> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/lbjlaq/Antigravity-Manager/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Routing & Mapping

> Configure custom model routing and mapping rules

## Overview

Model mapping allows you to route API requests for specific models (like GPT-4 or Claude) to your preferred Google AI models.

## Configuration

### Custom Mapping

<ParamField path="custom_mapping" type="object" default="{}">
  Custom exact model mapping table

  Maps incoming model names to target Google AI models.

  **Type**: `HashMap<String, String>`\
  **Location**: `config.rs:491`
</ParamField>

## Mapping Examples

### Basic Mapping

Route GPT-4 requests to Gemini Pro:

```json theme={null}
{
  "proxy": {
    "custom_mapping": {
      "gpt-4": "gemini-3.1-pro-high",
      "gpt-4o": "gemini-3-flash",
      "gpt-3.5-turbo": "gemini-2.5-flash"
    }
  }
}
```

### Wildcard Mapping

Use wildcards for pattern matching:

```json theme={null}
{
  "proxy": {
    "custom_mapping": {
      "gpt-4*": "gemini-3.1-pro-high",
      "claude-3-opus-*": "claude-opus-4-6-thinking",
      "claude-3-5-sonnet-*": "claude-sonnet-4-6"
    }
  }
}
```

## Preset Configurations

Antigravity provides built-in presets for common use cases:

### Default Preset

Balanced performance and cost:

```json theme={null}
{
  "gpt-4*": "gemini-3.1-pro-high",
  "gpt-4o*": "gemini-3-flash",
  "gpt-3.5*": "gemini-2.5-flash",
  "o1-*": "gemini-3.1-pro-high",
  "o3-*": "gemini-3.1-pro-high",
  "claude-3-5-sonnet-*": "claude-sonnet-4-6",
  "claude-3-opus-*": "claude-opus-4-6-thinking",
  "claude-haiku-*": "gemini-2.5-flash"
}
```

### Performance Preset

Maximum quality, higher cost:

```json theme={null}
{
  "gpt-4*": "claude-opus-4-6-thinking",
  "gpt-4o*": "claude-sonnet-4-6",
  "gpt-3.5*": "gemini-3-flash",
  "o1-*": "claude-opus-4-6-thinking",
  "claude-3-5-sonnet-*": "claude-sonnet-4-6",
  "claude-3-opus-*": "claude-opus-4-6-thinking"
}
```

### Cost-Effective Preset

Minimum cost, good performance:

```json theme={null}
{
  "gpt-4*": "gemini-3-flash",
  "gpt-4o*": "gemini-2.5-flash",
  "gpt-3.5*": "gemini-2.5-flash",
  "o1-*": "gemini-3-flash",
  "claude-3-5-sonnet-*": "gemini-3-flash",
  "claude-3-opus-*": "gemini-3-flash"
}
```

## z.ai Provider Integration

Route Claude requests to z.ai (GLM models):

<ParamField path="zai.enabled" type="boolean" default="false">
  Enable z.ai provider integration

  **Location**: `config.rs:227`
</ParamField>

<ParamField path="zai.base_url" type="string" default="https://api.z.ai/api/anthropic">
  z.ai API base URL

  **Location**: `config.rs:228-229`
</ParamField>

<ParamField path="zai.api_key" type="string" required>
  z.ai API key

  **Location**: `config.rs:231`
</ParamField>

<ParamField path="zai.dispatch_mode" type="enum" default="off">
  How to dispatch requests to z.ai

  **Options**:

  * `off`: Never use z.ai
  * `exclusive`: Use z.ai for all Anthropic protocol requests
  * `pooled`: Treat z.ai as one slot in the shared pool
  * `fallback`: Use z.ai only when Google pool is unavailable

  **Location**: `config.rs:161-175`
</ParamField>

### z.ai Model Mapping

<ParamField path="zai.model_mapping" type="object" default="{}">
  Per-model overrides for z.ai routing

  Maps Claude model IDs to z.ai model IDs.

  **Type**: `HashMap<String, String>`\
  **Location**: `config.rs:236-237`
</ParamField>

<ParamField path="zai.models.opus" type="string" default="glm-4.7">
  Default z.ai model for Opus family

  **Location**: `config.rs:182`
</ParamField>

<ParamField path="zai.models.sonnet" type="string" default="glm-4.7">
  Default z.ai model for Sonnet family

  **Location**: `config.rs:185`
</ParamField>

<ParamField path="zai.models.haiku" type="string" default="glm-4.5-air">
  Default z.ai model for Haiku family

  **Location**: `config.rs:188`
</ParamField>

### z.ai Configuration Example

```json theme={null}
{
  "proxy": {
    "zai": {
      "enabled": true,
      "base_url": "https://api.z.ai/api/anthropic",
      "api_key": "sk-zai-key...",
      "dispatch_mode": "fallback",
      "model_mapping": {
        "claude-3-opus": "glm-4.7",
        "claude-3-sonnet": "glm-4.7"
      },
      "models": {
        "opus": "glm-4.7",
        "sonnet": "glm-4.7",
        "haiku": "glm-4.5-air"
      }
    }
  }
}
```

## Advanced Features

### MCP (Model Context Protocol)

Enable advanced capabilities for z.ai models:

<ParamField path="zai.mcp.enabled" type="boolean" default="false">
  Enable MCP features

  **Location**: `config.rs:203`
</ParamField>

<ParamField path="zai.mcp.web_search_enabled" type="boolean" default="false">
  Enable web search capability

  **Location**: `config.rs:205`
</ParamField>

<ParamField path="zai.mcp.web_reader_enabled" type="boolean" default="false">
  Enable web content reading

  **Location**: `config.rs:207`
</ParamField>

<ParamField path="zai.mcp.vision_enabled" type="boolean" default="false">
  Enable vision/image understanding

  **Location**: `config.rs:209`
</ParamField>

## UI Configuration

You can configure model mappings through the Web UI:

1. Navigate to **API Proxy** settings
2. Expand the **Model Router** section
3. Select a preset or create custom mappings
4. Click **Apply** to activate

Changes take effect immediately without restarting the proxy service.

## Best Practices

<Note>
  * Test mappings with a small request before production use
  * Use wildcards (`*`) for flexible pattern matching
  * Consider cost vs. performance when choosing target models
  * Save custom mappings as presets for easy switching
  * Monitor token usage after changing mappings
</Note>

## Troubleshooting

### Mapping Not Applied

1. Verify the exact model name from client requests
2. Check wildcard pattern syntax
3. Ensure proxy service is running
4. Review debug logs for routing decisions

### Model Not Found

1. Confirm target model exists in your accounts
2. Check model availability in your region
3. Verify account quota hasn't been exhausted