By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models). You can configure a model to use [thinking mode](https://ai.google.dev/gemini-api/docs/thinking) (if it supports it) by adding a `mode` configuration to your model. This is useful for controlling reasoning token usage and response speed. If not specified, Gemini will automatically choose the thinking budget.

Here is an example of a custom Google AI model you could add to your Zed `settings.json`:

```json
{
  "language_models": {
    "google": {
      "available_models": [
        {
          "name": "gemini-2.5-flash-preview-05-20",
          "display_name": "Gemini 2.5 Flash (Thinking)",
          "max_tokens": 1000000,
          "mode": {
            "type": "thinking",
            "budget_tokens": 24000
          }
        }
      ]
    }
  }
}
```

Custom models will be listed in the model dropdown in the Agent Panel.

### LM Studio {#lmstudio}

> ✅ Supports tool use

1. Download and install the latest version of LM Studio from https://lmstudio.ai/download
2. In the app press ⌘/Ctrl + Shift + M and download at least one model, e.g. qwen2.5-coder-7b

   You can also get models via the LM Studio CLI:

   ```sh
   lms get qwen2.5-coder-7b
   ```

3. Make sure the LM Studio API server is running by executing:

   ```sh
   lms server start
   ```

Tip: Set [LM Studio as a login item](https://lmstudio.ai/docs/advanced/headless#run-the-llm-service-on-machine-login) to automate running the LM Studio server.

### Mistral {#mistral}

> ✅ Supports tool use

1. Visit the Mistral platform and [create an API key](https://console.mistral.ai/api-keys/)
2. Open the configuration view (`assistant: show configuration`) and navigate to the Mistral section
3. Enter your Mistral API key

The Mistral API key will be saved in your keychain.

Zed will also use the `MISTRAL_API_KEY` environment variable if it's defined.

#### Custom Models {#mistral-custom-models}

The Zed Assistant comes pre-configured with several Mistral models (codestral-latest, mistral-large-latest, mistral-medium-latest, mistral-small-latest, open-mistral-nemo, and open-codestral-mamba). All the default models support tool use. If you wish to use alternate models or customize their parameters, you can do so by adding the following to your Zed `settings.json`:

```json
{
  "language_models": {
    "mistral": {
      "api_url": "https://api.mistral.ai/v1",
      "available_models": [
        {
          "name": "mistral-tiny-latest",
          "display_name": "Mistral Tiny",
          "max_tokens": 32000,
          "max_output_tokens": 4096,
          "max_completion_tokens": 1024,
          "supports_tools": true
        }
      ]
    }
  }
}
```

Custom models will be listed in the model dropdown in the assistant panel.

### Ollama {#ollama}

> ✅ Supports tool use

Download and install Ollama from [ollama.com/download](https://ollama.com/download) (Linux or macOS) and ensure it's running with `ollama --version`.

1. Download one of the [available models](https://ollama.com/models), for example, for `mistral`:

   ```sh
   ollama pull mistral
   ```

2. Make sure that the Ollama server is running. You can start it either via running Ollama.app (macOS) or launching:

   ```sh
   ollama serve
   ```

3. In the Agent Panel, select one of the Ollama models using the model dropdown.

#### Ollama Context Length {#ollama-context}

Zed has pre-configured maximum context lengths (`max_tokens`) to match the capabilities of common models.
Zed API requests to Ollama include this as `num_ctx` parameter, but the default values do not exceed `16384` so users with ~16GB of ram are able to use most models out of the box.
See [get_max_tokens in ollama.rs](https://github.com/zed-industries/zed/blob/main/crates/ollama/src/ollama.rs) for a complete set of defaults.

> **Note**: Token counts displayed in the Agent Panel are only estimates and will differ from the model's native tokenizer.