context window 327.7K

When to use Llama 4 Scout

Llama 4 Scout is listed from deepinfra with function calling. Use this page to estimate prompt cost and compare it against alternatives before routing production workloads.

source_key: deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct