Skip to main content
Models are the AI systems that process your requests. You specify the model in each request body, and you can use an access key configuration to restrict which models an access key may call.

​
Specifying models

​
Model name only

{
  "model": "gpt-4o",
  "messages": [{"role": "user", "content": "Hello"}]
}
The gateway looks up gpt-4o in the model catalog and routes to OpenAI.

​
Provider prefix

{
  "model": "anthropic:claude-sonnet-4-6",
  "messages": [{"role": "user", "content": "Hello"}]
}
Use provider:model when you want to force a specific provider or target a model you run yourself.

​
Multiple models (failover)

List fallback models with the models array: 
{
  "model": "gpt-4o",
  "models": ["gpt-4o-mini", "anthropic:claude-sonnet-4-6"],
  "messages": [{"role": "user", "content": "Hello"}]
}
The gateway tries model first, then each entry in models in order, until one succeeds.

​
Unknown models (pass-through)

If a model is not in the catalog, the gateway still routes it when you include a provider prefix: 
{
  "model": "openai:some-new-model",
  "messages": [{"role": "user", "content": "Hello"}]
}
The provider returns an error if the model does not exist. Pass-through models must still be allowed by the access key’s configuration.

​
Model aliases

Model and provider names are not case-sensitive. The catalog includes built-in aliases—see Aliases reference.

​
Model capabilities

Models differ in input/output modalities, context window, and features. See the model catalog for details.

​
Next steps