tokentab

Nebius API Pricing 2026

Compare pricing for all Nebius LLM models. See input/output costs, context windows, and features.

Showing 27 models from Nebius. Prices are per 1 million tokens. Data sourced from official pricing pages via LiteLLM.

Models

27

Cheapest Input

$0.01

/1M tokens

Cheapest Output

$0.03

/1M tokens

Max Context

262K

tokens

27 models
Features
Qwen/Qwen2.5-Coder-7B$0.010$0.03032.8K32.8K
meta-llama/Llama-Guard-3-8B$0.020$0.060128K128K
meta-llama/Meta-Llama-3.1-8B-Instruct$0.020$0.060128K128K
Qwen/Qwen2-VL-7B-Instruct$0.020$0.060131.1K131.1K
mistralai/Mistral-Nemo-Instruct-2407$0.040$0.120128K128K
google/gemma-3-27b-it$0.060$0.200128K128K
Qwen/Qwen2.5-32B-Instruct$0.060$0.200128K128K
Qwen/Qwen3-14B$0.080$0.24032.8K32.8K
Qwen/Qwen3-4B$0.080$0.24032.8K32.8K
nvidia/Llama-3.3-Nemotron-Super-49B-v1$0.100$0.400131.1K131.1K
Qwen/Qwen3-30B-A3B$0.100$0.30032.8K32.8K
Qwen/Qwen3-32B$0.100$0.30032.8K32.8K
meta-llama/Llama-3.3-70B-Instruct$0.130$0.400128K128K
meta-llama/Meta-Llama-3.1-70B-Instruct$0.130$0.400128K128K
Qwen/Qwen2-VL-72B-Instruct$0.130$0.400131.1K131.1K
Qwen/Qwen2.5-72B-Instruct$0.130$0.400128K128K
Qwen/Qwen2.5-VL-72B-Instruct$0.130$0.400131.1K131.1K
Qwen/QwQ-32B$0.150$0.45032.8K32.8K
Qwen/Qwen3-235B-A22B$0.200$0.600262.1K262.1K
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.250$0.750128K128K
deepseek-ai/DeepSeek-V3$0.500$1.50128K128K
deepseek-ai/DeepSeek-V3-0324$0.500$1.50128K128K
nvidia/Llama-3.1-Nemotron-Ultra-253B-v1$0.600$1.80128K128K
deepseek-ai/DeepSeek-R1$0.800$2.40128K128K
deepseek-ai/DeepSeek-R1-0528$0.800$2.40164K164K
meta-llama/Meta-Llama-3.1-405B-Instruct$1.00$3.00128K128K
NousResearch/Hermes-3-Llama-3.1-405B$1.00$3.00128K128K

每周大模型价格速递

AI Model 调价时第一时间通知你。免费、不发垃圾邮件、随时退订。