> LiteLLM: While popular, it reimplements provider interfaces rather than leveraging official SDKs, which can lead to compatibility issues and unexpected behavior modifications
with no vested interest in litellm, i'll challenge you on this one. what compatibility issues have come up? (i expect text to have the least, and probably voice etc have more but for text i've had no issues)
you -want- to reimplement interfaces because you have to normalize api's. in fact without looking at any-llm code deeply i quesiton how you do ANY router without reimplementing interfaces. that's basically the whole job of the router.
Both approaches work well for standard text completion. Issues tend to be around edge cases like streaming behavior, timeout handling, or new features rolling out.
You're absolutely right that any router reimplements interfaces for normalization. The difference is what layer we reimplement at. We use SDKs where available for HTTP/auth/retries and reimplement normalization.
Bottom line is we both reimplement interfaces, just at different layers. Our bet on SDKs is mostly about maintenance preferences, not some fundamental flaw in LiteLLM's approach.
Szpadel 3 hours ago [-]
I use litellm as my personal AI gateway, and from user point of view there is no difference if proxy uses official SDK or not, this might be benefit for proxy developers.
but I can give you one example: litellm recently had issue with handling deepseek reasoning. they broke implementation and while reasoning was missing from sync and streaming responses.
chuckhend 3 hours ago [-]
LiteLLM is quite battle tested at this point as well.
> it reimplements provider interfaces rather than leveraging official SDKs, which can lead to compatibility issues and unexpected behavior modifications
Leveraging official SDKs also does not solve compatibility issues. any_llm would still need to maintain compatibility with those offical SDKs. I don't think one way clearly better than the other here.
AMeckes 3 hours ago [-]
That's true. We traded API compatibility work for SDK compatibility
work. Our bet is that providers are better at maintaining their own SDKs than we are at reimplementing their APIs. SDKs break less often and more predictably than APIs, plus we get provider-implemented features (retries, auth refresh, etc) "for free." Not zero maintenance, but definitely less. We use this in production at Mozilla.ai, so it'll stay actively maintained.
amanda99 3 hours ago [-]
Being battle tested is the only good thing I can say about LiteLLM.
scosman 3 hours ago [-]
You can add in it's still 10x better than LangChain
scosman 3 hours ago [-]
Yeah, official SDKs are sometimes a problem too. Together's included Apache Arrow, a ~60MB dependency, for a single feature (I patched to make it optional). If they ever lock dependency versions it could conflict with your project.
I'd rather a library that just used OpenAPI/REST, than one that takes a ton of dependencies.
bdhcuidbebe 9 minutes ago [-]
What is mozilla-ai?
Seems like reputation parasitism.
daveguy 2 minutes ago [-]
It is an official Mozilla Foundation subsidiary. Their website is here: https://www.mozilla.ai/
11 minutes ago [-]
amanda99 3 hours ago [-]
I'm excited to see this. Have been using LiteLLM but it's honestly a huge mess once you peek under the hood, and it's being developed very iteratively and not very carefully. For example. for several months recently (haven't checked in ~a month though), their Ollama structured outputs were completely botched and just straight up broken. Docs are a hot mess, etc.
I focused on making it Langchain compatible so you could drop it in as a replacement. And it offers virtual providers for automatic fallback when you reach rate limits and so on.
nexarithm 3 hours ago [-]
I have been also working on very similar open source project for python llm abstraction layer. I needed one for my research job. I inspired from that and created one for more generic usage.
There is liteLLM, OpenRouter, Arch (although that’s an edge/service proxy for agents) and now this. We all need a new problem to solve
CuriouslyC 4 hours ago [-]
LiteLLM is kind of a mess TBH, I guess it's ok if you just want a docker container to proxy to for personal projects, but actually using it in production isn't great.
can you double click a little bit? many files in professional repos are 1000s of lines. LoC in it self is not a code smell.
otabdeveloper4 2 hours ago [-]
LiteLLM is the worst code I have ever read in my life. Quite an accomplishment, lol.
dlojudice 4 hours ago [-]
> but actually using it in production isn't great.
I only use it in development. Could you elaborate on why you don't recommend using it in production?
honorable_coder 4 hours ago [-]
the people behind envoy proxy built: https://github.com/katanemo/archgw - has the learnings of Envoy but natively designed to process/route prompts to agents and LLMs. Would be curious about your thoughts
wongarsu 3 hours ago [-]
And all of them despite 80% of model providers offering an OpenAI compatible endpoint
ieuanking 4 hours ago [-]
we are trying to apply model-routing to academic work and pdf chat with ubik.studio -- def lmk what you think
why provide link if there is not a single portkey keyword there?
piker 3 hours ago [-]
This looks awesome.
Why Python? Probably because most of the SDKs are python, but something that could be ported across languages without requiring an interpreter would have been really amazing.
Shark1n4Suit 13 minutes ago [-]
That's the key question. It feels like many of these tools are trying to solve a systems-level problem (cross-language model execution) at the application layer (with a Python library).
A truly universal solution would likely need to exist at a lower level of abstraction, completely decoupling the application's language from the model's runtime. It's a much harder problem to solve there, but it would be a huge step forward.
pzo 3 hours ago [-]
for js/ts you have vercel aisdk [0], for c++ you have [1], for flutter/reactnative/kotlin there is [2]
I use Litellm Proxy, even in a dev environment via Docker, because the Usage and Logs feature greatly helps in providing visibility into LLM usage. The Caching functionality greatly helps in reducing costs for repetitive testing.
honorable_coder 4 hours ago [-]
a proxy means you offload observability, filtering, caching rules, global rate limiters to a specialized piece of software - pushing this in application code means you _cannot_ do things centrally and it doesn't scale as more copies of your application code get deployed. You can bounce a single proxy server neatly vs. updating a fleet of your application server just to monkey patch some proxy functionality.
AMeckes 4 hours ago [-]
Good points! any-llm handles the LLM routing, but you can still put it behind your own proxy for centralized control. We just don't force that architectural decision on you. Think of it as composable: use any-llm for provider switching, add nginx/envoy/whatever for rate limiting if you need it.
honorable_coder 4 hours ago [-]
How do I put this behind a proxy? You mean run the module as a containerized service?
But provider switching is built in some of these - and the folks behind envoy built: https://github.com/katanemo/archgw - developers can use an OpenAI client to call any model, offers preference-aligned intelligent routing to LLMs based on usage scenarios that developers can define, and acts as an edge proxy too.
AMeckes 3 hours ago [-]
To clarify: any-llm is just a Python library you import, not a service to run. When I said "put it behind a proxy," I meant your app (which imports any-llm) can run behind a normal proxy setup.
You're right that archgw handles routing at the infrastructure level, which is perfect for centralized control. any-llm simply gives you the option to handle routing in your application code when that makes sense (For example, premium users get Opus-4). We leave the architectural choice to you, whether that's adding a proxy, keeping routing in your app, or using both, or just using any-llm directly.
sparacha 2 hours ago [-]
But you can also use tokens to implement routing decisions in a proxy. You can make RBAC natively available to all agents outside code. The incremental feature work in code vs an out of process server is the trade off. One gets you going super fast the other offers a design choice that (I think) scales a lot better
RussianCow 4 hours ago [-]
You can do all of that without a proxy. Just store the current state in your database or a Redis instance.
honorable_coder 4 hours ago [-]
and managed from among the application servers that are greedily trying to store/retrieve this state? Not to mention you'll have to be in the business of defining, updating and managing the schema, ensuring that upgrades to the db don't break the application servers, etc, etc. The proxy server is the right design decision if you are truly trying to build something production worthy and you want it to scale.
klntsky 3 hours ago [-]
Anything like this, but in TypeScript?
AMeckes 3 hours ago [-]
Python only for now. Most providers have official TypeScript SDKs though, so the same approach (wrapping official SDKs) would work well in TS too.
I’ve been looking for something a bit different though related to Ollama. I’d like a load balancing reverse proxy that supports queuing requests to multiple Ollama servers and sending requests only when a Ollama server is up and idle (not processing). Anything exist?
renewiltord 3 hours ago [-]
In truth it wasn’t that hard for me to ask Claude Code to just implement the text completion API so routing wasn’t that much of a problem.
I didn't even need to click the link to know what this comic was. LiteLLM is great, we just needed something slightly different for our use case.
3 hours ago [-]
mkw5053 3 hours ago [-]
Interesting timing. Projects like Any-LLM or LiteLLM solve backend routing well but still involve server-side code. I’ve been tackling this from a different angle with Airbolt [1], which completely abstracts backend setup. Curious how others see the trade-offs between routing-focused tools and fully hosted backends like this.
I didn’t intend my original comment to be overly-promotional without relevance. I'm genuinely curious about the tradeoffs between different LLM API routing solutions, most acutely as a consumer.
qntmfred 3 hours ago [-]
don't you post links to your own stuff all the time? i don't think their comment was out of line.
Rendered at 22:43:34 GMT+0000 (Coordinated Universal Time) with Vercel.
with no vested interest in litellm, i'll challenge you on this one. what compatibility issues have come up? (i expect text to have the least, and probably voice etc have more but for text i've had no issues)
you -want- to reimplement interfaces because you have to normalize api's. in fact without looking at any-llm code deeply i quesiton how you do ANY router without reimplementing interfaces. that's basically the whole job of the router.
You're absolutely right that any router reimplements interfaces for normalization. The difference is what layer we reimplement at. We use SDKs where available for HTTP/auth/retries and reimplement normalization.
Bottom line is we both reimplement interfaces, just at different layers. Our bet on SDKs is mostly about maintenance preferences, not some fundamental flaw in LiteLLM's approach.
but I can give you one example: litellm recently had issue with handling deepseek reasoning. they broke implementation and while reasoning was missing from sync and streaming responses.
> it reimplements provider interfaces rather than leveraging official SDKs, which can lead to compatibility issues and unexpected behavior modifications
Leveraging official SDKs also does not solve compatibility issues. any_llm would still need to maintain compatibility with those offical SDKs. I don't think one way clearly better than the other here.
I'd rather a library that just used OpenAPI/REST, than one that takes a ton of dependencies.
Seems like reputation parasitism.
I shipped a similar abstraction for llms a bit over a week ago:
https://github.com/omarkamali/borgllm
pip install borgllm
I focused on making it Langchain compatible so you could drop it in as a replacement. And it offers virtual providers for automatic fallback when you reach rate limits and so on.
Github: https://github.com/proxai/proxai
Website: https://proxai.co/
I only use it in development. Could you elaborate on why you don't recommend using it in production?
Why Python? Probably because most of the SDKs are python, but something that could be ported across languages without requiring an interpreter would have been really amazing.
A truly universal solution would likely need to exist at a lower level of abstraction, completely decoupling the application's language from the model's runtime. It's a much harder problem to solve there, but it would be a huge step forward.
[0] https://github.com/vercel/ai
[1] https://github.com/ClickHouse/ai-sdk-cpp
[2] https://github.com/cactus-compute/cactus
But provider switching is built in some of these - and the folks behind envoy built: https://github.com/katanemo/archgw - developers can use an OpenAI client to call any model, offers preference-aligned intelligent routing to LLMs based on usage scenarios that developers can define, and acts as an edge proxy too.
You're right that archgw handles routing at the infrastructure level, which is perfect for centralized control. any-llm simply gives you the option to handle routing in your application code when that makes sense (For example, premium users get Opus-4). We leave the architectural choice to you, whether that's adding a proxy, keeping routing in your app, or using both, or just using any-llm directly.
I’ve been looking for something a bit different though related to Ollama. I’d like a load balancing reverse proxy that supports queuing requests to multiple Ollama servers and sending requests only when a Ollama server is up and idle (not processing). Anything exist?
[1] https://github.com/Airbolt-AI/airbolt