Nebius AI
European cloud AI inference platform
European hostingGDPR complianceOpen modelsPricingOpenAI-compatible
About Nebius AI
Nebius (formerly Yandex Cloud) offers AI inference services from European data centers. They provide access to popular open-source models with competitive pricing and GDPR-compliant infrastructure.
Key Models
Llama 4 MaverickQwen 3.5DeepSeek R1
Live Performance Data
Nebius AI Models on Antbase
| Model | Score | Requests | Success Rate | Avg Latency | p95 Latency | Capabilities |
|---|---|---|---|---|---|---|
| Qwen3 Next 80B A3B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 Coder 480B A35B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Hermes 4 70B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Gemma 2 2b It | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Llama 3.3 70B Instruct Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Llama 3 1 Nemotron Ultra 253B V1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Llama Guard 3 8B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 Coder 30B A3B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Nemotron Nano V2 12b | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Gemma 2 9b It Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 Coder 7B Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Llama 3.3 70B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek R1 0528 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| Qwen3 235B A22B Instruct 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 235B A22B Thinking 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 32B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 32B Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Gemma 3 27b It | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Gemma 3 27b It Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 VL 72B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁🔧 |
| DeepSeek V3 0324 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 4.5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| GLM 4.5 Air | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Gpt Oss 120b | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Gpt Oss 20b | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2 Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 30B A3B Thinking 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 30B A3B Instruct 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Hermes 4 405B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| INTELLECT 3 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2 Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| NVIDIA Nemotron 3 Nano 30B A3B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| MiniMax M2.1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| GLM 4.7 FP8 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| DeepSeek V3 0324 Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek R1 0528 Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| DeepSeek V3.2 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2.5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Meta Llama 3.1 8B Instruct Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Meta Llama 3.1 8B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Nemotron 3 Super 120b A12b | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek V3.2 Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Gpt Oss 120b Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3.5 397B A17B Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Next 80B A3B Thinking Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Kimi K2.5 Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3.5 397B A17B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| MiniMax M2.5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 235B A22B Thinking 2507 Fast | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Kimi K3 | 45.0 | 1 | 10000.0% | 217779ms | 217779ms |
How to Use Nebius AI on Antbase
All Nebius AI models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Nebius AI model or let ANT's intelligent router automatically select the best model for your task.
python
from openai import OpenAI
client = OpenAI(
base_url="https://antbase.ai/v1",
api_key="your-ant-api-key",
)
# Let ANT auto-route (may use Nebius AI if optimal)
response = client.chat.completions.create(
model="ant:auto",
messages=[{"role": "user", "content": "Hello!"}],
)
# Or route directly to a Nebius AI model
response = client.chat.completions.create(
model="nebius/llama-4-maverick",
messages=[{"role": "user", "content": "Hello!"}],
)Why Use Nebius AI Through Antbase?
- •No separate account needed — access Nebius AI models instantly through your Antbase API key.
- •Intelligent routing — ANT automatically selects the best Nebius AI model for each task, or falls over to another provider if Nebius AI is slow or down.
- •Same token prices — Antbase charges zero markup on Nebius AI token prices. You pay exactly what Nebius AI charges.
- •Automatic failover — if Nebius AI has an outage, your requests seamlessly route to an equivalent model on another provider.