--- title: Models | Letta Docs description: Use any model with Letta Agent --- Letta Agent is **model-agnostic**. Agents can use Claude, GPT, Gemini, or other supported models. Users can change an agent’s underlying model at any time, even mid-conversation. We recommend first-time users use a large frontier model (for example from OpenAI or Anthropic) to learn how Letta Agent works, since weaker models can cause the agent to behave in unexpected ways. See [leaderboard.letta.com](https://leaderboard.letta.com) for benchmarks comparing model performance. ## Switching models Use the `/model` command to switch models during a session. This opens a model selector that allows you to swap models and choose their reasoning settings (if applicable). ## Model toolsets Different models are trained to work best with different tools. For example, GPT models from OpenAI are trained to use a patch-based editing tool, while Claude models work better with string-based edit tools. Letta Agent handles this automatically with dynamic **toolsets** - tool configurations optimized for each model family. When you switch models with `/model`, Letta Code automatically switches to the optimal toolset. If you want to force a specific toolset, use the `/toolset` command. Agents on [Constellation](/letta-agent/constellation/index.md) come pre-configured with web search and web fetch tools. If you’re running agents using the local backend, you can set up your own web search utilities using custom [skills](/letta-agent/skills/index.md). ## Connecting model providers Letta Agent supports a wide variety of LLM providers, as well as coding plans such as ChatGPT and zAI. To connect additional providers, use `/connect` in the CLI. To see your available models, use `/model`. Local providers are configured on your machine. If you’re logged into [Constellation](/letta-agent/constellation/index.md), `/connect` also lets you configure providers for agents hosted in Constellation. Constellation providers are managed through Constellation’s LLM gateway. Constellation supports a smaller provider set than local mode; local inference providers like LM Studio, Ollama, and llama.cpp are available only in local mode. You can pay for LLM gateway usage with pay-as-you-go credits from the [usage page](https://app.letta.com/settings/organization/usage). | Provider | Local support | Constellation | | ------------------------------------------------------------------------------------------------ | ---------------------- | ---------------------- | | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock) | AWS credentials | AWS credentials | | [Anthropic API](https://platform.claude.com/settings/keys) | API key | API key | | [Claude Pro/Max](https://www.anthropic.com/claude-code) | Subscription | — | | [Azure OpenAI Responses](https://azure.microsoft.com/en-us/products/ai-foundry/models/openai) | API key | — | | [Cerebras](https://inference-docs.cerebras.ai) | API key | — | | [ChatGPT Plus/Pro Codex](https://developers.openai.com/codex/pricing/) | Subscription | Subscription | | [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/) | API key | — | | [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) | API key | — | | [DeepSeek](https://platform.deepseek.com/api_keys) | API key | — | | [Fireworks](https://fireworks.ai/) | API key | — | | [GitHub Copilot](https://github.com/features/copilot) | Subscription | — | | [Google Gemini](https://aistudio.google.com/app/api-keys) | API key | API key | | [Google Vertex AI](https://cloud.google.com/vertex-ai) | API key | — | | [Groq](https://console.groq.com/keys) | API key | — | | [Hugging Face](https://huggingface.co/settings/tokens) | API key | — | | [Kimi Code](https://platform.moonshot.ai/) | API key | API key | | [llama.cpp](https://github.com/ggml-org/llama.cpp) | Local endpoint | — | | [LM Studio](https://lmstudio.ai/) | Local endpoint | — | | [MiniMax](https://platform.minimax.io/docs/guides/quickstart-preparation) | API key or coding plan | API key or coding plan | | [MiniMax (China)](https://platform.minimaxi.com/) | API key | — | | [Mistral](https://console.mistral.ai/api-keys/) | API key | — | | [Moonshot AI](https://platform.moonshot.ai/) | API key | API key | | [Moonshot AI (China)](https://platform.moonshot.cn/) | API key | — | | [Ollama](https://ollama.com/) | Local endpoint | — | | [Ollama Cloud](https://ollama.com/) | API key | — | | [OpenAI API](https://platform.openai.com/settings/organization/api-keys) | API key | API key | | [OpenCode Go](https://opencode.ai/) | API key | — | | [OpenCode Zen](https://opencode.ai/) | API key | — | | [OpenRouter](https://openrouter.ai/docs/api-reference/authentication) | API key | API key | | [Together AI](https://docs.together.ai/docs/quickstart) | API key | — | | [Vercel AI Gateway](https://vercel.com/docs/ai-gateway) | API key | — | | [xAI](https://console.x.ai/) | API key | — | | [Xiaomi MiMo](https://github.com/XiaomiMiMo/MiMo) | API key | — | | Xiaomi MiMo Token Plan (Amsterdam) | Token plan | — | | Xiaomi MiMo Token Plan (China) | Token plan | — | | Xiaomi MiMo Token Plan (Singapore) | Token plan | — | | [zAI API](https://docs.z.ai/guides/overview/quick-start) | API key | API key | | [zAI Coding Plan](https://z.ai/subscribe) | Coding plan | Coding plan |