Cerebras
InferenceFREE TIERWafer-scale chip inference — 1,000+ tokens/sec
Operational
All systems responding normally
Last checked 12/06/2026, 3:45:10 am
123ms response
Uptime History100.00% uptime
2026-06-05Today
Uptime
100.00%
Avg Latency
251ms
P95 Latency
377ms
Fastest
76ms
Checks
150
Response Time
Last 60 checks76ms min251ms avg664ms max
💰 Pricing
llama-3.3-70bFREE
Input: $0.6/1MOutput: $0.6/1M
1000+ tokens/sec. llama-3.1-8b: $0.10/$0.10
Free tier available
⚡ Rate Limits
free
RPM: 30TPM: 60,000
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B 1000+ tokens/sec sustained | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
123ms12 June, 03:45 am
Operational
227ms12 June, 02:28 am
Operational
200ms12 June, 12:57 am
Operational
324ms11 June, 11:39 pm
Operational
239ms11 June, 10:03 pm
Operational
319ms11 June, 08:34 pm
Operational
175ms11 June, 06:50 pm
Operational
320ms11 June, 05:08 pm
Operational
317ms11 June, 03:21 pm
Operational
283ms11 June, 01:47 pm
Operational
127ms11 June, 12:22 pm
Operational
264ms11 June, 11:20 am
Operational
204ms11 June, 09:59 am
Operational
324ms11 June, 09:22 am
Operational
257ms11 June, 08:48 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
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
fal.ai
Ultra-fast image & video model inference for agents