Implementation:Togethercomputer Together python Endpoint Types

Knowledge Sources	Together Python
Domains	Infrastructure, Type_System
Last Updated	2026-02-15 16:00 GMT

Overview

Concrete type definitions for dedicated endpoint management provided by the Together Python SDK.

Description

This module defines the Pydantic models used for endpoint-related API requests and responses. Key types include DedicatedEndpoint (full endpoint details), ListEndpoint (summary for list queries), HardwareWithStatus (hardware config with availability), Autoscaling (scaling config), and the base TogetherJSONModel which provides JSON serialization with datetime handling.

Usage

Import these types when you need to type-hint endpoint-related data structures or inspect endpoint response objects returned by the Endpoints resource methods.

Code Reference

Source Location

• Repository: Together Python
• File: src/together/types/endpoints.py
• Lines: 1-123

Signature

class TogetherJSONModel(BaseModel): ...

class Autoscaling(TogetherJSONModel):
    min_replicas: int
    max_replicas: int

class HardwareWithStatus(TogetherJSONModel):
    object: Literal["hardware"]
    id: str
    pricing: EndpointPricing
    specs: HardwareSpec
    availability: Optional[HardwareAvailability] = None
    updated_at: datetime

class DedicatedEndpoint(BaseEndpoint):
    id: str
    type: Literal["dedicated"]
    display_name: str
    hardware: str
    autoscaling: Autoscaling

class ListEndpoint(BaseEndpoint):
    type: Literal["dedicated", "serverless"]

Import

from together.types.endpoints import DedicatedEndpoint, ListEndpoint, HardwareWithStatus

I/O Contract

Inputs

Name	Type	Required	Description
(constructed from API response dicts)	Dict[str, Any]	Yes	API JSON response data parsed into typed models

Outputs

Name	Type	Description
DedicatedEndpoint	Pydantic Model	Full endpoint with id, model, hardware, autoscaling, state
ListEndpoint	Pydantic Model	Summary endpoint with id, model, type, owner, state
HardwareWithStatus	Pydantic Model	Hardware config with GPU specs, pricing, and availability
Autoscaling	Pydantic Model	min_replicas and max_replicas configuration

Usage Examples

from together import Together

client = Together()

# DedicatedEndpoint is returned by create/get/update
endpoint = client.endpoints.create(
    model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
    hardware="1x_nvidia_h100_80gb_sxm",
    min_replicas=1,
    max_replicas=3,
)

# Access typed fields
print(endpoint.autoscaling.min_replicas)  # 1
print(endpoint.hardware)  # "1x_nvidia_h100_80gb_sxm"
print(endpoint.state)  # "STARTED"

# HardwareWithStatus from list_hardware
hw_list = client.endpoints.list_hardware()
for hw in hw_list:
    print(f"{hw.specs.gpu_type}: {hw.specs.gpu_memory}GB x{hw.specs.gpu_count}")

Related Pages

• Principle:Togethercomputer_Together_python_Endpoint_Management