Price Per TokenPrice Per Token
Nebius AIvsNovita AI

Nebius AI vs Novita AI

Compare pricing across 16 shared models. Nebius AI offers 24 models, Novita AI offers 82.

8 Ways to Use Fewer Tokens

Get the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.

16
Shared Models
5
Nebius AI Cheaper
6
Novita AI Cheaper
5
Same Price

Price Comparison — Shared Models

Model ↑Nebius AI Input Novita AI Input Nebius AI Output Novita AI Output Cheaper
Gemma 2 9B $0.030 $0.080 $0.090 $0.080Nebius AI
GLM 4.5 $0.600 $0.600 $2.20 $2.20Same
GLM 4.5 Air $0.200 $0.130 $1.20 $0.850Novita AI
GLM 4.7 $0.400 $0.540 $2.00 $1.98Nebius AI
GPT-OSS-20b $0.050 $0.040 $0.200 $0.150Novita AI
Kimi K2 Thinking $0.600 $0.600 $2.50 $2.50Same
Llama 3.1 8B Instruct $0.020 $0.020 $0.060 $0.050Novita AI
Llama 3.3 70B Instruct $0.130 $0.135 $0.400 $0.400Nebius AI
MiniMax M2.1 $0.300 $0.300 $1.20 $1.20Same
MiniMax M2.5 $0.300 $0.300 $1.20 $1.20Same
Qwen3 32B $0.100 $0.100 $0.300 $0.450Nebius AI
Qwen3 Coder 30B A3B Instruct $0.100 $0.070 $0.300 $0.270Novita AI
Qwen3 Coder 480B A35B (exacto) $0.400 $0.300 $1.80 $1.30Novita AI
Qwen3 Next 80B A3B Thinking $0.150 $0.150 $1.20 $1.50Nebius AI
Qwen3.5 397B A17B $0.600 $0.600 $3.60 $3.60Same
R1 0528 $2.00 $0.700 $6.00 $2.50Novita AI

Model Coverage

Nebius AIOnly on Nebius AI(8)
Hermes 4 405B$1.00/M
Hermes 4 70B$0.130/M
INTELLECT-3$0.200/M
meta-llama-llama-guard-3-8b$0.020/M
Nemotron 3 Super 120B A12B$0.300/M
Qwen2.5 Coder 7B Instruct$0.030/M
Qwen3 30B A3B Instruct 2507$0.100/M
Qwen3 30B A3B Thinking 2507$0.100/M
Shared(16)
16
models available on both
Nebius AINovita AI
24 total82 total
Novita AIOnly on Novita AI(66)
DeepSeek V3$0.400/M
DeepSeek V3 0324$0.270/M
DeepSeek V3.1$0.270/M
DeepSeek V3.1 Terminus$0.270/M
DeepSeek V3.2$0.269/M
DeepSeek V3.2 Exp$0.270/M
ERNIE 4.5 21B A3B$0.070/M
ERNIE 4.5 21B A3B Thinking$0.070/M
ERNIE 4.5 300B A47B$0.280/M
ERNIE 4.5 VL 28B A3B$0.140/M
ERNIE 4.5 VL 424B A47B$0.420/M
Gemma 3 27B$0.119/M
GLM 4.5V$0.600/M
GLM 4.6$0.550/M
GLM 4.6V$0.300/M
GLM 5$1.00/M
GLM-4.7-Flash$0.070/M
GPT-OSS-120b$0.050/M
Hermes 2 Pro - Llama-3 8B$0.140/M
KAT-Coder-Pro V1$0.207/M
Kimi K2 0711$0.570/M
Kimi K2 0905 (exacto)$0.600/M
Kimi K2.5$0.570/M
Llama 3 70B Instruct$0.510/M
Llama 3 8B Instruct$0.040/M
Llama 3 8B Lunaris$0.050/M
Llama 3 Euryale 70B v2.1$1.48/M
Llama 3.1 70B Instruct$0.340/M
Llama 3.1 Euryale 70B v2.2$1.48/M
Llama 3.2 11B Vision Instruct$0.060/M
Llama 3.2 1B Instruct$0.020/M
Llama 3.2 3B Instruct$0.030/M
Llama 4 Maverick$0.270/M
Llama 4 Scout$0.180/M
MiMo-V2-Flash$0.100/M
MiniMax M1$0.440/M
MiniMax M2$0.300/M
MiniMax M2.7$0.300/M
Mistral 7B Instruct$0.059/M
Mistral Nemo$0.040/M
MythoMax 13B$0.090/M
Nous Hermes Llama 2 13B$0.170/M
OpenChat 7B$0.060/M
OpenHermes 2.5 Mistral 7B$0.170/M
Qwen2 VL 72B Instruct$0.450/M
Qwen2.5 72B Instruct$0.380/M
Qwen2.5 VL 72B Instruct$0.800/M
Qwen3 235B A22B Instruct 2507$0.090/M
Qwen3 235B A22B Thinking 2507$0.300/M
Qwen3 30B A3B$0.090/M
Qwen3 Coder Next$0.200/M
Qwen3 Next 80B A3B Instruct$0.150/M
Qwen3 VL 235B A22B Instruct$0.300/M
Qwen3 VL 235B A22B Thinking$0.980/M
Qwen3 VL 30B A3B Instruct$0.200/M
Qwen3 VL 30B A3B Thinking$0.200/M
Qwen3 VL 8B Instruct$0.080/M
Qwen3.5-122B-A10B$0.400/M
Qwen3.5-27B$0.300/M
R1$0.700/M
R1 Distill Llama 70B$0.800/M
R1 Distill Llama 8B$0.040/M
R1 Distill Qwen 14B$0.150/M
R1 Distill Qwen 32B$0.300/M
sophosympatheia/midnight-rose-70b$0.800/M
WizardLM-2 8x22B$0.620/M

Full Provider Pricing

Nebius AI
Nebius AI Full Pricing
View all 24 models with detailed pricing

Frequently Asked Questions

Novita AI is cheaper on 6 out of 16 shared models. Nebius AI is cheaper on 5 models. 5 models have the same price.
Nebius AI and Novita AI share 16 models. Nebius AI has 8 exclusive models, while Novita AI has 66 exclusive models.
Novita AI offers 82 models compared to Nebius AI's 24. However, model count alone doesn't determine the better provider — consider pricing, latency, and which specific models you need.

Built by @aellman

Archive
Follow us:
Advertise | Terms of Service | Privacy Policy

2026 68 Ventures, LLC. All rights reserved.