Search
Contact salesAI Studio log inGPU Cloud log in

AI Studio pricing

Select from premium AI models with flexible pricing — choose between high-speed or cost-efficient endpoints to match your performance and budget requirements.

Get started with AI Studio

$100 welcome credit

Sign up today and receive $100* in free inference credits to try our product through the Playground, or to spend on your inference workloads through the API.

Playground

The Nebius AI Studio provides a model playground: a web interface to try out and compare different AI models available in Nebius AI Studio without writing any code.

Two flavors

Choose between fast and base flavors to suit your project needs. Fast flavor delivers quicker results for time-sensitive tasks, while base flavor offers economical processing for larger workloads.

Check out available models and prices

Prices shown are per 1 million tokens.

Model
Flavor
Input
Output
Meta/Llama-3.1-8B-Instruct
fast
$0.03
$0.09
base
$0.02
$0.06
Meta/Llama-3.1-70B-Instruct
fast
$0.25
$0.75
base
$0.13
$0.40
Meta/Llama-3.1-405B-Instruct
fast
-
-
base
$1.00
$3.00
Meta/Llama-Guard-3
fast
$0.03
$0.09
Soon
base
$0.02
$0.06
Soon
MistralAI/Mistral-Nemo-Instruct-2407
fast
$0.08
$0.24
base
$0.04
$0.12
MistralAI/Mixtral-8x22B-Instruct-v0.1
fast
$0.70
$2.10
base
$0.40
$1.20
MistralAI/Mixtral-8x7B-Instruct-v0.1
fast
$0.15
$0.45
base
$0.08
$0.24
MistralAI/Pixtral-12B-2409
fast
$0.03
$0.09
Soon
base
$0.02
$0.06
Soon
DeepSeekAI/DeepSeek-Coder-V2-Lite-Instruct-FP8
fast
$0.08
$0.24
base
$0.04
$0.12
Microsoft/Phi-3-mini-4k-instruct
fast
$0.13
$0.40
base
$0.04
$0.13
Microsoft-Phi-3-Medium-128k-instruct
fast
$0.15
$0.45
base
$0.10
$0.30
Qwen2.5-Coder-7B
fast
$0.03
$0.09
base
$0.01
$0.03
Qwen2.5-Coder-7B-Instruct
fast
$0.03
$0.09
base
$0.01
$0.03
Qwen2.5-72B-Instruct
fast
$0.25
$0.75
base
$0.13
$0.40
Qwen2-VL-7B-Instruct
fast
$0.03
$0.09
Soon
base
$0.02
$0.06
Soon
Qwen2-VL-72B-Instruct
fast
$0.25
$0.75
Soon
base
$0.13
$0.40
Soon
Google-Gemma-2-27B-it
fast
$0.17
$0.51
base
$0.10
$0.30
Google-Gemma-2-9B-it
fast
$0.03
$0.09
base
$0.02
$0.06
Ai2/OLMo-7B-Instruct-HF
fast
-
-
base
$0.08
$0.24
NVIDIA/Llama-3.1-Nemotron-70B-Instruct-HF
fast
$0.25
$0.75
base
$0.13
$0.40
aaditya/Llama3-OpenBioLLM-8B
fast
-
-
base
$0.02
$0.06
aaditya/Llama3-OpenBioLLM-70B
fast
-
-
base
$0.13
$0.40
llava-1.5-7B-HF
fast
$0.03
$0.09
Soon
base
$0.02
$0.06
Soon
llava-v1.5-13B
fast
$0.03
$0.09
Soon
base
$0.02
$0.06
Soon

Welcome to Nebius AI Studio

Nebius AI Studio is a new product from Nebius designed to help foundation model users and app builders simplify the process of creating applications using these models. Our first release, Inference Service, provides endpoints for the most popular AI models.

Start building now