Nebius AI Studio models and pricing
We track 23 models on Nebius AI Studio from 12 labs. The cheapest paid model is Qwen 3 Embedding 8B, at $0.01 per million input tokens and Free per million output tokens. Input prices range from $0.01 to $3 and output prices from $0.24 to $15 per million tokens. The largest context window is 1M tokens (Inkling 2 Small, Kimi K3.1 Pro Highspeed and 9 other models). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Nebius AI Studio
- Qwen 3 Embedding 8B$0.01 / Free
- Nemotron 3.5 Lightning 30B$0.06 / $0.24
- Gemma 3 27B IT$0.10 / $0.30
- Qwen3-30B-A3B-Instruct-2507$0.10 / $0.30
- GLM-5.3-Flash$0.15 / $0.50
Input / output per million tokens, paid models, by combined price.
Newest models on Nebius AI Studio
- Inkling 2 Small5 Nov 2026
- Kimi K3.1 Pro Highspeed23 Oct 2026
- MiniMax-M3.1-Flash19 Oct 2026
- DeepSeek V4.1 Flash 101717 Oct 2026
- NVIDIA Nemotron 3.5 Super VL15 Oct 2026
By the lab's release date.
All Nebius AI Studio models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Inkling 2 Small thinkingmachines/Inkling-2-Small | Thinkingmachines | $0.30 | $1 | 1M | models.dev |
| Kimi K3.1 Pro Highspeed moonshotai/Kimi-K3.1-Pro | Moonshot AI | $2 | $10 | 1M | models.dev |
| MiniMax-M3.1-Flash MiniMaxAI/MiniMax-M3.1-Flash | MiniMax | $0.15 | $0.60 | 1M | models.dev |
| DeepSeek V4.1 Flash 1017 deepseek-ai/DeepSeek-V4.1-Flash-1017 | DeepSeek | $0.30 | $1.20 | 1M | models.dev |
| NVIDIA Nemotron 3.5 Super VL nvidia/Nemotron-3.5-Super-VL | NVIDIA | $0.30 | $0.90 | 1M | models.dev |
| Muse Spark Open meta-models/muse-spark-open | Meta | $1.25 | $4.25 | 1M | models.dev |
| Beam 1.0 reflection/beam | Reflection | $0.25 | $1 | 1M | models.dev |
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | Zhipu AI (Z.ai) | $0.15 | $0.50 | 1M | models.dev |
| Qwen3.8 27B Qwen/Qwen3.8-27B | Alibaba (Qwen) | $0.45 | $3 | 262K | models.dev |
| GLM-5.3 zai-org/GLM-5.3 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek | $1.32 | $3.96 | 979K | models.dev |
| Nemotron 3.5 Lightning 30B nvidia/Nemotron-3_5-Lightning | NVIDIA | $0.06 | $0.24 | 1M | models.dev |
| Kimi K3 moonshotai/Kimi-K3 | Moonshot AI | $3 | $15 | 1M | models.dev |
| GLM-5.2 zai-org/GLM-5.2 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| Nemotron 3 Ultra nvidia/Nemotron-3-Ultra-550b-a55b | NVIDIA | $1 | $3 | 1M | models.dev |
| MiniMax-M3 MiniMaxAI/MiniMax-M3 | MiniMax | $0.30 | $1.20 | 1M | models.dev |
| NVIDIA Nemotron 3 Super 120B A12B nvidia/nemotron-3-super-120b-a12b | NVIDIA | $0.30 | $0.90 | 262K | models.dev |
| Hermes-4-405B NousResearch/Hermes-4-405B | Nousresearch | $1 | $3 | 131K | models.dev |
| gpt-oss-120b openai/gpt-oss-120b | OpenAI | $0.15 | $0.60 | 131K | models.dev |
| Qwen3-30B-A3B-Instruct-2507 Qwen/Qwen3-30B-A3B-Instruct-2507 | Alibaba (Qwen) | $0.10 | $0.30 | 262K | models.dev |
| Qwen3 235B A22B Instruct 2507 Qwen/Qwen3-235B-A22B-Instruct-2507 | Alibaba (Qwen) | $0.20 | $0.60 | 262K | models.dev |
| Qwen 3 Embedding 8B Qwen/Qwen3-Embedding-8B | Alibaba (Qwen) | $0.01 | Free | 41K | models.dev |
| Gemma 3 27B IT google/gemma-3-27b-it | Google DeepMind | $0.10 | $0.30 | 110K | models.dev |
Frequently asked questions
How much does Nebius AI Studio cost per million tokens?
Prices on Nebius AI Studio depend on the model. Across the 23 models we track, input costs $0.01 to $3 per million tokens and output costs $0.24 to $15 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on Nebius AI Studio?
Qwen 3 Embedding 8B from Alibaba (Qwen) is the cheapest paid model we track on Nebius AI Studio, at $0.01 per million input tokens and Free per million output tokens. Next are Nemotron 3.5 Lightning 30B ($0.06 / $0.24) and Gemma 3 27B IT ($0.10 / $0.30). Prices last verified 18 Nov 2026.
How many models does Nebius AI Studio offer?
We currently track 23 active models on Nebius AI Studio from 12 labs, led by Alibaba (Qwen) (4), NVIDIA (4), Zhipu AI (Z.ai) (3) and DeepSeek (2).
Which model on Nebius AI Studio has the largest context window?
Inkling 2 Small, Kimi K3.1 Pro Highspeed and 9 other models share the largest context window we track on Nebius AI Studio: 1,048,576 tokens (1M).