# Vanta

> Vanta is an AI chat client for iPhone and iPad. Connect to your own server, run supported models on-device, or use cloud providers with your own API keys.

## Official pages

- [Vanta](https://vantaclient.app/): Product overview.
- [Vanta documentation](https://vantaclient.app/docs/): Practical guides for using Vanta with LM Studio, Ollama, vLLM, on-device models, cloud APIs, MCP tools and PDFs.
- [Get started with Vanta](https://vantaclient.app/docs/getting-started/): Choose a server, on-device model or cloud provider, save a model preset, and send your first message in Vanta on iPhone or iPad.
- [Use LM Studio on your iPhone or iPad](https://vantaclient.app/docs/lm-studio/): Connect Vanta to LM Studio over your local network, enter the correct API base URL, and check the model and connection.
- [Use Ollama on your iPhone or iPad](https://vantaclient.app/docs/ollama/): Connect Vanta to an Ollama server using its OpenAI-compatible API, including LAN binding, model identifiers and connection checks.
- [Connect your iPhone or iPad to vLLM](https://vantaclient.app/docs/vllm/): Use Vanta with a vLLM OpenAI-compatible server, including its base URL, model identifier, optional API key and security limits.
- [Run on-device AI on your iPhone or iPad](https://vantaclient.app/docs/on-device/): Use supported GGUF and MLX models directly on your device, or choose available Apple Intelligence, with practical memory and offline limits.
- [Connect a cloud API to Vanta](https://vantaclient.app/docs/cloud-providers/): Use OpenRouter or a custom OpenAI-compatible provider with your own API key, save a model preset, and understand API billing and data flow.
- [Connect MCP tools to Vanta](https://vantaclient.app/docs/mcp/): Add a remote MCP server over HTTPS, choose Streamable HTTP or SSE, configure authentication, and use tools with a compatible model.
- [Chat with PDFs and images](https://vantaclient.app/docs/files-and-pdfs/): Attach PDFs in Vanta, understand text extraction and retrieval, choose a vision model for images, and check file and privacy limits.
- [Fix a Vanta connection or model problem](https://vantaclient.app/docs/troubleshooting/): Troubleshoot unreachable servers, API errors, missing models, local memory pressure, Apple Intelligence availability, tools and PDF attachments.
- [Vanta updates](https://vantaclient.app/changelog/): Confirmed Vanta release notes, with App Store availability distinguished from the app version in development.
- [Which models work with Vanta?](https://vantaclient.app/compatibility/): Compare Vanta's supported server APIs, GGUF, MLX and Apple Intelligence capabilities, with honest device and performance limitations.
- [What you can do with Vanta](https://vantaclient.app/features/): Use self-hosted, on-device and cloud AI models on iPhone and iPad, with documents, memory, group conversations and compatible tools.
- [Local AI on iPhone and iPad](https://vantaclient.app/local-ai/): Choose between on-device AI and a self-hosted server for your iPhone or iPad. Understand offline use, memory, PDFs, images, tools and privacy.
- [Buy Vanta once](https://vantaclient.app/pricing/): Vanta is a paid iPhone and iPad app with no Vanta subscription. Learn what the purchase covers and which optional services cost extra.
- [Privacy and where your data goes](https://vantaclient.app/privacy/): See how Vanta handles conversations, files, API keys, memory, speech and tools across on-device, self-hosted and cloud workflows.
- [Get help with Vanta](https://vantaclient.app/support/): Find setup guides, troubleshoot Vanta, and contact the developer with useful details about your device, model or connection.

## Machine-readable content

- [Full documentation](https://vantaclient.app/llms-full.txt): All Markdown page content, generated from the same sources as the HTML.

Each page has a Markdown representation at the same path with .md instead of its trailing slash (for example /docs/ollama.md). Canonical HTML is authoritative. Product facts checked 2026-10-02.