Hugging Face
InferenceFREE TIERServerless inference API — 100k+ open models on demand
Operational
All systems responding normally
Last checked 30/04/2026, 7:02:47 am
218ms response
Uptime History100.00% uptime
2026-04-25Today
Uptime
100.00%
Avg Latency
210ms
P95 Latency
258ms
Fastest
88ms
Checks
150
Response Time
Last 60 checks88ms min210ms avg542ms max
💰 Pricing
serverless inferenceFREE
Dedicated endpoints from $0.06/hr. Model pricing varies.
Free tier with rate limits
⚡ Rate Limits
free
RPM: 30TPM: 60,000
Free inference: 30 RPM, 60K TPM per model.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct Serverless inference. 100k+ models on demand. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
218ms30 Apr, 07:02 am
Operational
137ms30 Apr, 06:32 am
Operational
207ms30 Apr, 05:56 am
Operational
102ms30 Apr, 05:18 am
Operational
161ms30 Apr, 04:43 am
Operational
221ms30 Apr, 04:00 am
Operational
142ms30 Apr, 03:23 am
Operational
167ms30 Apr, 02:48 am
Operational
88ms30 Apr, 02:07 am
Operational
177ms30 Apr, 01:26 am
Operational
230ms30 Apr, 12:34 am
Operational
192ms29 Apr, 11:41 pm
Operational
174ms29 Apr, 10:56 pm
Operational
231ms29 Apr, 10:18 pm
Operational
190ms29 Apr, 09:45 pm
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
fal.ai
Ultra-fast image & video model inference for agents