
SAMPLE OUTPUT
━━ MODEL
Llama 3.3 70B Instruct.
Meta
llama-3.3-70b-instruct
Open-weight reasoning + chat. 128K context.
━━ RATE
$0.0008
per 1K output tokens
ALL-IN. NO HIDDEN FEES.
━━ INPUT
PLAYGROUND
━━ OUTPUT
AWAITING INPUT.
━━ CURL
CALL IT FROM
ANYTHING.
curl https://plumestudios.dev/api/run/llama-3.3-70b-instruct \
-H "Authorization: Bearer $PLUME_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "…"
}'