Llama 3.1 Instruct (70B) (w/ latency optimized inference)

AWS Bedrock

Llamaembedding

Pricing

Input Price

$0.9

Output Price

—

Cached Input

—

Batch Input

—

Batch Output

—

per 1M tokens · USD

View official pricing →

Capabilities

Context—

Max Output—

Tools—

Batch—

Caching—

AWS Bedrock →

Related Models

Meta: Llama 3.1 70B Instruct

In: $0.4Out: $0.4

Meta: Llama 3.1 8B Instruct

In: $0.05Out: $0.08

Meta: Llama 3.2 11B Vision Instruct

In: $0.345Out: $0.345

Meta: Llama 3.2 1B Instruct

In: $0.027Out: $0.201

Meta: Llama 3.2 3B Instruct

In: $0.05Out: $0.33

Meta: Llama 3.2 3B Instruct (free)

In: FreeOut: Free