N
Nebius
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-07-212026-08-19
Inference Latency
Google: Gemma 2 9B266ms TTFT · 36 TPS
Qwen: Qwen2.5 Coder 7B Instruct238ms TTFT · 96 TPS
Google: Gemma 3 27B513ms TTFT · 19 TPS
Qwen: Qwen3 32B659ms TTFT · 22 TPS
Qwen: Qwen3 30B A3B Instruct 2507351ms TTFT · 45 TPS
Meta: Llama 3.3 70B Instruct1362ms TTFT · 8 TPS
Nous: Hermes 4 70B264ms TTFT · 64 TPS
OpenAI: gpt-oss-120b330ms TTFT · 174 TPS
Qwen: Qwen3 Next 80B A3B Thinking320ms TTFT · 99 TPS
Qwen: Qwen3 235B A22B Instruct 2507652ms TTFT · 29 TPS
Qwen: Qwen2.5 VL 72B Instruct809ms TTFT · 24 TPS
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1320ms TTFT · 38 TPS
Nous: Hermes 4 405B509ms TTFT · 31 TPS
Z.ai: GLM 5.1543ms TTFT · 32 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Google: Gemma 2 9B | $0.03 | $0.09 | 266ms | 36 |
| Qwen: Qwen2.5 Coder 7B Instruct | $0.03 | $0.09 | 238ms | 96 |
| Google: Gemma 3 27B | $0.10 | $0.30 | 513ms | 19 |
| Qwen: Qwen3 32B | $0.10 | $0.30 | 659ms | 22 |
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.10 | $0.30 | 351ms | 45 |
| Meta: Llama 3.3 70B Instruct | $0.13 | $0.40 | 1362ms | 8 |
| Nous: Hermes 4 70B | $0.13 | $0.40 | 264ms | 64 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 330ms | 174 |
| Qwen: Qwen3 Next 80B A3B Thinking | $0.15 | $1.20 | 320ms | 99 |
| Prime Intellect: INTELLECT-3 | $0.20 | $1.10 | — | — |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.20 | $0.60 | 652ms | 29 |
| Qwen: Qwen2.5 VL 72B Instruct | $0.25 | $0.75 | 809ms | 24 |
| NVIDIA: Nemotron 3 Super | $0.30 | $0.90 | — | — |
| NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 | $0.60 | $1.80 | 320ms | 38 |
| Nous: Hermes 4 405B | $1.00 | $3.00 | 509ms | 31 |
| Z.ai: GLM 5.1 | $1.40 | $4.40 | 543ms | 32 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.