Skip to main content

A Python package for seamless multi-LLM routing, observability, and LLM-agnostic integration.

Project description

    Frosty AI is a Python package for seamless multi-LLM (Large Language Model) routing, observability, and management.
    
    Frosty empowers developers and organizations to remain LLM-agnostic, enabling seamless integration, management, and switching between various LLM providers without vendor lock-in. 
    With Frosty, you can:
    
    - Flexibly integrate with multiple LLM providers like OpenAI, Anthropic, and Mistral.
    - Future-proof your applications by easily switching to new or better-performing models as they become available.
    - Optimize costs by choosing models based on performance and pricing, avoiding vendor lock-in.
    
    For the most up-to-date documentation and usage examples, please visit the [Frosty AI Documentation](https://github.com/brittmmorris/frosty-ai-docs).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

frosty_ai-1.1.tar.gz (8.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

frosty_ai-1.1-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file frosty_ai-1.1.tar.gz.

File metadata

  • Download URL: frosty_ai-1.1.tar.gz
  • Upload date:
  • Size: 8.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for frosty_ai-1.1.tar.gz
Algorithm Hash digest
SHA256 1861c025e01bfb5606ded971a81fa76afb2da941dfd6c1da71a09fc33f428226
MD5 55c69a8fa0f16f0b904127a484e6d078
BLAKE2b-256 bd08106d72c91496fa2dbca690d53978137dce38daf332fc0e258b45f43234e9

See more details on using hashes here.

File details

Details for the file frosty_ai-1.1-py3-none-any.whl.

File metadata

  • Download URL: frosty_ai-1.1-py3-none-any.whl
  • Upload date:
  • Size: 7.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for frosty_ai-1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 75a23071ee8d65861043007580ddd3eeec13a8181f9dceffa2b38530922653cd
MD5 ada15113b03e05db17c5567277903f15
BLAKE2b-256 b162856afd306632185cae5c9058cffa97ffb4cef9474c31e5deed7e3d9bffc1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page