SambaNova Cloud
activeRDU-accelerated inference with a persistent free tier — no credit card required. Llama 3.1/3.2/3.3 series up to 405B, 200K tokens/day free.
https://api.sambanova.ai/v1
Avg Latency
—
90-day Uptime
—%
Rate Limits
20 RPM / — RPD
Sign-up Required
Yes
Info
Base URL https://api.sambanova.ai/v1
Sign-up Required Yes
Credit Card Not required
Context Window 128K
Last Verified 2026-03-30
fast-inferenceopenai-compatiblellamavisionfunction-call
Models (8)
Meta-Llama-3.3-70B-Instruct
CTX: 128K · 20 RPM
Meta-Llama-3.1-8B-Instruct
CTX: 128K · 30 RPM
Meta-Llama-3.1-70B-Instruct
CTX: 128K · 20 RPM
Meta-Llama-3.1-405B-Instruct
CTX: 128K · 10 RPM
Meta-Llama-3.2-1B-Instruct
CTX: 128K · 30 RPM
Meta-Llama-3.2-3B-Instruct
CTX: 128K · 30 RPM
Meta-Llama-3.2-11B-Vision-Instruct
CTX: 128K · 10 RPM
Meta-Llama-3.2-90B-Vision-Instruct
CTX: 128K · 1 RPM
Quick Start
export API_KEY="your_api_key_here"
curl https://api.sambanova.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "Meta-Llama-3.3-70B-Instruct",
"messages": [
{"role": "user", "content": "Hello! How are you?"}
]
}'