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

# LLM Providers

> The models Raily uses for its agentic layer, answers, and embeddings

Raily works with the major model providers. They are used in three places:

* **Agentic layer** — analyzes a query and rewrites it for better retrieval. See [Agentic Layer](/concepts/agentic-layer).
* **Answers** — generates the response from the retrieved passages in chat.
* **Embeddings** — turns your content and queries into vectors. You choose the embedding provider per collection when you connect a [vector store](/integrations/vector-store/overview).

<CardGroup cols={3}>
  <Card title="OpenAI" icon="wand-magic-sparkles">
    GPT for answers and OpenAI embeddings
  </Card>

  <Card title="Anthropic" icon="comment">
    Claude for answers
  </Card>

  <Card title="Google" icon="google">
    Gemini for the agentic layer, answers, and embeddings
  </Card>

  <Card title="Vertex AI" icon="cloud">
    Google Vertex embeddings
  </Card>

  <Card title="AWS Bedrock" icon="aws">
    Bedrock embeddings
  </Card>

  <Card title="Sentence Transformers" icon="vector-square">
    Self-hosted open-source embeddings
  </Card>
</CardGroup>