Your team's enabled models determine which models the AI Router can choose. Open your team in the dashboard, go to Models, and select the models you want to enable for each provider. The AI Router applies this configuration server-side on every request, so your application does not need to send a model list.
Make sure you have completed the Quickstart first. See the dashboard Models page for the complete list of models you can enable. In model routing mode AI Router only executes models of providers with a connected and enabled provider key; model selection is independent of provider keys.
Deprecated models are marked on the Models page. They keep working until their sunset date, but you should move to a successor model.
The Models page has a switch Automatically add new models from enabled providers. When it is on, every model we add for one of your enabled providers is added to your allowlist and used for routing right away. When it is off, new models are ignored until you enable them yourself.
You can restrict an API key to a subset of your team's enabled models. Open your team in the dashboard, go to Settings → API Keys, and create a key. Expand Router Configuration in the dialog and select the subset of models the key may use. The subset is fixed when the key is created, and a key cannot enable models that are disabled for the team; to change it, create a new key.
For requests that need a different allowlist, pass model names in extra_body.models. A single-element list turns the request into a plain gateway call to that model.
Per-request parameters override your account configuration. When a request sends routing parameters, the AI Router uses those values for that request instead of your account configuration. Requests that hard-code routing parameters will not pick up later changes you make in the dashboard.
Using OpenAI:
Using langchain:
Using langchain.js:
...
client.chat.completions.create(
model="auto",
messages=[<omitted>],
extra_body={
'models': ['mistral-large', 'gpt-5.2']
}
)
llm = ChatOpenAI(
model="auto",
base_url='https://api.airouter.io',
model_kwargs={
'extra_body': {
'models': ['mistral-large', 'gpt-5.2'],
},
},
)
import { ChatOpenAI } from '@langchain/openai';
import { PromptTemplate } from '@langchain/core/prompts';
const llm = new ChatOpenAI({
model: 'auto',
apiKey: '<THE-API-KEY-YOU-GENERATED>',
configuration: { baseURL: "https://api.airouter.io" },
modelKwargs: {
models: ['mistral-large', 'gpt-5.2'],
},
});
const prompt = PromptTemplate.fromTemplate(
'What is the capital of France?',
);
const chain = prompt.pipe(llm);
const result = await chain.invoke({});