# Models

Invoke supports a wide range of AI models from leading providers. Each model has different capabilities, context windows, and pricing.

## Available Models

| Model                                    | Context | Images | Thinking |
|------------------------------------------|---------|--------|----------|
| `claude-opus-4-7`                       | 1.0M    |        |          |
| `claude-opus-4-6`                       | 1.0M    |        |          |
| `claude-sonnet-4-6`                     | 1.0M    |        |          |
| `claude-sonnet-4-5-20250929`            | 200K    |        |          |
| `claude-sonnet-4-20250514`              | 200K    |        |          |
| `claude-opus-4-1-20250805`              | 200K    |        |          |
| `claude-3-5-haiku-20241022`             | 200K    |        |          |
| `claude-haiku-4-5-20251001`             | 200K    |        |          |
| `gpt-5.5-pro-2026-04-23`                 | 1.0M    |        |          |
| `gpt-5.5-2026-04-23`                     | 1.0M    |        |          |

## Selecting a Model

### Open the model selector

Click the **model dropdown** in the chat input area (shows current model name).

### Browse available models

Models are grouped by provider. Only models you've enabled in Settings appear here.

### Choose your model

Click a model to select it. Your choice is saved for future conversations.

## Configuring Model Visibility

Control which models appear in the model selector:

1. Go to **Settings → Models**  
2. Toggle models on/off for each provider  
3. Disabled models won't appear in the selector

Hide models you don't use to keep the selector clean and focused.

## Using Ollama (Local Models)

Run AI models locally with Ollama:

### Install Ollama

Download and install [Ollama](https://ollama.ai/) on your machine.

### Pull a model

```
ollama pull llama3.2
ollama pull codellama
```

### Configure in Invoke

Go to **Settings → Ollama** and ensure the connection is configured.

### Select your local model

Ollama models appear in the model selector under "Ollama".

Local models run entirely on your machine—no API keys or internet required.

## Choosing the Right Model

### For everyday coding

- **Claude Sonnet** or **GPT-5** — Good balance of speed and capability  
- **Gemini Flash** — Fast responses for quick tasks

### For complex reasoning

- **Claude Opus** — Deep analysis and planning  
- Models with **Extended Thinking** — Enable for complex problems

### For cost efficiency

- **Claude Haiku** — Fast and affordable  
- **Ollama models** — Free (runs locally)

### For vision tasks

- Any model with **Vision** capability  
- Upload screenshots for UI debugging, error analysis, etc.

## API Keys

Each provider requires an API key. See [Getting Started](/content/docs/getting-started#configure-your-ai-provider/index.html) for setup instructions.

| Provider | Get API Key |
|----------|-------------|
| Anthropic | [console.anthropic.com](https://console.anthropic.com/) |
| OpenAI | [platform.openai.com](https://platform.openai.com/api-keys) |
| Google | [aistudio.google.com](https://aistudio.google.com/apikey) |
| xAI | [x.ai](https://x.ai/) |