Skip to main content
The Models endpoint returns every model your API key can access. Because NexLLM uses channel groups to control model access, the list you receive reflects the specific group assigned to your key — different keys may return different sets of models. Use this endpoint to programmatically discover available model IDs before making inference requests.

​
Endpoint

GET https://www.nexllm.ai/v1/models
This endpoint requires no request body. Include your API key in the Authorization header as usual.

​
Response Fields

​
data
array
An array of model objects representing every model accessible to your API key.
​
data[].id
string
The unique identifier for the model. Pass this value as the model parameter in chat, embeddings, and other inference requests. Examples: gpt-4o, aws/claude-haiku-4-5, gemini-2.5-flash.
​
data[].owned_by
string
The organization that owns or provides the underlying model, such as openai, anthropic, or google.

​
Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://www.nexllm.ai/v1"
)

models = client.models.list()

for model in models.data:
    print(model.id)

​
Example Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "owned_by": "openai"
    },
    {
      "id": "aws/claude-haiku-4-5",
      "object": "model",
      "owned_by": "anthropic"
    },
    {
      "id": "gemini-2.5-flash",
      "object": "model",
      "owned_by": "google"
    }
  ]
}
The models returned depend on the channel group assigned to your API key. If you expect to see a model that isn’t appearing in the list, confirm that your key’s group includes that model. Use an API key assigned to the default group to see all models available on the platform.
Want to understand how channel groups control model access? Visit the Channel Groups overview to learn how to assign the right group to your API keys.