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

# Serverless models

> Explore the models currently available for serverless inference, ready to use instantly for chat and embeddings.

> [!WARNING]
>
> **Upcoming model changes**
>
> On 11 December 2026, two models leave serverless inference and one moves to dedicated models. To keep your application running, switch to an alternative model before then. [See the affected models](#upcoming-model-changes).

Our model list is available in the Nscale Console under **AI Services → Models**, or on [our website ](https://www.nscale.com/product/serverless).

You can also programmatically access model information including pricing and context length through the [/v1/models API endpoint](https://docs.nscale.com/api-reference/models/list-models.md).

> [!TIP]
>
> Try out some of the examples from the Use Cases documentation:
>
> * [Chat](https://docs.nscale.com/docs/use-cases/chat.md)

## Available models

These models are available for serverless inference. Prices are in USD per 1 million tokens.

| Model | Author | Input price | Output price |
| - | - | - | - |
| GLM 5.3 | Z.ai | \$1.40 | \$4.40 |
| Mistral-Large-3-675B-Instruct-2512-NVFP4 | Mistral AI | \$1.00 | \$2.50 |
| Qwen3.8-27B | Qwen | \$0.20 | \$2.50 |
| Qwen3.8-Flash-Next-FP8 | Qwen | \$0.15 | \$0.47 |

`Qwen3-Embedding-8B` is also available for embeddings.

> [!NOTE]
>
> We don't currently offer image generation models on serverless inference. We're looking at newer image models to support.

Need a model that isn't in our serverless catalog? See [dedicated models](https://docs.nscale.com/docs/dedicated-models/deploy-a-model.md) or [contact support](mailto:helpdesk@nscale.com).

## Upcoming model changes

These changes take effect on 11 December 2026.

| Model | Change | What to do |
| - | - | - |
| Qwen3.8-Flash-Next-FP8 | Retired from serverless | Switch to another model in the [available models](#available-models) table. |
| Qwen3-Embedding-8B | Retired from serverless | No other embedding model is available on serverless. [Contact support](mailto:helpdesk@nscale.com) to discuss options. |
| Mistral-Large-3-675B-Instruct-2512-NVFP4 | Moves to dedicated models | Run it as a [dedicated model](https://docs.nscale.com/docs/dedicated-models/deploy-a-model.md), or switch to another model in the [available models](#available-models) table. |

We're working on bringing new models to serverless inference, and we'll update this page as they become available. For help choosing a replacement in the meantime, [contact support](mailto:helpdesk@nscale.com).

> [card] Looking for a model?
>
> We're always reviewing new models to add to our serverless inference platform. Whether you're a researcher, a developer, or just someone with a great idea,
> we'd love to hear from you. Let us know what you'd like to see available next.
