Nebius: Models Intelligence, Performance & Price
Analysis of Nebius's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Nebius for your use-case.
Most Intelligent
Updated
Intelligence index
Total 41 models
Fastest
Output speed
Total 41 models
Lowest Price
Blended price (per 1M tokens)
Total 41 models
Nebius offers 41 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Nebius are DeepSeek V4 Pro (Max) (44), Kimi K2.6 (43), DeepSeek V4 Pro (High) (41).
- For output speed, the fastest models are gpt-oss-120b (high) Fast (679 t/s), NVIDIA Nemotron 3 Super (401 t/s), gpt-oss-120b (high) Base (363 t/s). Speed varies significantly across models, with a 103% difference between the fastest and slowest.
- For latency, gpt-oss-120b (high) Base (1.02s), Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) (1.02s), gpt-oss-120b (low) Base (1.04s) offer the lowest time to first token.
- For pricing, NVIDIA Nemotron 3 Nano ($0.08), Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) ($0.08), Qwen3 32B Base ($0.12) offer the lowest blended prices per 1M tokens.
- For context window size, DeepSeek V4 Pro (1m), DeepSeek V4 Pro (Max) (1m), DeepSeek V4 Pro (High) (1m) support the largest context windows on Nebius.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence vs. Price
Context Window
Context Window
JSON Mode & Function Calling
Function (Tool) Calling & JSON Mode
| Models | Function calling | JSON Mode |
|---|---|---|
| DeepSeek V4 Pro (Max), Nebius | ||
| Kimi K2.6, Nebius | ||
| DeepSeek V4 Pro (High), Nebius | ||
| GLM-5.1 (FP8, Base), Nebius | ||
| GLM-5 (FP4), Nebius | ||
| Kimi K2.5 Fast, Nebius | ||
| Kimi K2.5, Nebius | ||
| Nemotron 3 Ultra, Nebius | ||
| GLM-5.1 (FP8, Base), Nebius | ||
| Kimi K2.6, Nebius | ||
| Qwen3.5 397B A17B (Base, FP4), Nebius | ||
| MiniMax-M2.5 (FP4), Nebius |
Pricing
Intelligence vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Key definitions
Frequently Asked Questions
Common questions about Nebius
Nebius offers 41 models that we track: DeepSeek V4 Pro (Max), Kimi K2.6, DeepSeek V4 Pro (High), GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.5, Nemotron 3 Ultra, GLM-5.1, Kimi K2.6, Qwen3.5 397B A17B, MiniMax-M2.5, DeepSeek V3.2, DeepSeek V3.2, GLM-5, Qwen3.5 397B A17B, Qwen3.5 397B A17B, DeepSeek V4 Pro, Kimi K2.5, NVIDIA Nemotron 3 Super, DeepSeek V3.2, DeepSeek V3.2, gpt-oss-120b (high), gpt-oss-120b (high), Qwen3 235B A22B 2507, Qwen3 Next 80B A3B, Qwen3 Next 80B A3B, Qwen3 235B 2507, gpt-oss-120b (low), NVIDIA Nemotron 3 Nano, Nemotron 3 Nano Omni 30B A3B Reasoning, Qwen3 32B, Hermes 4 70B, Llama Nemotron Ultra, Qwen3 30B A3B 2507, Hermes 4 405B, Hermes 4 405B, Qwen3 32B, Llama 3.3 70B, Hermes 4 70B, and Gemma 3 27B.
The most intelligent model available on Nebius is DeepSeek V4 Pro (Max) with an Intelligence Index score of 44.
The fastest model on Nebius by output speed is gpt-oss-120b (high) at 679.4 tokens per second.
The model with the lowest time to first token on Nebius is gpt-oss-120b (high) at 1.02s. Lower latency means faster initial response time.
The most affordable model on Nebius by blended price is NVIDIA Nemotron 3 Nano at $0.08 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Nebius vary up to 25x across models, from $0.08 per 1M tokens for NVIDIA Nemotron 3 Nano to $1.93 per 1M tokens for DeepSeek V4 Pro.
Yes, Nebius offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 41 models on Nebius support JSON mode for structured output.
Yes, all 41 models on Nebius support function calling (tool use).
Yes, Nebius offers 25 reasoning models: DeepSeek V4 Pro (Max), Kimi K2.6, DeepSeek V4 Pro (High), GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.5, Nemotron 3 Ultra, Qwen3.5 397B A17B, MiniMax-M2.5, DeepSeek V3.2, DeepSeek V3.2, NVIDIA Nemotron 3 Super, gpt-oss-120b (high), gpt-oss-120b (high), Qwen3 235B A22B 2507, Qwen3 Next 80B A3B, Qwen3 Next 80B A3B, gpt-oss-120b (low), NVIDIA Nemotron 3 Nano, Nemotron 3 Nano Omni 30B A3B Reasoning, Qwen3 32B, Hermes 4 70B, Llama Nemotron Ultra, and Hermes 4 405B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 41 models on Nebius are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Nebius, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.