---
title: "Multi-Model Support"
description: "Access hundreds of AI models through a pluggable gateway abstraction"
---

ChatJS provides access to hundreds of models from multiple providers through a pluggable [gateway system](/gateways/overview). Set `ai.gateway` in `chat.config.ts` to choose your backend, then configure which models are available and how they behave.

<Frame>
  <img src="/docs/images/ai-models.gif" alt="Switching between AI models in the model selector" />
</Frame>

See [Gateways](/gateways/overview) for setup instructions and the full gateway comparison.

## Model Configuration

All model settings live in `chat.config.ts` under the `ai` key:

```typescript title="chat.config.ts"
ai: {
  gateway: "vercel",
  providerOrder: ["openai", "google", "anthropic", "xai"],
  disabledModels: ["morph/morph-v3-large", "morph/morph-v3-fast"],
  curatedDefaults: [
    "openai/gpt-5-nano",
    "openai/gpt-5-mini",
    "google/gemini-2.5-flash-lite",
    "anthropic/claude-sonnet-4.5",
    // ...
  ],
  anonymousModels: [
    "google/gemini-2.5-flash-lite",
    "openai/gpt-5-mini",
    // ...
  ],
  workflows: {
    chat: "openai/gpt-5-nano",
    title: "google/gemini-2.5-flash-lite",
    pdf: "openai/gpt-5-mini",
    chatImageCompatible: "openai/gpt-4o-mini",
  },
  tools: {
    image: {
      enabled: true,
      default: "google/gemini-3-pro-image",
    },
  },
},
```

| Setting                    | Description                                      |
| -------------------------- | ------------------------------------------------ |
| `ai.gateway`               | Active AI gateway                                |
| `ai.providerOrder`         | Provider sort order in the model selector        |
| `ai.disabledModels`        | Models hidden from all users                     |
| `ai.curatedDefaults`       | Models enabled by default for new users          |
| `ai.anonymousModels`       | Models available to anonymous users              |
| `ai.workflows.*`           | Default models for shared application workflows  |
| `ai.tools.*`               | Tool enablement and tool-specific model defaults |

> **Note**
>
> Image generation uses `ai.tools.image.default`. Language models with the `image-generation` tag can also generate images inline. See [Image Generation](/features/image-generation) for details.

## Reasoning Variants

Models that support extended thinking are automatically split into two variants:

- `{model-id}` (standard mode)
- `{model-id}-reasoning` (extended thinking enabled)

This happens automatically in `buildAppModels()` for any model with `reasoning: true`.

## Visibility Pipeline

Model visibility is determined through a pipeline:

### Authenticated Users

1. **Remove** disabled models (`ai.disabledModels`)
2. **Apply defaults** (`ai.curatedDefaults` plus any new API models not in `models.generated.ts`)
3. **Apply user overrides** from saved preferences

### Anonymous Users

1. **Remove** disabled models
2. **Filter** to `ai.anonymousModels` only

## User Settings

Users configure their model preferences at `/settings/models`. This page lets users toggle individual models on or off. A link to [AI Registry](https://airegistry.app) provides detailed model information.