Skip to content

Nebius AI Studio

Pricing page

212 listings across 89 models

Page 2 of 4. The lists below split this page's listings into those sold by Nebius AI Studio, run by Nebius AI Studio, or sent to Nebius AI Studio by a marketplace.

Sold by Nebius AI Studio

15 listings on this page sold by Nebius AI Studio.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
MiniMax M3
$0.30cache read $0.06$1.201M
Nemotron 3.5 Super VLfp4
Not enough data yet$0.30cache read $0.06$0.901MNot measured
Nemotron 3 Ultranebius/nvidia/Nemotron-3-Ultra-550b-a55b
$1.00cache read $0.12$3.001M
MiniMax M2.5
$0.30$1.20197KNot measured
DeepSeek R1
$0.80$2.40128K
DeepSeek R1nebius/deepseek-ai/DeepSeek-R1-0528 · 0528
$0.80$2.40164K
$0.20cache read $0.05$0.60262KNot measured
Qwen3 Next 80B A3Bnebius/Qwen/Qwen3-Next-80B-A3B-Thinking · thinking
$0.15$1.20128KNot measuredNot measured
$0.20$0.60262KNot measured
Not enough data yet$1.00cache read $0.20$3.00131KNot measuredNot measured
GPT OSS 120Bfp4
$0.15cache read $0.10$0.60131K
Nemotron 3 Super 120B A12B
$0.30cache read $0.06$0.90262KNot enough data yetNot measuredNot measured
Not enough data yet$0.06cache read $0.03$0.241MNot measuredNot measured
QwQ 32B
$0.15$0.4533KNot measured
Qwen3 32B
$0.10$0.3041KNot measured

Run by Nebius AI Studio

36 listings on this page where Nebius AI Studio runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
MiniMax M3
 Llmgateway$0.30$1.20Not published by the provider
Nemotron 3.5 Super VLfp4 · GLB
 NanoGPTNot enough data yet$0.315cache read $0.063$0.945Not published by the providerNot measured
DeepSeek V3.2
 Llmgateway$0.30$0.45Not published by the providerNot measured
NVIDIA Nemotron 3.5 Super VL 120Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 · bf16
 Hugging Face$0.30$0.901MNot measuredNot measured
 Hugging Face$0.20$0.80262KNot measuredNot measured
Nemotron 3 Ultranebius/nvidia/Nemotron-3-Ultra-550b-a55b
 Eden AI$1.00$3.001M
 Hugging Face$0.60$2.50262K
MiniMax M2.5
 Llmgateway$0.30$1.20Not published by the providerNot measured
DeepSeek R1deepseek-ai/DeepSeek-R1-0528 · 0528
 Hugging Face$0.80$2.40164K
GLM 4.5
 Hugging Face$0.60$2.20131KNot measured
 Hugging Face$0.50$2.40131KNot measuredNot measured
 Cortecs AI——262KNot measured
Qwen3 CoderQwen/Qwen3-Coder-480B-A35B-Instruct
 Hugging Face$0.40$1.80262KNot measured
 Cortecs AINot enough data yet——128KNot measuredNot measured
GPT OSS 120B
 Cortecs AI——131K
GLM 4.5 Air
 Hugging Face$0.20$1.20131KNot measuredNot measured
Kimi K2moonshotai/Kimi-K2-Instruct
 Llmgateway$0.50$2.40Not published by the providerNot measured
Nemotron 3 Super 120B A12B
 Eden AI$0.30$0.90262KNot enough data yetNot measuredNot measured
INTELLECT-3PrimeIntellect/INTELLECT-3-FP8 · fp8
 Hugging FaceNot enough data yet$0.20$1.10131KNot measuredNot measured
 Hugging FaceNot enough data yet$0.10$0.30262KNot measuredNot measured
Qwen3 32B
 Hugging Face$0.10$0.3041KNot measured
Show all 36 listings

Showing 21 of 36: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works