Hugging Face
InferenceFREE TIERServerless inference API — 100k+ open models on demand
Operational
All systems responding normally
Last checked 21/09/2026, 9:43:17 am
189ms response
Uptime History100.00% uptime
2026-09-19Today
Uptime
100.00%
Avg Latency
196ms
P95 Latency
266ms
Fastest
73ms
Checks
150
Response Time
Last 60 checks73ms min196ms avg296ms 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
189ms21 Sept, 09:43 am
Operational
215ms21 Sept, 09:34 am
Operational
179ms21 Sept, 09:21 am
Operational
138ms21 Sept, 09:09 am
Operational
160ms21 Sept, 08:52 am
Operational
131ms21 Sept, 08:42 am
Operational
187ms21 Sept, 08:34 am
Operational
184ms21 Sept, 08:22 am
Operational
267ms21 Sept, 08:09 am
Operational
260ms21 Sept, 07:53 am
Operational
184ms21 Sept, 07:42 am
Operational
177ms21 Sept, 07:34 am
Operational
210ms21 Sept, 07:21 am
Operational
185ms21 Sept, 07:09 am
Operational
220ms21 Sept, 06:52 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
fal.ai
Ultra-fast image & video model inference for agents