Skip to content

Nemotron 3.5 Lightning 30b a3b (FREE)

nemotron-3.5-lightning:free

NvidiaChat (OpenAI-style)Degraded

Specifications

Endpoint type
Chat (OpenAI-style)
Context window
1000K tokens
Input price
FREE
Output price
FREE
Cache read price
FREE
Max output
32K tokens

Live status

Uptime 24h
89.69%
Uptime 7d
81.93%
Error rate
10.31%
Avg latency
13970 ms
Token speed 24h
15.1 tok/s
Nemotron 3.5 Lightning 30b a3b (FREE) | SleepyAI - Your Coding Agent and Unified AI GateWay