Using Llama 3.2 3B Instruct on Cloudflare Workers AI

Implementation guide · Llama 3.2 · AI at Meta

ServerlessOpen Weights

Cloudflare Workers AI exposes Llama 3.2 3B Instruct through model ID @cf/meta/llama-3.2-3b-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

Quick Start

1
Create an account at Cloudflare Workers AI and generate an API key.
2
Use the Cloudflare Workers AI SDK or REST API to call @cf/meta/llama-3.2-3b-instruct — see the documentation for request format.
3
You'll be billed $0.05/1M input, $0.34/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

See Cloudflare Workers AI documentation for integration details.

Pricing on Cloudflare Workers AI

Type	Price (per 1M)
Input tokens	$0.05
Output tokens	$0.34

Capabilities

Structured Outputs

About Llama 3.2 3B Instruct

Llama 3.2 3B Instruct is Meta's Llama 3.2 model. It offers a 128K-token context window with weights openly available for self-hosting and scores 34.7 on MMLU PRO.

Full model details →

Model Specs

Released2024-09-25

Parameters3.21B

Context128k

ArchitectureDecoder Only

Knowledge cutoff2023-12

Cloudflare

San Francisco, California, United States