Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vast.ai/llms.txt

Use this file to discover all available pages before exploring further.

Create a new serverless endpoint group.

​
Signature

VastAI.create_endpoint(
    min_load: float = 0.0,
    target_util: float = 0.9,
    cold_mult: float = 2.5,
    cold_workers: int = 5,
    max_workers: int = 20,
    endpoint_name: Optional[str] = None
) -> str

​
Parameters

​
min_load
float
default:"0.0"
Minimum load (requests/sec) below which idle workers are scaled down.
​
target_util
float
default:"0.9"
Target worker utilization ratio (0.0-1.0); workers are added to stay at this level.
​
cold_mult
float
default:"2.5"
Multiplier applied to warm worker count for pre-warming cold workers.
​
cold_workers
int
default:"5"
Number of pre-warmed (cold) workers to keep ready.
​
max_workers
int
default:"20"
Maximum number of workers allowed in this endpoint.
​
endpoint_name
Optional[str]
Human-readable name for the endpoint.

​
Returns

str, Result from the API call.

​
Example

from vastai import VastAI

client = VastAI(api_key="YOUR_API_KEY")
result = client.create_endpoint()
print(result)