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

Openrouter Fusion API

openrouter.ai

Post reply on HN
Print view View original

21–30 of 98 posts

Re: Openrouter Fusion API

#21

Post by galsapir »

michaelbuckbee wrote: post #11

I ran a quick eval to see what this looks like qualitatively vs just calling Opus 4.7 or GPT 5.5 directly. As expected, Fusion was 7x slower and 4x the cost. This isn't a knock against it, just that it I think this places Fusion into a "use it only when you need it" category. https://3fpi5avcqq.evvl.io/

yeah its really counterintuitive i think; i.e, getting the right framework and structure for this to work probably isn't trivial, models really hate playing well together. i wonder how their version would fair in real world use.

Re: Openrouter Fusion API

#22

Post by maccam912 »

rektlessness wrote: post #18

I tried OpenRouter Fusion with the budget model option but swapped out DeepSeek v3.2 for DeepSeek V4 Pro. The results weren't that bad. An interesting take on quorums for sure. However I did notice a tool call to Claude Opus 4.8 for 1168 - 237 tokens, and $0.0118 cost, which I cannot account for because Opus was not in my selection and only revealed in logs. Strange.

Same for me! I bet they use opus to synthesize the final answer somehow? Regardless, it was unexpected.

Re: Openrouter Fusion API

#24

Post by _pdp_ »

You could easily distribute the same task to 5 subagents that are specifically programmed to do as best as they can based on their scope and merge the results into a single coherent response.

That is more or less the same thing.

I am not sure who is the intended user of this fusion api as with all things prompt + model matter.

Re: Openrouter Fusion API

#25

Post by vidarh »

_pdp_ wrote: post #24

You could easily distribute the same task to 5 subagents that are specifically programmed to do as best as they can based on their scope and merge the results into a single coherent response. That is more or less the same thing. I am not sure who is the intended user of this fusion api as with all things prompt + model matter.

People who don't want the hassle. A lot of Openrouters selling point is removing hassle, and providing things like this can move them up the value chain for people who aren't very cost sensitive and are happy to pay to get better outcomes without having to do the work themselves.

Re: Openrouter Fusion API

#26

Post by bsenftner »

I'm sure many have made something like this, I've done a few. I've found simply submitting one's prompt to multiple models to be kind of pointless. You're just going to get statistical noise from the variances in their training methods, as they are all training on pretty much the same data.

I get significantly better results by pre-prompting each LLM (they can be the same LLM too, just another instance), I pre-prompt them to approach from a different perspective. Basically, I create expert personas that each believe they are someone of a different career, different intellectual perspectives, and then that generates a real debate between experts.

Re: Openrouter Fusion API

#27

Post by Oras »

bsenftner wrote: post #26

I'm sure many have made something like this, I've done a few. I've found simply submitting one's prompt to multiple models to be kind of pointless. You're just going to get statistical noise from the variances in their training methods, as they are all training on pretty much the same data. I get significantly better results by pre-prompting each LLM (they can be the same LLM too, just another instance), I pre-prompt…

Agree, and I see opus and Gemini pro as “quality” on openrouter fusion, this would be super pricy if the prompts are dynamic and not optimised for caching.

I would love to hear why they have created it, what was the business case, what this is going to serve? As you said, this is pretty easy to replicate

Re: Openrouter Fusion API

#28

Post by jiaosdjf »

dsl wrote: post #16

Heh. I built "Fusion" a few months ago as an MCP using OpenRouter. The idea was to give Claude a "panel of experts" to go talk to when it got stuck. After extensive testing and benchmarking I discovered that when you ask one model to judge another's response you don't actually get a better answer. You are just asking it "how closely does this resemble the answer you would have given me." Additional rounds and all the…

But.. but I told the LLM that it is an _expert_, is that worth nothing??

Re: Openrouter Fusion API

#29

Post by huflungdung »

dsl wrote: post #16

Heh. I built "Fusion" a few months ago as an MCP using OpenRouter. The idea was to give Claude a "panel of experts" to go talk to when it got stuck. After extensive testing and benchmarking I discovered that when you ask one model to judge another's response you don't actually get a better answer. You are just asking it "how closely does this resemble the answer you would have given me." Additional rounds and all the…

[dead]
Post reply on HN