# Endpoints

We provide different endpoints with different price/performance tradeoffs. Our endpoints depend on internal models. Some of them are open-weight, which allow users to deploy them on their own, on arbitrary infrastructure. See Self-deployment for details.

### Generative endpoints[​](https://docs.mistral.ai/platform/endpoints/#generative-endpoints) <a href="#generative-endpoints" id="generative-endpoints"></a>

All our generative endpoints can reason on contexts up to 32k tokens and follow fine-grained instructions.&#x20;

We only provide chat access through our API. Users can access underlying base models for endpoints relying on open-weight models.

#### Tiny[​](https://docs.mistral.ai/platform/endpoints/#tiny) <a href="#tiny" id="tiny"></a>

This generative endpoint is best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.

Currently powered by Mistral-7B-v0.2, a better fine-tuning of the initial Mistral-7B released, inspired by the fantastic work of the community.

API name: `nido-tiny`

#### Small[​](https://docs.mistral.ai/platform/endpoints/#small) <a href="#small" id="small"></a>

Higher reasoning capabilities and more capabilities.

The endpoint supports English, French, German, Italian, and Spanish and can produce and reason about code.

Currently powered Mixtral-8X7B-v0.1, a sparse mixture of experts model with 12B active parameters.

API name: `nido-small`

#### Medium[​](https://docs.mistral.ai/platform/endpoints/#medium) <a href="#medium" id="medium"></a>

This endpoint currently relies on an internal prototype model.

API name: `nido-medium`

### Embedding models[​](https://docs.mistral.ai/platform/endpoints/#embedding-models) <a href="#embedding-models" id="embedding-models"></a>

Embedding models enable retrieval and retrieval-augmented generation applications.

Our endpoint outputs vectors in `1024` dimensions. It achieves a retrieval score of 55.26 on MTEB.

API name: `nido-embed`