Experiential
Dev tools
model gateway
SHOW HN2026
How HN took it
7 positive, 17 neutral or asking, 0 mixed, 9 critical, out of 33 comments about the project. Thread score +0.01.
Idea: 4 for, 5 againstDocs: 0 for, 2 againstPrivacy: 0 for, 2 againstPricing: 1 for, 0 againstExecution: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Open source and no markup is the right default for a gateway
From 1 comment
Open source and no markup is the right default for a gateway. The caching question above is the one I would want answered before swapping models though.
akshay_akula on HN
Router and model optimization from traffic is a useful differentiator
From 1 comment
Router and model optimization from traffic is the main differentiator
kfallah15 on HN
Objections
Switching models may break cached input token savings
From 2 comments
Could you say more about how caching works? One major advantage of sticking with a single model is saving money on cached input tokens. I'd imagine if you swap between a bunch of…
Areibman on HNOpen source and no markup is the right default for a gateway. The caching question above is the one I would want answered before swapping models though.
akshay_akula on HN
Telemetry is on by default despite open source claim
From 1 comment
Your GitHub readme says telemetry is on by default
aHumbleUser on HN
Small team could reproduce it quickly
From 1 comment
impressive only if using pre-gpt era assumptions about saas/products/software. unfortunately a small team can reproduce it in two months, which greatly lowers value of it. we, as…
rdslw on HN
Requests
Explain how caching works
From 2 comments
Could you say more about how caching works? One major advantage of sticking with a single model is saving money on cached input tokens. I'd imagine if you swap between a bunch of…
Areibman on HNOpen source and no markup is the right default for a gateway. The caching question above is the one I would want answered before swapping models though.
akshay_akula on HN
Support semantic caching at the router level
From 1 comment
What online signal recalibrates simulated rankings against actual task success? Also do you have a plan to support semantic caching at the router level?
sangwook on HN
Questions
How does the opt-in model training from traffic work
From 1 comment
> and use your traffic to (opt in) train you a model. Is there more info on this? I'm curious exactly what it is. Is it fine-tuning/LoRA on some base model? Don't cloud providers…
d2p on HN
Why text world models
From 1 comment
why text world models? Is this backed by any evidence or did you find it to be good in practice?
carloslfu on HN
Alternatives named
LiteLLM
From 2 comments
Congrats on the launching of your product. I will be taking it for a spin to compare it with these other products that seem to be competing directly with what you have to offer:…
mongrelion on HNI have not tried it yet. Is it similar to LiteLLM? If so, what sets it apart?
cheema33 on HN
Bifrost
From 1 comment
Congrats on the launching of your product. I will be taking it for a spin to compare it with these other products that seem to be competing directly with what you have to offer:…
mongrelion on HN
GoModel
From 1 comment
Congrats on the launching of your product. I will be taking it for a spin to compare it with these other products that seem to be competing directly with what you have to offer:…
mongrelion on HN
vLLM Semantic Router
From 1 comment
A part of me wishes the open source community would focus making research and industry-backed initiatives like the vLLM Semantic Router rock solid. Then I'd spend less time every…
nejch on HN
ngrok AI gateway
From 1 comment
You guys should look into ngrok ai gateway. We have some small models running on local hardware that we tried to use but it was too painful. Just wanted to not waste all the…
akshay_akula on HN