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.
Start for free
Begin with $1 in free credits to explore our models through the Playground or API. Start building in minutes.
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.
Text to text
Prices shown are per 1 million tokens.
Batch inference is automatically billed at 50% of the base real-time model price, rounded up to the nearest cent. Example: If a model’s base price is $0.13 input and $0.40 output, batch inference is $0.07 input and $0.20 output respectively.
Model
Flavor
Input
Output
Meta/Llama-3.3-70B-Instruct
fast
$0.25
$0.75
base
$0.13
$0.40
Meta/Llama-3.1-8B-Instruct
fast
$0.03
$0.09
base
$0.02
$0.06
Meta/Llama-3.1-70B-Instruct
fast
–
–
base
$0.13
$0.40
Meta/Llama-3.1-405B-Instruct
fast
–
–
base
$1.00
$3.00
NousResearch/Hermes-3-Llama-405B
fast
–
–
base
$1.00
$3.00
Meta/Llama-Guard-3
fast
–
–
base
$0.02
$0.06
MistralAI/Mistral-Nemo-Instruct-2407
fast
–
–
base
$0.04
$0.12
deepseek-ai/DeepSeek-R1
fast
–
–
base
$0.80
$2.4
deepseek-ai/DeepSeek-R1-0528
fast
–
–
base
$0.80
$2.4
deepseek-ai/DeepSeek-V3
fast
–
–
base
$0.50
$1.5
deepseek-ai/DeepSeek-V3-0324
fast
$2
$6
base
$0.50
$1.5
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
fast
–
–
base
$0.25
$0.75
microsoft/phi-4
fast
–
–
base
$0.10
$0.30
Qwen/Qwen3-4B-fast
fast
$0.08
$0.24
base
–
–
Qwen/Qwen3-14B
fast
–
–
base
$0.08
$0.24
Qwen/Qwen3-32B
fast
$0.2
$0.6
base
$0.1
$0.3
Qwen/Qwen3-30B-A3B
fast
$0.3
$0.9
base
$0.1
$0.3
Qwen/Qwen3-235B-A22B
fast
–
–
base
$0.2
$0.6
QwQ-32B
fast
$0.50
$1.50
base
$0.15
$0.45
Qwen2.5-Coder-7B
fast
$0.03
$0.09
base
$0.01
$0.03
Qwen2.5-32B-Instruct
fast
$0.13
$0.40
base
$0.06
$0.20
Qwen2.5-72B-Instruct
fast
$0.25
$0.75
base
$0.13
$0.40
Qwen2-VL-72B-Instruct
fast
–
–
base
$0.13
$0.40
Nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
fast
–
–
base
$0.60
$1.80
aaditya/Llama3-OpenBioLLM-70B
fast
–
–
base
$0.13
$0.40
m42-health/Llama3-Med42-8B
fast
–
–
base
$0.02
$0.06
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.