# Provider Routing

Source: https://ofox.ai/docs/develop/advanced/provider-routing

A model is often served by more than one provider — `bytedance/seedance-2.0`, for example, comes from both `volcengine` and `byteplus`. ofox selects a provider automatically; `provider.type` pins the request to a specific one.

## Default routing behaviour

When no `provider` field is sent, ofox distributes the request by weight across the channels currently serving that model. Which provider serves any single request is not predictable.

## Pinning a provider

Pass the provider name in the `type` field. The field is located differently for each model type:

| Model type | Field path |
|------|------|
| Chat models | `extra_body.provider.type` |
| Video models | `provider.type` |

**The Gemini native protocol ignores `extra_body.provider` in the body** — the request succeeds and the constraint simply does not apply, with no error. On that protocol use the `X-OfoxAI-Provider-Type` header instead. The per-protocol field contract is in [API · Provider routing](https://ofox.ai/docs/api/provider-routing).

**Chat models**

**cURL**

```bash filename="Terminal"
curl https://api.ofox.ai/v1/chat/completions \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5.5",
    "messages": [{ "role": "user", "content": "..." }],
    "extra_body": {
      "provider": { "type": "bedrock" }
    }
  }'
```

**Python**

```python filename="provider_routing.py"
client.chat.completions.create(
    model="anthropic/claude-sonnet-5.5",
    messages=[{"role": "user", "content": "..."}],
    extra_body={"extra_body": {"provider": {"type": "bedrock"}}},
)
```

**TypeScript**

```typescript filename="provider-routing.ts"
await client.chat.completions.create({
  model: 'anthropic/claude-sonnet-5.5',
  messages: [{ role: 'user', content: '...' }],
  extra_body: { provider: { type: 'bedrock' } },
} as any)
```

With the official OpenAI SDKs, `extra_body` must be present as a literal key in the request body. The TypeScript SDK sends it as written in the params object. The Python SDK's `extra_body=` argument merges its contents into the top level of the body, so the key must be nested one level deeper, or passed as a request header instead.

**Video models**

**cURL**

```bash filename="Terminal"
curl https://api.ofox.ai/v1/videos \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bytedance/seedance-2.0-mini",
    "prompt": "...",
    "duration": 5,
    "provider": { "type": "byteplus" }
  }'
```

**Python**

```python filename="provider_routing_video.py"
requests.post(
    "https://api.ofox.ai/v1/videos",
    headers={"Authorization": f"Bearer {OFOX_API_KEY}"},
    json={
        "model": "bytedance/seedance-2.0-mini",
        "prompt": "...",
        "duration": 5,
        "provider": {"type": "byteplus"},
    },
)
```

**TypeScript**

```typescript filename="provider-routing-video.ts"
await fetch('https://api.ofox.ai/v1/videos', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${OFOX_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'bytedance/seedance-2.0-mini',
    prompt: '...',
    duration: 5,
    provider: { type: 'byteplus' },
  }),
})
```

## Available providers

The providers currently supported by ofox are listed below. Short names, shown in parentheses, are equivalent to the full name; either may be used:

| Provider | Description |
|------|------|
| `openai` | [OpenAI](https://openai.com)：official API for the GPT family |
| `anthropic` | [Anthropic](https://www.anthropic.com)：official API for the Claude family |
| `gemini` | [Google AI](https://ai.google.dev)：official API for the Gemini family |
| `azure_foundry` (`foundry`) | [Azure AI Foundry](https://azure.microsoft.com/products/ai-foundry)：model hosting platform on Microsoft Azure |
| `aws_bedrock` (`bedrock`) | [Amazon Bedrock](https://aws.amazon.com/bedrock/)：model hosting service on AWS |
| `google_vertex` (`vertex`) | [Vertex AI](https://cloud.google.com/vertex-ai)：model hosting platform on Google Cloud |
| `aliyun` | [Alibaba Cloud Bailian](https://www.aliyun.com/product/bailian)：Alibaba Cloud's model service platform |
| `alicloud` | [Alibaba Cloud Model Studio](https://www.alibabacloud.com/product/modelstudio)：Alibaba Cloud's international model service platform |
| `volcengine` | [Volcengine Ark](https://www.volcengine.com/product/ark)：ByteDance's platform for mainland China |
| `byteplus` | [BytePlus](https://www.byteplus.com)：ByteDance's platform for markets outside mainland China |
| `deepseek` | [DeepSeek](https://platform.deepseek.com)：official API for the DeepSeek family |
| `moonshot` | [Moonshot AI](https://platform.moonshot.cn)：official API for the Kimi family |
| `zhipu` | [Zhipu AI](https://open.bigmodel.cn)：official API for the GLM family |
| `zai` | [Z.ai](https://docs.z.ai)：official API for the GLM family outside mainland China |
| `minimax` | [MiniMax](https://platform.minimaxi.com)：official API for the MiniMax family |
| `grok` | [xAI](https://x.ai)：official API for the Grok family |
| `jina` | [Jina AI](https://jina.ai)：embedding and rerank models |
| `tencent` | [Tencent Cloud Hunyuan](https://cloud.tencent.com/product/hunyuan)：Tencent Cloud's model service platform |

Not every provider serves every model. Which providers serve a given model — and which protocols each of them supports — is shown on that model's page in the [model catalog](https://ofox.ai/models). The same data is available programmatically as `provider_cards[]` from `GET /v2/models/catalog/{provider}/{slug}?include=provider_price`.

### Chat models

Chat models are spread across most of the providers above. The exact mapping and protocol support are given on each model's page.

### Video models

The `bytedance/seedance-*` family is served by the two providers below, whose content policies differ:

| Provider | Description | Content policy |
|------|------|------|
| `volcengine` | Volcengine Ark, ByteDance's platform for mainland China | Standard moderation |
| `byteplus` | BytePlus, ByteDance's platform for markets outside mainland China | Allows not-for-all-audiences (NSFW) content |

`byteplus` allows seedance to generate not-for-all-audiences (NSFW) content, while `volcengine` applies standard moderation. **`provider.type: "byteplus"` must be set explicitly when such content is required**; otherwise the weighted distribution may route the request to `volcengine`, where moderation will reject it.

## Common errors

| `error.type` | Trigger |
|------|------|
| `invalid_provider_type` | The value is not in the provider enum: a misspelled name, or a retired spelling. |
| `provider_type_unavailable` | The provider exists but does not serve this model. For chat models the error message also lists the providers that do. |