Nebius AI

European cloud AI inference platform

European hostingGDPR complianceOpen modelsPricingOpenAI-compatible
HQ: Amsterdam, NetherlandsFounded: 2023nebius.ai

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

Intelligence Score
50.0
Total Requests
1
Success Rate
10000.0%
Avg Latency
4662ms
Models
51
Tokens Processed
58.7K

Nebius AI Models on Antbase

ModelScoreRequestsSuccess RateAvg Latencyp95 LatencyCapabilities
Qwen3 Next 80B A3B Thinking50.000.0%400ms1000ms
🧠🔧
Qwen3 Coder 480B A35B Instruct50.000.0%400ms1000ms
🔧
Hermes 4 70B50.000.0%400ms1000ms
Gemma 2 2b It50.000.0%400ms1000ms
🔧
Llama 3.3 70B Instruct Fast50.000.0%400ms1000ms
🔧
Llama 3 1 Nemotron Ultra 253B V150.000.0%400ms1000ms
🔧
Llama Guard 3 8B50.000.0%400ms1000ms
Qwen3 Coder 30B A3B Instruct50.000.0%400ms1000ms
🔧
Nemotron Nano V2 12b50.000.0%400ms1000ms
🔧
Gemma 2 9b It Fast50.000.0%400ms1000ms
🔧
Qwen2.5 Coder 7B Fast50.000.0%400ms1000ms
🔧
Llama 3.3 70B Instruct50.000.0%400ms1000ms
🔧
DeepSeek R1 052850.000.0%400ms1000ms
🧠
Qwen3 235B A22B Instruct 250750.000.0%400ms1000ms
🔧
Qwen3 235B A22B Thinking 250750.000.0%400ms1000ms
🧠🔧
Qwen3 32B50.000.0%400ms1000ms
🔧
Qwen3 32B Fast50.000.0%400ms1000ms
🔧
Gemma 3 27b It50.000.0%400ms1000ms
🔧
Gemma 3 27b It Fast50.000.0%400ms1000ms
🔧
Qwen2.5 VL 72B Instruct50.000.0%400ms1000ms
👁🔧
DeepSeek V3 032450.000.0%400ms1000ms
🔧
GLM 4.550.000.0%400ms1000ms
GLM 4.5 Air50.000.0%400ms1000ms
Gpt Oss 120b50.000.0%400ms1000ms
Gpt Oss 20b50.000.0%400ms1000ms
Kimi K2 Instruct50.000.0%400ms1000ms
Qwen3 30B A3B Thinking 250750.000.0%400ms1000ms
🧠🔧
Qwen3 30B A3B Instruct 250750.000.0%400ms1000ms
🔧
Hermes 4 405B50.000.0%400ms1000ms
INTELLECT 350.000.0%400ms1000ms
Kimi K2 Thinking50.000.0%400ms1000ms
🧠
NVIDIA Nemotron 3 Nano 30B A3B50.000.0%400ms1000ms
🔧
MiniMax M2.150.000.0%400ms1000ms
GLM 4.7 FP850.000.0%400ms1000ms
DeepSeek V3 0324 Fast50.000.0%400ms1000ms
🔧
DeepSeek R1 0528 Fast50.000.0%400ms1000ms
🧠
DeepSeek V3.250.000.0%400ms1000ms
🔧
GLM 550.000.0%400ms1000ms
Kimi K2.550.000.0%400ms1000ms
Meta Llama 3.1 8B Instruct Fast50.000.0%400ms1000ms
🔧
Meta Llama 3.1 8B Instruct50.000.0%400ms1000ms
🔧
Nemotron 3 Super 120b A12b50.000.0%400ms1000ms
🔧
DeepSeek V3.2 Fast50.000.0%400ms1000ms
🔧
Gpt Oss 120b Fast50.000.0%400ms1000ms
Qwen3.5 397B A17B Fast50.000.0%400ms1000ms
🔧
Qwen3 Next 80B A3B Thinking Fast50.000.0%400ms1000ms
🧠🔧
Kimi K2.5 Fast50.000.0%400ms1000ms
Qwen3.5 397B A17B50.000.0%400ms1000ms
🔧
MiniMax M2.550.000.0%400ms1000ms
Qwen3 235B A22B Thinking 2507 Fast50.000.0%400ms1000ms
🧠🔧
Kimi K345.0110000.0%217779ms217779ms

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.