id | str | "llama-3.3-70b-versatile" | The id of the Groq model to use |
name | str | "Groq" | The name of the model |
provider | str | "Groq" | The provider of the model |
frequency_penalty | Optional[float] | None | Penalizes new tokens based on their frequency in the text so far |
logit_bias | Optional[Any] | None | Modifies the likelihood of specified tokens appearing in the completion |
logprobs | Optional[bool] | None | Whether to return log probabilities of the output tokens |
max_tokens | Optional[int] | None | Maximum number of tokens to generate |
presence_penalty | Optional[float] | None | Penalizes new tokens based on whether they appear in the text so far |
seed | Optional[int] | None | Random seed for deterministic sampling |
stop | Optional[Union[str, List[str]]] | None | Sequences where the API stops generating further tokens |
temperature | Optional[float] | None | Controls randomness in the model’s output |
top_logprobs | Optional[int] | None | Number of most likely tokens to return log probabilities for |
top_p | Optional[float] | None | Controls diversity via nucleus sampling |
user | Optional[str] | None | A unique identifier representing your end-user |
extra_headers | Optional[Any] | None | Additional headers to include in requests |
extra_query | Optional[Any] | None | Additional query parameters to include in requests |
request_params | Optional[Dict[str, Any]] | None | Additional parameters to include in the request |
api_key | Optional[str] | None | The API key for Groq (defaults to GROQ_API_KEY env var) |
base_url | Optional[Union[str, httpx.URL]] | None | The base URL for the Groq API. When unset, the Groq client falls back to the GROQ_BASE_URL env var, then https://api.groq.com |
timeout | Optional[int] | None | Request timeout in seconds |
max_retries | Optional[int] | None | Maximum number of retries for failed requests, handled by the Groq client |
default_headers | Optional[Any] | None | Default headers to include in all requests |
default_query | Optional[Any] | None | Default query parameters to include in all requests |
http_client | Optional[Union[httpx.Client, httpx.AsyncClient]] | None | Custom httpx client to use for requests |
client_params | Optional[Dict[str, Any]] | None | Additional parameters for client configuration |
client | Optional[GroqClient] | None | A pre-configured instance of the Groq client |
async_client | Optional[AsyncGroqClient] | None | A pre-configured instance of the async Groq client |
model_type | ModelType | ModelType.MODEL | Functional role of this model (MODEL, OUTPUT_MODEL, or PARSER_MODEL). Set by the agent during initialization |
supports_native_structured_outputs | bool | False | True if the model supports structured outputs natively |
supports_json_schema_outputs | bool | False | True if the model requires a JSON schema for structured outputs |
system_prompt | Optional[str] | None | System prompt from the model added to the Agent |
instructions | Optional[List[str]] | None | Instructions from the model added to the Agent |
tool_message_role | str | "tool" | Role used for tool messages |
assistant_message_role | str | "assistant" | Role used for assistant messages |
cache_response | bool | False | Cache model responses to avoid redundant API calls during development |
cache_ttl | Optional[int] | None | Time-to-live for cached model responses, in seconds. If None, cache never expires |
cache_dir | Optional[str] | None | Directory for cached model responses. If None, uses the default cache location |
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 |
retry_with_guidance | bool | True | Retry the model invocation with a guidance message for known errors avoidable with extra instructions |
retry_with_guidance_limit | int | 1 | Number of times to retry the model invocation with guidance |
