> ## Documentation Index
> Fetch the complete documentation index at: https://www.narev.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Nebius model pricing

> Browse Nebius model prices.

## Models and pricing

| Model ID | Input / 1M tokens | Output / 1M tokens | Cache read / 1M tokens | Cache write / 1M tokens |
| - | - | - | - | - |
| [deepseek-ai/DeepSeek-V4-Flash-0731](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=deepseek-ai%2FDeepSeek-V4-Flash-0731) | \$0.14 | \$0.28 | \$0.01 | — |
| [deepseek-ai/DeepSeek-V4-Pro](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=deepseek-ai%2FDeepSeek-V4-Pro) | \$1.75 | \$3.5 | \$1.75 | — |
| [deepseek-ai/DeepSeek-V4-Pro-0813](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=deepseek-ai%2FDeepSeek-V4-Pro-0813) | \$1.32 | \$3.96 | \$0.04 | — |
| [deepseek-ai/DeepSeek-V4.1-Flash](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=deepseek-ai%2FDeepSeek-V4.1-Flash) | \$0.3 | \$1.2 | \$0.01 | — |
| [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=deepseek-ai%2FDeepSeek-V4.1-Flash-1017) | \$0.3 | \$1.2 | \$0.006 | — |
| [google/gemma-3-27b-it](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=google%2Fgemma-3-27b-it) | \$0.1 | \$0.3 | \$0.04 | — |
| [meta-models/muse-spark-open](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=meta-models%2Fmuse-spark-open) | \$1.25 | \$4.25 | \$0.15 | — |
| [MiniMaxAI/MiniMax-M3](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=MiniMaxAI%2FMiniMax-M3) | \$0.3 | \$1.2 | \$0.06 | — |
| [MiniMaxAI/MiniMax-M3.1-Flash](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=MiniMaxAI%2FMiniMax-M3.1-Flash) | \$0.15 | \$0.6 | \$0.015 | — |
| [moonshotai/Kimi-K2.7-Code](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=moonshotai%2FKimi-K2.7-Code) | \$0.95 | \$4 | \$0.15 | — |
| [moonshotai/Kimi-K3](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=moonshotai%2FKimi-K3) | \$3 | \$15 | \$0.3 | — |
| [NousResearch/Hermes-4-405B](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=NousResearch%2FHermes-4-405B) | \$1 | \$3 | \$0.2 | — |
| [nvidia/Nemotron-3\_5-Lightning](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=nvidia%2FNemotron-3_5-Lightning) | \$0.06 | \$0.24 | \$0.06 | — |
| [nvidia/nemotron-3-super-120b-a12b](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=nvidia%2Fnemotron-3-super-120b-a12b) | \$0.3 | \$0.9 | \$0.06 | — |
| [nvidia/Nemotron-3-Ultra-550b-a55b](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=nvidia%2FNemotron-3-Ultra-550b-a55b) | \$1 | \$3 | \$0.12 | — |
| [nvidia/Nemotron-3.5-Super-VL](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=nvidia%2FNemotron-3.5-Super-VL) | \$0.3 | \$0.9 | \$0.06 | — |
| [openai/gpt-oss-120b](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=openai%2Fgpt-oss-120b) | \$0.15 | \$0.6 | \$0.1 | — |
| [Qwen/Qwen3-235B-A22B-Instruct-2507](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=Qwen%2FQwen3-235B-A22B-Instruct-2507) | \$0.2 | \$0.6 | \$0.2 | — |
| [Qwen/Qwen3-30B-A3B-Instruct-2507](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=Qwen%2FQwen3-30B-A3B-Instruct-2507) | \$0.1 | \$0.3 | \$0.1 | — |
| [Qwen/Qwen3.5-397B-A17B](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=Qwen%2FQwen3.5-397B-A17B) | \$0.6 | \$3.6 | \$0.12 | — |
| [Qwen/Qwen3.8-27B](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=Qwen%2FQwen3.8-27B) | \$0.45 | \$3 | \$0.1 | — |
| [reflection/beam](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=reflection%2Fbeam) | \$0.25 | \$1 | \$0.05 | — |
| [zai-org/GLM-5.2](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=zai-org%2FGLM-5.2) | \$1.4 | \$4.4 | \$0.14 | — |
| [zai-org/GLM-5.3](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=zai-org%2FGLM-5.3) | \$1.4 | \$4.4 | \$0.26 | — |
| [zai-org/GLM-5.3-Flash](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=zai-org%2FGLM-5.3-Flash) | \$0.15 | \$0.5 | \$0.03 | — |

> **Enterprise pricing**
>
> | Model ID | Availability |
> | - | - |
> | [moonshotai/Kimi-K2.6](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=moonshotai%2FKimi-K2.6) | Pricing for this model is available on enterprise plans only. |
> | [nvidia/Cosmos3-Super-Reasoner](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=nvidia%2FCosmos3-Super-Reasoner) | Pricing for this model is available on enterprise plans only. |
> | [openbmb/MiniCPM-V-4\_5](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=openbmb%2FMiniCPM-V-4_5) | Pricing for this model is available on enterprise plans only. |
> | [Qwen/Qwen3-Embedding-8B](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=Qwen%2FQwen3-Embedding-8B) | Pricing for this model is available on enterprise plans only. |
> | [zai-org/GLM-5.1](https://api.narev.ai/v1/prices?provider_id=nebius\&model_id=zai-org%2FGLM-5.1) | Pricing for this model is available on enterprise plans only. |

```bash Request theme={null}
curl --request GET \
  --url 'https://api.narev.ai/v1/prices?provider_id=nebius&model_id=deepseek-ai%2FDeepSeek-V4-Flash-0731'
```

```json Price record (snapshot) theme={null}
{
  "model_id": "deepseek-ai/DeepSeek-V4-Flash-0731",
  "provider_id": "nebius",
  "pricing": {
    "prompt": 1.4e-7,
    "completion": 2.8e-7,
    "discount": 0,
    "request": 0,
    "web_search": 0,
    "input_cache_read": 1e-8,
    "input_cache_write": 0,
    "image": 0,
    "image_output": 0,
    "audio": 0,
    "audio_output": 0,
    "input_audio_cache": 0,
    "internal_reasoning": 0
  }
}
```

## Provider details

| Property | Value |
| - | - |
| Headquarters | NL |

[Privacy policy](https://docs.nebius.com/legal/studio/privacy/) · [Terms of service](https://docs.nebius.com/legal/studio/terms-of-use/)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.