Novita AI
Inference200+ models via one API — LLM, image, video, TTS
Operational
All systems responding normally
Last checked 19/09/2026, 12:36:01 pm
594ms response
Uptime History100.00% uptime
2026-09-17Today
Uptime
100.00%
Avg Latency
588ms
P95 Latency
729ms
Fastest
400ms
Checks
150
Response Time
Last 60 checks400ms min588ms avg893ms max
💰 Pricing
llama-3.3-70b
Input: $0.45/1MOutput: $0.45/1M
LLM + image + video + TTS in one API
⚡ Rate Limits
free
RPM: 60TPM: 120,000
Free: 60 RPM. Paid: higher limits available.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B 200+ models via one API. LLM/image/video/TTS. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
594ms19 Sept, 12:36 pm
Operational
514ms19 Sept, 12:15 pm
Operational
573ms19 Sept, 11:51 am
Operational
621ms19 Sept, 11:30 am
Operational
557ms19 Sept, 11:07 am
Operational
701ms19 Sept, 10:31 am
Operational
494ms19 Sept, 09:52 am
Operational
729ms19 Sept, 09:43 am
Operational
597ms19 Sept, 09:36 am
Operational
513ms19 Sept, 09:26 am
Operational
593ms19 Sept, 09:10 am
Operational
516ms19 Sept, 08:52 am
Operational
543ms19 Sept, 08:44 am
Operational
861ms19 Sept, 08:36 am
Operational
628ms19 Sept, 08:26 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