LiteLLM

“There's nothing novel about being internally compromised which you've demonstrated two times in a row”

“We work hard on improving the stability and security of LiteLLM on each release.”

“LiteLLM has one of the nicest programmer UX to use but this is not good at all.”

“this seems systemic - if three developers had their keys stolen, it implies the real problem is elsewhere”

“after the last supply chain attack, people would be smarter than ship things with LiteLLM”

“Announcing that there's a private enterprise repo you should be paying for if you don't want a credential stealer”

“Currently using litellm and its been pretty solid for me”

“It can issue virtual keys, so provider API keys never go near the sandbox”

“this de-bloat has 2k LOC and specifies its only two deps ones most people want as deps”

“2,900 LOC is still way too much for handling a remote API call, especially in a high level language such as Python”

“the latency it contributes to the end-to-end AI processing has been not noticeable in practice for our users”

“I like the API, and since this is open source I will copy the design with attribution”

“This readme is better than most readmes. However they came to making it, it's clearly working”

“This is a cool project, and the idea of using LLMs to selectively extract features from open source projects is an interesting concept.”

“LiteLLM is bad. Shit performance, buggy, and none of it surprising if you look at the tangled mess that is their codebase.”

“The approach substantially reduce the amount of data leak, and errors.”

“You might have luck converting between standards using litellm's proxy.”

“This is great news (the Rust announcement, not me filling out the form)!”

“LiteLLM has the most mature, and broadest range of unified api's x providers.”

“if you run a proxy like LiteLLM, you can configure it to send requests to different api endpoints on the back end”

“LiteLLM is a great option if you're comfortable running infrastructure.”

“allows to set the budget per day/week, and it's free”

“middleware like LiteLLM that also monitors usage so that your coding frenzy doesn't turn into a $20k bill”

“Just use litellm or any-llm if you want to convert to OpenAI format”

“Incredibly poor performance, riddled with serious bugs and to be honest devs that don't seem to understand them.”

“LiteLLM had a major security incident recently, and often isn't actually that useful an abstraction”

“I literally pressed sync dependencies button 1 minute after the malware version was removed.”

“I was able to create Virtual Keys on the free version with no issues.”

“the abstraction layer that was supposed to save you time just cost an unknown number of people every credential on their machine”

“litellm==1.82.8 is the compromised package. It contains litellm_init.pth which spawns malware on every Python startup.”

“LiteLLM made it much easier for developers to use it rather than reinventing and debugging such nuances”

“There are hundreds of PRs fixing valid issues to your github repo seemingly in limbo for weeks.”

“this library made it easy by making one single API you call”

“everyone who needs to get shit done uses something lighter like the above two”

“Uses LiteLLM for multi-model support (Qwen, Gemini, Claude, DeepSeek)”

“the operational surface wasn't worth it for something that's really just a retry loop with state”

“Then there is LiteLLM and similar that make it even easier”

“LiteLLM is excellent, but its pure-Python HTTP layer adds SDK overhead.”

“litellm does a very good job and it's not a platform middle man, just a python library”

“Cowork + litellm proxy + a local vision LLM should work incredibly well”