Scaleway AI
InferenceEuropean cloud AI inference — GDPR-compliant, open models
Degraded
Elevated response times or partial issues
Last checked 21/09/2026, 9:43:17 am
555ms response
Uptime History0.00% uptime
2026-09-19Today
Uptime
0.00%
Avg Latency
668ms
P95 Latency
878ms
Fastest
322ms
Checks
150
Response Time
Last 60 checks322ms min668ms avg3675ms max
💰 Pricing
llama-3.3-70b
Input: $0.25/1MOutput: $0.25/1M
EU-based inference. Prices vary by region.
⚡ Rate Limits
standard
RPM: 100TPM: 100,000
EU data residency. Pay-as-you-go. Limits per region.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B European cloud AI. GDPR-compliant inference. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Degraded
555ms21 Sept, 09:43 am
Degraded
496ms21 Sept, 09:34 am
Degraded
804ms21 Sept, 09:21 am
Degraded
541ms21 Sept, 09:09 am
Degraded
811ms21 Sept, 08:52 am
Degraded
623ms21 Sept, 08:42 am
Degraded
777ms21 Sept, 08:34 am
Degraded
812ms21 Sept, 08:22 am
Degraded
568ms21 Sept, 08:09 am
Degraded
473ms21 Sept, 07:53 am
Degraded
798ms21 Sept, 07:42 am
Degraded
852ms21 Sept, 07:34 am
Degraded
803ms21 Sept, 07:21 am
Degraded
789ms21 Sept, 07:09 am
Degraded
666ms21 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
Hugging Face
Serverless inference API — 100k+ open models on demand