The model list endpoint provides information about the currently available models. There are two ways to retrieve model details.

  1. Request details of all available models.
  2. Request details about a specific model.

​
Base URL

The base URL is the same when requesting details for all available models or a specific model.

https://api.sambanova.ai/

​
All available models

The examples below describe how to request details for all available models.

​
Endpoint

GET /v1/models

​
Example response

The example below demonstrates the reponse for all available models.

In our example, we only list three models.

{
    "data": [
        {
            "context_length": 16384,
            "id": "DeepSeek-R1",
            "max_completion_tokens": 4096,
            "object": "model",
            "owned_by": "[email protected]",
            "pricing": {
                "completion": "0.000007",
                "prompt": "0.000005"
            }
        },
        {
            "context_length": 32768,
            "id": "DeepSeek-R1-Distill-Llama-70B",
            "max_completion_tokens": 4096,
            "object": "model",
            "owned_by": "[email protected]",
            "pricing": {
                "completion": "0.000001",
                "prompt": "0.000001"
            }
        },
        {
            "context_length": 16384,
            "id": "Qwen2.5-Coder-32B-Instruct",
            "max_completion_tokens": 4096,
            "object": "model",
            "owned_by": "[email protected]",
            "pricing": {
                "completion": "0.000003",
                "prompt": "0.000002"
            }
        }
    ],
    "object": "list"
}

​
Response fields

The table below describes the response fields along with their types and descriptions when requesting details for all available models.

FieldTypeDescription
dataArrayList of available models.
idStringThe model ID.
objectStringType of object (always “model”).
owned_byStringThe owner of the model.
context_lengthIntegerMaximum supported context length in tokens.
max_completion_tokensIntegerMaximum tokens that can be generated per request.
pricing.completionStringPrice per completion token.
pricing.promptStringPrice per prompt token.

​
Specific model

The examples below describe how to request details for a specific model.

​
Endpoint

GET /v1/models/{model_id}

​
Path parameter

Parameter: model_id

The official ID name of the model to query (e.g., Qwen2.5-Coder-32B-Instruct). Refer to the Supported models list.

​
Example response

The example below demonstrates the reponse for a specific models.

{
    "context_length": 16384,
    "id": "Qwen2.5-Coder-32B-Instruct",
    "max_completion_tokens": 4096,
    "object": "model",
    "owned_by": "[email protected]",
    "pricing": {
        "completion": "0.000003",
        "prompt": "0.000002"
    }
}

​
Response feilds

The table below describes the response fields along with their types and descriptions when requesting details for a specific model.

FieldTypeDescription
idStringThe model ID.
objectStringType of object (always “model”).
owned_byStringThe owner of the model.
context_lengthIntegerMaximum supported context length in tokens.
max_completion_tokensIntegerMaximum tokens that can be generated per request.
pricing.completionStringPrice per completion token.
pricing.promptStringPrice per prompt token.