Llama 3.2 3B Instruct

Compact Llama 3.2 3B for efficient inference.

llama-3.2-3b-instruct

STABLE

32,768 context

Starting at $0.03/M input tokens

Starting at $0.05/M output tokens

Streaming

JSON Output

Select Provider

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

UNSTABLE

novita/llama-3.2-3b-instruct

Context Size

32.8k

Stability

unstable

Pricing

Input

$0.03

Cached

—

Output

$0.05

Capabilities

Streaming

JSON Output