llm-cost-monitor 1.0.0

Official Python SDK for LLM Cost Monitor - Track, aggregate, and analyze LLM usage costs

llmcost

Open-source LLM cost observability platform API. Track, aggregate, and analyze LLM usage costs across your applications.

This Python package is automatically generated by the OpenAPI Generator project:

• API version: v1.0.0
• Package version: 1.0.0
• Generator version: 7.18.0
• Build package: org.openapitools.codegen.languages.PythonClientCodegen

Requirements.

Python 3.9+

Installation & Usage

pip install

If the python package is hosted on a repository, you can install directly using:

pip install git+https://github.com/GIT_USER_ID/GIT_REPO_ID.git

(you may need to run pip with root permission: sudo pip install git+https://github.com/GIT_USER_ID/GIT_REPO_ID.git)

Then import the package:

import llmcost

Setuptools

Install via Setuptools.

python setup.py install --user

(or sudo python setup.py install to install the package for all users)

Then import the package:

import llmcost

Tests

Execute pytest to run the tests.

Getting Started

Please follow the installation procedure and then run the following:

import llmcost
from llmcost.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost:8080
# See configuration.py for a list of all supported configuration parameters.
configuration = llmcost.Configuration(
    host = "http://localhost:8080"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure API key authorization: ApiKeyAuth
configuration.api_key['ApiKeyAuth'] = os.environ["API_KEY"]

# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['ApiKeyAuth'] = 'Bearer'


# Enter a context with an instance of the API client
with llmcost.ApiClient(configuration) as api_client:
    # Create an instance of the API class
    api_instance = llmcost.AlertsApi(api_client)
    create_alert_request = {"threshold":100.0,"window_interval":"24h"} # CreateAlertRequest | 

    try:
        # Create budget alert
        api_response = api_instance.create_alert(create_alert_request)
        print("The response of AlertsApi->create_alert:\n")
        pprint(api_response)
    except ApiException as e:
        print("Exception when calling AlertsApi->create_alert: %s\n" % e)

Documentation for API Endpoints

All URIs are relative to http://localhost:8080

Class	Method	HTTP request	Description
AlertsApi	create_alert	POST /v1/alerts	Create budget alert
AlertsApi	delete_alert	DELETE /v1/alerts/{id}	Delete alert
AlertsApi	list_alerts	GET /v1/alerts	List budget alerts
EventsApi	create_event	POST /v1/events	Track LLM usage event
EventsApi	list_events	GET /v1/events	List LLM usage events
MetricsApi	get_metrics	GET /v1/metrics	Get aggregated metrics
PricingApi	list_pricing	GET /v1/pricing	List model pricing

Documentation For Models

• Alert
• CreateAlertRequest
• CreateEventRequest
• ErrorResponse
• ErrorResponseError
• Event
• EventListResponse
• EventResponse
• MetricPoint
• MetricsResponse
• ModelPricing

Documentation For Authorization

Authentication schemes defined for the API:

ApiKeyAuth

• Type: API key
• API key parameter name: Authorization
• Location: HTTP header

Author