N
Nebius
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
90%2026-09-192026-10-18
Inference Latency
Qwen: Qwen2.5 Coder 7B Instruct238ms TTFT · 96 TPS
Google: Gemma 2 9B266ms TTFT · 36 TPS
NVIDIA: Nemotron 3 Nano 30B A3B397ms TTFT · 82 TPS
Google: Gemma 3 27B731ms TTFT · 47 TPS
Qwen: Qwen3 30B A3B Instruct 2507333ms TTFT · 40 TPS
OpenAI: gpt-oss-120b332ms TTFT · 270 TPS
Qwen: Qwen3 235B A22B Instruct 2507364ms TTFT · 51 TPS
Reflection: Beam 1.0 501B A23B935ms TTFT · 97 TPS
DeepSeek: DeepSeek V4.1 Flash667ms TTFT · 68 TPS
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1320ms TTFT · 38 TPS
MoonshotAI: Kimi K2.7 Code1040ms TTFT · 182 TPS
Nous: Hermes 4 405B428ms TTFT · 39 TPS
Meta: Muse Spark Open1674ms TTFT · 95 TPS
Z.ai: GLM 5.2388ms TTFT · 175 TPS
Z.ai: GLM 5.3529ms TTFT · 94 TPS
Z.ai: GLM 5.1624ms TTFT · 31 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Qwen: Qwen2.5 Coder 7B Instruct | $0.03 | $0.09 | 238ms | 96 |
| Google: Gemma 2 9B | $0.03 | $0.09 | 266ms | 36 |
| NVIDIA: Nemotron 3 Nano 30B A3B | $0.06 | $0.24 | 397ms | 82 |
| Google: Gemma 3 27B | $0.10 | $0.30 | 731ms | 47 |
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.10 | $0.30 | 333ms | 40 |
| Nous: Hermes 4 70B | $0.13 | $0.40 | — | — |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 332ms | 270 |
| Prime Intellect: INTELLECT-3 | $0.20 | $1.10 | — | — |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.20 | $0.60 | 364ms | 51 |
| Reflection: Beam 1.0 501B A23B | $0.25 | $1.00 | 935ms | 97 |
| DeepSeek: DeepSeek V4.1 Flash | $0.30 | $1.20 | 667ms | 68 |
| NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 | $0.60 | $1.80 | 320ms | 38 |
| MoonshotAI: Kimi K2.7 Code | $0.95 | $4.00 | 1040ms | 182 |
| Nous: Hermes 4 405B | $1.00 | $3.00 | 428ms | 39 |
| Meta: Muse Spark Open | $1.25 | $4.25 | 1674ms | 95 |
| Z.ai: GLM 5.2 | $1.40 | $4.40 | 388ms | 175 |
| Z.ai: GLM 5.3 | $1.40 | $4.40 | 529ms | 94 |
| Z.ai: GLM 5.1 | $1.40 | $4.40 | 624ms | 31 |
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.