Nebius AI

European AI cloud platform for scalable ML workloads.

📍 🇪🇺 EU7 models availableVisit Website →
7
Available Models
$0.7
Avg Input Price/M
$0.13
Cheapest Model
nebius/meta-llama/Llama-3.3-70B-Instruct
$2.00
Most Expensive
nebius/deepseek-ai/DeepSeek-V3-0324-fast

Features Overview

0
Vision Support
0
Advanced Reasoning
0
Caching Support
1
Computer Use

Privacy & Data Policy

Data Retention

No data retention

Location

🇪🇺 EU

All Nebius AI Models

View All Providers →
Context Window
128K tokens
Max Output
Unlimited
Input
$2.00/M tokens
Output
$6.00/M tokens

DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.

Context Window
128K tokens
Max Output
Unlimited
Input
$0.13/M tokens
Output
$0.4/M tokens

A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.

Context Window
131K tokens
Max Output
Unlimited
Input
$0.5/M tokens
Output
$2.40/M tokens
Context Window
262K tokens
Max Output
Unlimited
Input
$0.4/M tokens
Output
$1.80/M tokens
Context Window
128K tokens
Max Output
Unlimited
Input
$0.6/M tokens
Output
$2.20/M tokens
Context Window
128K tokens
Max Output
Unlimited
Input
$0.5/M tokens
Output
$1.50/M tokens

DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.

Computer Use
Context Window
164K tokens
Max Output
Unlimited
Input
$0.8/M tokens
Output
$2.40/M tokens

DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.

Ready to use Nebius AI models?

Access all Nebius AI models through Requesty's unified API with intelligent routing, caching, and cost optimization.

Nebius AI AI Models - Pricing & Features | Requesty