Providers /Nebius AI Studio
Models
15
Regions
—
00
Editorial by LLMap · updated Aug 2, 2026Our take
Nebius is a cloud computing provider based in the Netherlands. It has verified European data residency and an independent security attestation, making it the default data-residency choice for downloadable-model inference in our catalogue.
Use this for GDPR-sensitive workloads needing EU processing with verified posture, or for European latency zones for downloadable-model inference. Skip it if you need the very broadest catalogue or the lowest absolute price on every model.
Strengths
- The only verified EU-headquartered option among major hosts we track.
- Competitive mid-size pricing on models such as Hermes 4 70B.
Trade-offs
- Catalogue skews to a narrower model set than DeepInfra or the aggregators.
01
Privacy & data handling
- ✓
- Yes
- ✗
- No
- No answer on record
The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.
Trains on your prompts
✗No
Logs prompts
✗No
✓Offered
✓Attested
Prompt retention: none.
02
Models & pricing
Gemma 3 27B27.4B$0.10 / $0.30 /1M110K5h agoGLM 5.1754B$1.40 / $4.40 /1M203K5h agogpt-oss-120b120B$0.15 / $0.60 /1M131K5h agoHermes 4 405B406B$1.00 / $3.00 /1M131K5h agoHermes 4 70B70.6B$0.13 / $0.40 /1M131K5h agoKimi K2.7 Code1.1T$0.95 / $4.00 /1M8K4d agoKimi K32.8T$3.00 / $15.00 /1M1M5d agoLlama 3.3 70B Instruct70.6B$0.13 / $0.40 /1M131K25h agoNemotron 3 Super124B$0.30 / $0.90 /1M262K5h agoQwen2.5 VL 72B Instruct73.4B$0.25 / $0.75 /1M32K5h agoQwen3 235B A22B Instruct 2507235B$0.20 / $0.60 /1M262K7h agoQwen3 30B A3B Instruct 250730.5B$0.10 / $0.30 /1M262K13h agoQwen3 32B32.8B$0.10 / $0.30 /1M41K5h agoQwen3 32B32.8B$0.10 / $0.30 /1M41K6d agoQwen3 Next 80B A3B Thinking81.3B$0.15 / $1.20 /1M128K5h ago