---
title: Custom
description: Custom vendor configuration for third-party API proxies and local models
---

For model services accessed via the OpenAI-compatible protocol or locally deployed models, such as:

- **Third-party API proxies**: call multiple models through a unified API base
- **Local models**: models deployed locally with tools like Ollama, vLLM, LocalAI
- **Private deployments**: model services deployed inside an enterprise

<Note>
  Difference from the `openai` vendor: when a custom vendor is selected, switching models via `/config model` does not automatically switch the vendor type — the custom API address is always used.
</Note>

## Text Chat

### Third-party API proxy

```json
{
  "bot_type": "custom",
  "model": "",
  "custom_api_key": "YOUR_API_KEY",
  "custom_api_base": "https://{your-proxy.com}/v1"
}
```

| Parameter | Description |
| --- | --- |
| `bot_type` | Must be set to `custom` |
| `model` | Model name; any model name supported by the proxy service |
| `custom_api_key` | API key provided by the proxy service |
| `custom_api_base` | API endpoint provided by the proxy service; must be OpenAI-compatible |

### Local models

Local models usually do not require an API key — only the API base needs to be filled in:

```json
{
  "bot_type": "custom",
  "model": "qwen3.5:27b",
  "custom_api_base": "http://localhost:11434/v1"
}
```

Common local deployment tools and their default endpoints:

| Tool | Default API Base |
| --- | --- |
| [Ollama](https://ollama.com) | `http://localhost:11434/v1` |
| [vLLM](https://docs.vllm.ai) | `http://localhost:8000/v1` |
| [LocalAI](https://localai.io) | `http://localhost:8080/v1` |

### Switching Models

Switching models under a custom vendor only changes `model` — `bot_type` and the API endpoint remain unchanged:

```
/config model qwen3.5:27b
```

## Configuring Multiple Custom Providers

If you need to configure several OpenAI-compatible third-party services at once (e.g. SiliconFlow, Qiniu), use the `custom_providers` list and activate one by setting `bot_type` to `"custom:<id>"`:

```json
{
  "bot_type": "custom:3f2a9c1b",
  "custom_providers": [
    {
      "id": "3f2a9c1b",
      "name": "siliconflow",
      "api_key": "YOUR_SILICONFLOW_KEY",
      "api_base": "https://api.siliconflow.cn/v1",
      "model": "deepseek-ai/DeepSeek-V3"
    },
    {
      "id": "a1b2c3d4",
      "name": "qiniu",
      "api_key": "YOUR_QINIU_KEY",
      "api_base": "https://api.qnaigc.com/v1",
      "model": "deepseek-v3"
    }
  ]
}
```

| Parameter | Description |
| --- | --- |
| `custom_providers` | List of custom providers; each item has `id`, `name`, `api_key`, `api_base`, and an optional `model` |
| `bot_type` | Set to `"custom:<id>"` to activate a specific provider; `id` is the provider's unique identifier |
| `id` | Server-generated short identifier (8-char hex); used as the primary key for each provider |
| `name` | User-facing display label — can be freely renamed without breaking anything |
| `model` | Optional; when set, this model is used instead of the global `model` field |

<Note>
  The `id` is auto-generated by the web console when you add a provider — you don't need to create it manually. If editing `config.json` by hand, use any unique 8-character hex string (e.g. run `python3 -c "import uuid; print(uuid.uuid4().hex[:8])"`).
</Note>

<Note>
  When `bot_type` is exactly `"custom"` (no colon suffix), CowAgent uses the legacy single-provider `custom_api_key` / `custom_api_base` fields, so existing configurations keep working without any changes.
</Note>