Yes—pass them via the

parameters

keyword on

Flow.deploy(...)

in Prefect 3.x. Example:

from prefect import flow

@flow
def my_flow(x: int = 1, y: str = "a"):
    print(x, y)

# Create a deployment with default parameters
my_flow.deploy(
    name="prod",
    work_pool_name="my-pool",
    parameters={"x": 5, "y": "b"},
)

From a source (e.g., GitHub):

from prefect import flow

@flow
def my_flow(x: int = 1):
    print(x)

my_flow.from_source(
    "<https://github.com/owner/repo>",
    entrypoint="flows/my_flow.py:my_flow",
).deploy(
    name="prod",
    work_pool_name="my-pool",
    parameters={"x": 42},
)

Notes: - Parameter names must match your flow’s function signature. - Values should be JSON-serializable. - Prefect validates types by default; if needed, set

enforce_parameter_schema=False

. - You can still override parameters at run time (e.g., via UI or

prefect deployment run

with

--param

flags). Docs: - Deploy via Python