> For the complete documentation index, see [llms.txt](https://dnotifier.gitbook.io/product-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dnotifier.gitbook.io/product-docs/integrations/llm-providers.md).

# LLM providers

Pass `provider` and `model` on `sendAI`, or set them once on an agent. Save the provider key in **Projects → AI Studio → Providers** before calling it.

```js
await notifier.sendAI({
  senderId: "user-123",
  provider: "open_ai",
  model: "gpt-4o",
  message: { text: "Summarize this refund policy in one sentence." },
});
```

| Provider      | `provider`      | Models                                                          |
| ------------- | --------------- | --------------------------------------------------------------- |
| OpenAI        | `open_ai`       | `gpt-4o`, `gpt-4o-mini`, `o3-mini`                              |
| Anthropic     | `anthropic`     | `claude-sonnet-4-20250514`, `claude-haiku-4-5-20251001`         |
| Google Gemini | `google_gemini` | `gemini-2.0-flash`                                              |
| Perplexity    | `perplexity`    | `sonar`, `sonar-pro`                                            |
| Azure AI      | `azure_ai`      | Your Azure deployment name, for example `gpt-4o`                |
| AWS Bedrock   | `aws_bedrock`   | `amazon.nova-lite-v1:0`                                         |
| Hugging Face  | `hugging_face`  | `meta-llama/Meta-Llama-3-8B-Instruct`                           |
| Ollama        | `ollama`        | The tag from `ollama list`, for example `llama3.2` or `mistral` |

Use the model id shown for that provider in the dashboard. Azure uses the deployment name. Ollama and Hugging Face use the model you enabled on that connection.

## Setup guides

| Provider      | Guide                                                                                                               |
| ------------- | ------------------------------------------------------------------------------------------------------------------- |
| OpenAI        | [OpenAI integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/open-ai-integration.md)              |
| Anthropic     | [Anthropic integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/anthropic-integration.md)         |
| Google Gemini | [Google Gemini integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/google-gemini-integration.md) |
| Perplexity    | [Perplexity integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/perplexity-integration.md)       |
| Azure AI      | [Azure AI integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/azure-ai-integration.md)           |
| AWS Bedrock   | [AWS Bedrock integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/aws-bedrock-integration.md)     |
| Hugging Face  | [Hugging Face integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/hugging-face-integration.md)   |
| Ollama        | [Ollama local integration](https://dnotifier.gitbook.io/product-docs/ai/multi-models/ollama-local-integration.md)   |

→ [Send a prompt](https://dnotifier.gitbook.io/product-docs/ai/send-prompt.md) · [Define an agent](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/define-agent.md)
