✨ Feature: Add feature: support setting API key random load balancing

💻 Code: Optimize log display: add error provider name display.

✨ Feature: Add feature: Support that as long as the prefix of the API key exists in the configuration file, the API key is valid.

🐛 Bug: Fix the bug where the embedding URL for GLM and GitHub models is incorrect.

🐛 Bug: The bug where the provider's name, which is purely numeric, was not converted to a string has been fixed.

🐛 Bug: Fix the bug of ZeroDivisionError when the API key does not exist.

🐛 Bug: Fix the bug where GitHub models cannot retrieve the model when the model field is not set.

🐛 Bug: Fix the bug where API initialization throws an error when no API key is present.

✨ Feature: Add feature: support setting rate limit for each model individually

🐛 Bug: Fix the bug where the os module was not imported.

💻 Code: Optimize to reduce unnecessary log output.

🐛 Bug: Fix the bug where the return data type of frequency limit is incorrect.

🐛 Bug: Fix the bug of incorrect function parameters entering the cooldown state.

🐛 Bug: 1. Fix the bug where the closed client cannot be found when closing the request client.

🐛 Bug: Fix the bug where Vercel fails to start successfully.

🐛 Bug: Fix the bug where Vercel fails to start successfully.

🐛 Bug: Fix the bug of incorrect weight allocation

🪞 Frontend: Fixed the bug where the chart size was displayed incorrectly when there was no data.

🪞 Frontend: Add request model statistics bar chart

🐛 Bug: Fix the bug where weight polling did not check if the weight channel conforms to the request model.

Default to all models if model field is not set

✨ Feature: Add support for embeddings model

🐛 Bug: Fix the bug where the model is not persisted to the file after being automatically retrieved.

📖 Docs: Add documentation for serv00 deployment steps.

✨ Feature: Added lottery scheduling algorithm and support for random scheduling algorithm.

🐛 Bug: Fix the bug where the sheet page cannot fully display when there are too many models.

🐛 Bug: Fix the bug where the /v1/models endpoint returns incomplete models

🐛 Bug: Fix the bug where the remote configuration file cannot be parsed.

fix: create ThreadSafeCircularList with correct api list

if api key is invalid, raise except

fix: api could be a list

🐛 Bug: Fix the bug where /v1/models does not work.

✨ Feature: 1. Add support for experimental frontend.

🐛 Bug: Fix the bug where channel responses fail but are replied to normally and are not recognized as a request failure.

🐛 Bug: Fix the bug where using asterisks for api key does not conform to yaml syntax

Refactor: Add support for retrieving all models when the model name is "*"

🐛 Bug: 1. Fix the bug that causes an error when Claude uploads a PNG image.

✨ Feature: Add support for v1/moderations endpoint.

✨ Feature: Add database, count the first character time.

🐛 Bug: Fix the bug where the fixed message for pass-through did not check for generation failure.

🐛 Bug: Fix the bug that treats api.yaml as a folder.

🐛 Bug: Fix the bug where the next channel cannot be automatically switched when an error occurs in non-streaming output for o1-mini and o1-preview.

🐛 Bug: Fix the bug that fails to properly catch httpx.RemoteProtocolError.

🤖 Models: Add support for o1-mini o1-preview model

🐛 Bug: Fix the bug where error codes are not accurately returned to the client.

✨ Feature: Add feature: Support Cloudflare API model

🐛 Bug: 1. Fix the bug of log errors being repeatedly displayed.

✨ Feature: Add feature: Add support for weighted load balancing.

Add feature: support load balancing for multiple keys in a single channel, enabled by default.

Add feature: support OpenAI dall-e-3 image generation