> ## Documentation Index
> Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Routing quickstart
> Create a reusable router in Portal or through the API, then send a request through it
Create a reusable router when you need traffic splitting, conditional routes or a saved routing configuration. You can create it in [Portal](#create-your-first-router-on-portal) or through the [API](#create-your-first-router-via-api). To call a model directly first, use the [Inference quickstart](https://docs.inworld.ai/router/quickstart.md).
While this guide uses the OpenAI Chat Completions compatible `/v1/chat/completions` endpoint, you can also integrate with our [Anthropic Messages API compatible](https://docs.inworld.ai/router/anthropic-compatibility.md) `/v1/messages` endpoint, [OpenAI SDK](https://docs.inworld.ai/router/openai-compatibility.md#openai-sdk), and Anthropic SDK.
These examples run on your server with a **Standard** API key. Set `INWORLD_API_KEY` to the copied Base64 credential as-is; do not encode it again. Direct requests use Basic. Creating a router through the API additionally requires Router **Write** permission; calling chat completions does not. Browser/mobile clients should use a [backend-minted token](https://docs.inworld.ai/portal/ephemeral-tokens.md#connect-a-client-through-your-backend) or a server proxy. See [authentication recovery](https://docs.inworld.ai/portal/api-key-auth.md#recover-from-authentication-failures) if a request fails.
## Create your first router on Portal
In [Inworld Portal](https://platform.inworld.ai/), go to **Routers** and select "Compare frontier models".
Click **Save** to create this router, which splits your traffic between Anthropic's Opus 4.6, Google's Gemini 3.1 Pro, and OpenAI's GPT-5.2.
Go to [**API Keys**](https://platform.inworld.ai/api-keys) and click **Generate new key**. Copy the Base64 credentials.
Now run the following code to make your first request to your router.
```bash curl
curl --request POST \
--url https://api.inworld.ai/v1/chat/completions \
--header "Authorization: Basic $INWORLD_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "inworld/compare-frontier-models",
"messages": [
{"role": "user", "content": "Who created you?"}
]
}'
```
If you run the request multiple times, you should see traffic split across Anthropic's Opus 4.6, Google's Gemini 3.1 Pro, and OpenAI's GPT-5.2.
## Create your first router via API
In [Inworld Portal](https://platform.inworld.ai/), go to [**API Keys**](https://platform.inworld.ai/api-keys) and click **Generate new key**. Enable **Write** permissions for the Router API, and click **Generate**.
Copy the Base64 credentials.
Now let's create a router that splits your traffic between Anthropic's Opus 4.6, Google's Gemini 3.1 Pro, and OpenAI's GPT-5.2.
```shell curl
curl --location 'https://api.inworld.ai/router/v1/routers' \
--header 'Content-Type: application/json' \
--header "Authorization: Basic $INWORLD_API_KEY" \
--data '{
"name": "compare-frontier-models",
"default_route": {
"route_id": "default",
"variants": [
{
"variant": {
"variant_id": "anthropic",
"model_id": "anthropic/claude-opus-4-6"
},
"weight": 33
},
{
"variant": {
"variant_id": "google",
"model_id": "google-ai-studio/gemini-3.1-pro-preview"
},
"weight": 33
},
{
"variant": {
"variant_id": "openai",
"model_id": "openai/gpt-5.2"
},
"weight": 34
}
]
}
}'
```
```python Python
import os
import requests
url = "https://api.inworld.ai/router/v1/routers"
headers = {
"Content-Type": "application/json",
"Authorization": f"Basic {os.environ['INWORLD_API_KEY']}"
}
data = {
"name": "compare-frontier-models",
"default_route": {
"route_id": "default",
"variants": [
{
"variant": {
"variant_id": "anthropic",
"model_id": "anthropic/claude-opus-4-6"
},
"weight": 33
},
{
"variant": {
"variant_id": "google",
"model_id": "google-ai-studio/gemini-3.1-pro-preview"
},
"weight": 33
},
{
"variant": {
"variant_id": "openai",
"model_id": "openai/gpt-5.2"
},
"weight": 34
}
]
}
}
response = requests.post(url, headers=headers, json=data)
print(response.json())
```
```javascript JavaScript
const response = await fetch("https://api.inworld.ai/router/v1/routers", {
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": `Basic ${process.env.INWORLD_API_KEY}`
},
body: JSON.stringify({
name: "compare-frontier-models",
default_route: {
route_id: "default",
variants: [
{
variant: {
variant_id: "anthropic",
model_id: "anthropic/claude-opus-4-6"
},
weight: 33
},
{
variant: {
variant_id: "google",
model_id: "google-ai-studio/gemini-3.1-pro-preview"
},
weight: 33
},
{
variant: {
variant_id: "openai",
model_id: "openai/gpt-5.2"
},
weight: 34
}
]
}
})
});
const data = await response.json();
console.log(data);
```
Now run the following code to make your first request to your router.
```bash curl
curl --request POST \
--url https://api.inworld.ai/v1/chat/completions \
--header "Authorization: Basic $INWORLD_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "inworld/compare-frontier-models",
"messages": [
{"role": "user", "content": "Who created you?"}
]
}'
```
If you run the request multiple times, you should see traffic split across Anthropic's Opus 4.6, Google's Gemini 3.1 Pro, and OpenAI's GPT-5.2.
## Next steps
Now that you've made your first request, you can explore more of Inworld Inference's capabilities.
Understand core router concepts, including fallbacks, conditional routing, and more
Learn more about how to use conditional routing
View request and response schemas for Chat Completions and Router APIs