Models

List all models currently available on the INFER network.

Endpoint


GET /api/v1/models

Response


{
  "object": "list",
  "data": [
    {
      "id": "llama-3.1-8b",
      "object": "model",
      "owned_by": "meta",
      "pricing": {
        "prompt": 0.10,
        "completion": 0.10,
        "unit": "per_million_tokens"
      }
    },
    {
      "id": "llama-3.1-70b",
      "object": "model",
      "owned_by": "meta",
      "pricing": {
        "prompt": 0.50,
        "completion": 0.50,
        "unit": "per_million_tokens"
      }
    },
    {
      "id": "mixtral-8x22b",
      "object": "model",
      "owned_by": "mistralai",
      "pricing": {
        "prompt": 0.60,
        "completion": 0.60,
        "unit": "per_million_tokens"
      }
    }
  ]
}

Available Models

Model ID	Provider	Context	Price (per 1M tokens)
`llama-3.1-8b`	Meta	128K	$0.10
`llama-3.1-70b`	Meta	128K	$0.50
`mixtral-8x22b`	Mistral AI	64K	$0.60

Model Selection

Specify the model ID in the model field of your chat completions request. If a model is temporarily unavailable (no nodes serving it), the request will return a 503 error.

The network continuously adds new models as node operators deploy them. Check /api/v1/models for the latest availability.