NVIDIA NIM
InferenceFREE TIEROptimised inference microservices — GPU-native, enterprise-grade
Operational
All systems responding normally
Last checked 04/08/2026, 1:49:13 am
689ms response
Uptime History100.00% uptime
2026-07-30Today
Uptime
100.00%
Avg Latency
547ms
P95 Latency
830ms
Fastest
257ms
Checks
150
Response Time
Last 60 checks257ms min547ms avg1027ms max
💰 Pricing
llama-3.3-70bFREE
Input: $0.77/1MOutput: $0.77/1M
Build.nvidia.com free tier. Enterprise pricing via sales.
1000 credits free
⚡ Rate Limits
free
RPM: 40
1000 free API credits on signup.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B Enterprise-grade inference microservices. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
689ms4 Aug, 01:49 am
Operational
543ms4 Aug, 12:48 am
Operational
477ms3 Aug, 11:47 pm
Operational
826ms3 Aug, 10:48 pm
Operational
615ms3 Aug, 09:43 pm
Operational
625ms3 Aug, 08:28 pm
Operational
537ms3 Aug, 07:09 pm
Operational
620ms3 Aug, 05:51 pm
Operational
512ms3 Aug, 04:30 pm
Operational
513ms3 Aug, 03:15 pm
Operational
365ms3 Aug, 01:54 pm
Operational
350ms3 Aug, 12:35 pm
Operational
934ms3 Aug, 11:37 am
Operational
360ms3 Aug, 10:54 am
Operational
488ms3 Aug, 10:01 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
Cerebras
Wafer-scale chip inference — 1,000+ tokens/sec
Together AI
Open-source model inference — Llama, Mixtral, FLUX
Fireworks AI
Fast open-model inference — FireFunction, Llama, Mixtral
OpenRouter
Unified API across 200+ models — route by price or speed
Hugging Face
Serverless inference API — 100k+ open models on demand