List models

Retrieve a list of available Serverless Inference models and their IDs using the models endpoint.

This page shows how to retrieve all models available through the Serverless Inference API, along with their IDs. Use this endpoint to discover available models programmatically, select a model dynamically at runtime, or confirm which models your account can access.

Request examples

The following examples show how to call the models endpoint from Python and from the command line.

Python

import openai

client = openai.OpenAI(
    base_url="https://api.inference.wandb.ai/v1",
    api_key="[YOUR-API-KEY]",
    project="[YOUR-TEAM]/[YOUR-PROJECT]"  # Optional, for usage tracking
)

response = client.models.list()

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

Bash

curl https://api.inference.wandb.ai/v1/models \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer [YOUR-API-KEY]" \
  -H "OpenAI-Project: [YOUR-TEAM]/[YOUR-PROJECT]"

Response format

The endpoint returns a list of model objects in OpenAI-compatible format, so you can parse the response using standard OpenAI client libraries. Each entry includes the model ID you pass to other Inference API endpoints.

{
  "object": "list",
  "data": [
    {
      "id": "deepseek-ai/DeepSeek-V3.1",
      "object": "model",
      "created": 0,
      "owned_by": "system",
      "root": "deepseek-ai/DeepSeek-V3.1"
    },
    {
      "id": "openai/gpt-oss-20b",
      "object": "model",
      "created": 0,
      "owned_by": "system",
      "root": "openai/gpt-oss-20b"
    }
    // ... more models
  ]
}