> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.vapi.ai/providers/model/overview/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server. # Model providers > Reference of every large language model provider Vapi supports, including provider IDs and where to configure each one. This page lists the large language model (LLM) providers Vapi supports, with each provider's ID and dedicated documentation. The model is the LLM that generates your voice agent's responses. You select one by setting `model.provider` and `model.model` on an assistant. See [Create Assistant](/api-reference/assistants/create) in the API reference. ## Quick reference The provider string is the exact value you pass in `model.provider`. | Provider | Provider string | | ------------------------------------------------------------------------ | ------------------- | | [Anthropic](/providers/model/anthropic#language-model) | `anthropic` | | [Anthropic (Bedrock)](/providers/model/anthropic-bedrock#language-model) | `anthropic-bedrock` | | [Anyscale](/providers/model/anyscale#language-model) | `anyscale` | | [Azure OpenAI](/providers/model/azure-openai#language-model) | `azure-openai` | | [Cerebras](/providers/model/cerebras#language-model) | `cerebras` | | [Custom LLM](/customization/custom-llm/using-your-server) | `custom-llm` | | [DeepInfra](/providers/model/deepinfra#language-model) | `deepinfra` | | [DeepSeek](/providers/model/deepseek#language-model) | `deep-seek` | | [Google](/providers/model/gemini#language-model) | `google` | | [Groq](/providers/model/groq#language-model) | `groq` | | [Inflection AI](/providers/model/inflection-ai#language-model) | `inflection-ai` | | [MiniMax](/providers/model/minimax#language-model) | `minimax` | | [Mistral](/providers/model/mistral#language-model) | `mistral` | | [OpenAI](/providers/model/openai#language-model) | `openai` | | [OpenRouter](/providers/model/openrouter#language-model) | `openrouter` | | [Perplexity](/providers/model/perplexity#language-model) | `perplexity-ai` | | [The Grid](/customization/custom-llm/thegrid) | `custom-llm` | | [Together AI](/providers/model/togetherai#language-model) | `together-ai` | | [xAI](/providers/model/xai#language-model) | `xai` | > **Note** > > The **Assistant → Model** dropdown in the [Vapi Dashboard](https://dashboard.vapi.ai) is the most current list of selectable models. ## Related #### [Create an assistant](/api-reference/assistants/create) Set `model.provider` and `model.model` in the API. #### [Provider keys](/customization/provider-keys) Bring your own API keys under the dashboard Integrations tab. > Look up the LLM providers Vapi supports and their IDs ## Docs - [Anthropic](https://docs.vapi.ai/providers/model/anthropic.md): Connect Anthropic to Vapi to use Claude models as your voice agent's language model. Covers the supported Claude models and how to use them in the API. - [Anthropic Bedrock](https://docs.vapi.ai/providers/model/anthropic-bedrock.md): Connect AWS Bedrock credentials to Vapi and use Anthropic Claude models with your AWS account, regions, rate limits, and data controls. - [Anyscale](https://docs.vapi.ai/providers/model/anyscale.md): Connect an Anyscale account to Vapi and configure an assistant with the exact model ID available through your Anyscale account. - [Azure OpenAI](https://docs.vapi.ai/providers/model/azure-openai.md): Connect an Azure OpenAI resource to Vapi. Configure credentials, deployment names, supported models, regions, and endpoints. - [Cerebras](https://docs.vapi.ai/providers/model/cerebras.md): Connect a Cerebras API key to Vapi and configure an assistant with an exact model ID from your Cerebras account. - [DeepInfra](https://docs.vapi.ai/providers/model/deepinfra.md): Connect a DeepInfra account to Vapi and configure an assistant with an exact model ID from DeepInfra's current model catalog. - [DeepSeek](https://docs.vapi.ai/providers/model/deepseek.md): Connect a DeepSeek API key to Vapi and configure an assistant with a supported DeepSeek model. - [Google](https://docs.vapi.ai/providers/model/gemini.md): Configure Google Gemini as your Vapi assistant's language model and choose from the models Vapi supports. - [Groq](https://docs.vapi.ai/providers/model/groq.md): Connect Groq to Vapi, choose a supported model, and configure it as your assistant's language model. - [Inflection AI](https://docs.vapi.ai/providers/model/inflection-ai.md): Connect an Inflection AI API key to Vapi and configure an assistant with a supported Inflection AI model. - [MiniMax](https://docs.vapi.ai/providers/model/minimax.md): Configure MiniMax as your Vapi assistant's language model and choose from the models Vapi supports. - [Mistral](https://docs.vapi.ai/providers/model/mistral.md): Connect Mistral to Vapi to use Mistral Large and Mistral Small as your voice agent's language model. Configure it in the dashboard. - [OpenAI](https://docs.vapi.ai/providers/model/openai.md): Configure OpenAI as your Vapi assistant's language model and choose from the GPT models Vapi supports. - [OpenRouter](https://docs.vapi.ai/providers/model/openrouter.md): Connect an OpenRouter account to Vapi and configure an assistant with an exact model ID from OpenRouter's current model catalog. - [Perplexity](https://docs.vapi.ai/providers/model/perplexity.md): Connect a Perplexity account to Vapi and configure an assistant with an exact model ID supported by the Perplexity Sonar API. - [The Grid](https://docs.vapi.ai/customization/custom-llm/thegrid.md): Wire The Grid, an OpenAI-compatible inference marketplace, into Vapi with the custom-llm provider and Custom Credentials. - [Together AI](https://docs.vapi.ai/providers/model/togetherai.md): Connect a Together AI account to Vapi and configure an assistant with an exact model ID from Together AI's current serverless catalog. - [xAI](https://docs.vapi.ai/providers/model/xai.md): Configure xAI as your Vapi assistant's language model and choose from the Grok models Vapi supports.