Listings
All listings: Nebius AI Studio
Every listing for the models on page 4 of 4 of Nebius AI Studio, including each model's other versions and routes. Back to Nebius AI Studio
Sold by Nebius AI Studio
11 listings on this page sold by Nebius AI Studio.
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
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|
Nemotron 3 Nano Omni πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.06 | $0.24 | 262K | βNot enough data yet |
Cosmos3-Super-Reasoner πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.10 | $0.30 | 262K | βNot enough data yet |
nim/nvidia/llama-3.3-nemotron-super-49b-v1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.10 | $0.40 | 131K | βNot enough data yet |
Hermes 4 70B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.13 | $0.40 | 131K | 54.0Good value (54.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Beam 1.0 501B A23B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.25cache read $0.05 | $1.00 | 1M | βNot enough data yet |
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.60 | $1.80 | 128K | βNot enough data yet |
minicpm-v-4-5 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.658cache read $0.13 | $1.11 | 32K | βNot enough data yet |
Nousresearch Hermes 3 Llama 3.1 405b πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $1.00 | $3.00 | 128K | βNot enough data yet |
Flux Dev π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
Flux Schnell π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
Stable Diffusion XL π¬π§Maker headquartered in GB, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
Run by Nebius AI Studio
8 listings on this page where Nebius AI Studio runs the model. Another provider sells these listings.
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
| Model | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|---|
Hermes 4 70B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.13 | $0.40 | 131K | 54.0Good value (54.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | |
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.60 | $1.80 | 131K | βNot enough data yet | |
Beam 1.0 501B A23B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.2625cache read $0.0525 | $1.05 | βNot published by the provider | βNot enough data yet | |
Hermes High πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. RouterThis is a router, not a fixed model. The provider chooses which model answers, and that choice can change. | βNot enough data yet | βNot enough data yet | $1.47cache read $0.273 | $4.62 | βNot published by the provider | βNot enough data yet | |
Hermes Low πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. RouterThis is a router, not a fixed model. The provider chooses which model answers, and that choice can change. | βNot enough data yet | βNot enough data yet | $1.47cache read $0.273 | $4.62 | βNot published by the provider | βNot enough data yet | |
Hermes Medium πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. RouterThis is a router, not a fixed model. The provider chooses which model answers, and that choice can change. | βNot enough data yet | βNot enough data yet | $1.47cache read $0.273 | $4.62 | βNot published by the provider | βNot enough data yet | |
Nemotron 3 Ultra 550B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $1.00 | $3.00 | βNot published by the provider | βNot enough data yet | |
Nemotron Nano 12b V2 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.07 | $0.20 | 131K | βNot enough data yet |