id | str | "nvidia/llama-3.1-nemotron-70b-instruct" | The id of the NVIDIA model to use |
name | str | "NVIDIA" | The name of the model |
provider | str | "NVIDIA" | The provider of the model |
api_key | Optional[str] | None | The API key for NVIDIA (defaults to NVIDIA_API_KEY env var) |
base_url | str | "https://integrate.api.nvidia.com/v1" | The base URL for the NVIDIA API |
retries | int | 0 | Number of retries to attempt before raising a ModelProviderError |
delay_between_retries | int | 1 | Delay between retries, in seconds |
exponential_backoff | bool | False | If True, the delay between retries is doubled each time |
