Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Smart model routing directly in Claude, Codex and Cursor

github.com

Post reply on HN
Print view View original

91–100 of 127 posts

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#91

Post by matt_d »

adchurch wrote: post #81
matt_d wrote: post #73

Looks interesting! Out of curiosity, how does it compare with vLLM Semantic Router? For reference: https://vllm-semantic-router.com/ https://github.com/vllm-project/semantic-router vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models, https://arxiv.org/abs/2603.04444 https://github.com/vllm-project/semantic-router For instance, does it offer similar algorithms: - vllm-sr/auto: efficient…

Good questions. From what I can tell, vLLM semantic router is more optimized for one-off prompt/response workflows rather than agentic coding (I don't think it's cache aware). As another commenter ( https://news.ycombinator.com/item?id=48689994 ) pointed out, for one-off requests, I think it makes more sense to lock to one model whose behavior you understand very well. For dynamic requests like the ones going to a co…

[flagged]

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#92

Post by ValentineC »

devmor wrote: post #53
adchurch wrote: post #21

Earlier quoted context omitted.

Yeah that's a really interesting point, tbh I think the more relevant variable here is the harness you're using rather than the specific model? i.e. GPT 5.5 in the Claude harness behaves a lot more like Claude than Codex if that makes sense. Hard to quantify this ofc but that's what I've felt vibes wise from using this for the last month.

I have the same general feeling as well. Like you, I can’t prove it’s not just personal feeling - but e.x. Opus via Copilot CLI behaves entirely different than Opus via Claude Code, which behaves differently than Opus via OpenCode or Pi.

I have the same feeling. I've been trying Claude Code directly ever since Copilot nerfed their request-based system, and Opus just seems to perform "better" in Claude Code.

It's also possible that it's the 1m context versus the 200k context (Copilot's limit) doing some of the work here.

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#93

Post by ValentineC »

nativeit wrote: post #87

This would have been neat back when I could afford enough tokens to even set it up properly. Now I’ve had to increase my GH Copilot subscription just to cover the bare minimum updates to a few websites every month, and I no longer do any test driving, or even recreational coding projects. I don’t have hundreds of dollars a month to plow into these products, so I’m rationing use, looking for better local options, and…

> Now I’ve had to increase my GH Copilot subscription

Maybe you should move away from a subscription that started charging by the token instead of by the request?

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#94

Post by ValentineC »

adchurch wrote: post #76
notatoad wrote: post #74

Is this talking to claude code, or to claude api (and paying api rates)? programatically routing requests through claude code sounds like a good way to get banned, just like the opencode and openclaw users.

If you have a Claude sub with subsidized usage we use that. If not you pay API prices.

Is that because you start by running it inside Claude Code? I don't see how Claude would allow any other harness to call them for their subscription, after all that OpenClaw hullabaloo.

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#96

Post by jmalicki »

adchurch wrote: post #79
jmalicki wrote: post #60

> with no noticeable differences in quality or velocity. Have you done any A/B tests on this with evidence? (That's one thing I'd be very interested to see for claims like this - I'm not necessarily doubting you, it just seems like it could be useful to understand claims of quality/efficiency)

Great question! Our main product quantifies engineering productivity & quality so I think we're uniquely qualified to answer this - our velocity has only gone up and our quality (bugs introduced, code turnover) has not budged per our own analysis.

> our velocity has only gone up

That is super curious - using more low quality cheaper models increased your velocity? My prior would have been slightly reduced velocity but massive reduction in token costs made it worthwhile.

Is that due to the faster inference time?

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#97

Post by hmokiguess »

matt_d wrote: post #73

Looks interesting! Out of curiosity, how does it compare with vLLM Semantic Router? For reference: https://vllm-semantic-router.com/ https://github.com/vllm-project/semantic-router vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models, https://arxiv.org/abs/2603.04444 https://github.com/vllm-project/semantic-router For instance, does it offer similar algorithms: - vllm-sr/auto: efficient…

I tried Sakana Fugu, boy is it hungry ... it blows up tokens like nothing I have ever seen. Not that impressed with the results I got from it however if I'm being honest. Now I'm bought into their buy 1 get 2nd month free so will keep trying it but may cancel after.

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#99

Post by adchurch »

jpease wrote: post #90

Is this noticeably different than having your implementation planning phase break a larger task into sub-tasks, and recording the ideal model to use based on scope as part of the task definition?

Yes because it's a model explicitly trained to make model selections! Opus probably doesn't have a great idea of when to send a task to DeepSeek vs. to Sonnet, for example.

Re: Show HN: Smart model routing directly in Claude, Codex and Cursor

#100

Post by dools »

nativeit wrote: post #87

This would have been neat back when I could afford enough tokens to even set it up properly. Now I’ve had to increase my GH Copilot subscription just to cover the bare minimum updates to a few websites every month, and I no longer do any test driving, or even recreational coding projects. I don’t have hundreds of dollars a month to plow into these products, so I’m rationing use, looking for better local options, and…

I've been building a reasonably complicated project over the past week using deepseek v4 pro almost exclusively (a couple of k2.7 and 1 session with gpt5.5 to re-assess some architectural questions). Deepseek is super capable though if you're a coder. I don't even write "code" but I can tell when it's doing something dumb and tell it how to do it better, but other than that I'm not micro managing it or using it "just for auto complete" or whatever.

And it is SO fucking cheap.

Post reply on HN