← model directory

cloudflare

meta/llama-3.2-3b-instruct

cloudflare/meta/llama-3.2-3b-instruct

↓ runs free on your own hardware

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

specs & pricing
Type
text
Provider
cloudflare
Model ID
cloudflare/meta/llama-3.2-3b-instruct
Context window
80K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.056 / 1M tokens
Output price
$0.37 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.