OpenRouter

5K posts

OpenRouter banner
OpenRouter

OpenRouter

@OpenRouter

The largest LLM marketplace. 500+ models (incl. 50+ free), the best prices, explorable data, private chat, & a unified API. https://t.co/qJG5mKrQ6j

شامل ہوئے Temmuz 2023
378 فالونگ114K فالوورز
پن کیا گیا ٹویٹ
OpenRouter
OpenRouter@OpenRouter·
Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇
OpenRouter tweet media
English
681
1.7K
14.6K
5.8M
OpenRouter ری ٹویٹ کیا
Jerry Liu
Jerry Liu@jerryjliu0·
This is an insane release from OpenRouter, and not just because it's perfect timing. It shows that frontier models alone do not own all the points on the cost-accuracy Pareto curve for knowledge work tasks; in fact they may not be on the Pareto curve at all. The Pareto curve may be defined by a mixture of models, which any independent third-party (e.g. an AI startup) has access to but the model labs do not. It's also surprising because this feature seems extremely horizontal and is not even well-tuned for a specific task. You can prompt the Fusion API with anything. This just means that for any given workflow subset, there's even greater alpha to exploit, by hillclimbing a task-specific benchmark. The more specific the workflow, the more hillclimbing you can do. This should be pretty obvious with a practical example - if you're trying to automate invoice reconciliation at scale, you can be orders of magnitude cheaper and more reliable than "raw" Claude by tuning an agentic workflow with a mixture of models for document extraction, line-item validation, and contract matching. That alpha is what's exploitable by any company out there that's not a frontier lab.
OpenRouter@OpenRouter

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

English
33
20
285
62.4K
keeran
keeran@keeran·
Not seeing a lot / enough about this Fusion implementation on @OpenRouter . Really sounds like the future, or a significant part of it. I’ve done spark -> gpt vs opus -> execplan for gpt loops plenty of times. All the time. It should be automatic.
English
1
2
4
548
OpenRouter
OpenRouter@OpenRouter·
New Free capacity on OpenRouter, served by @eigenlabs's Darkbloom: gpt-oss-20b and Gemma 4 26B Start using the models today ↓
OpenRouter tweet media
English
7
13
212
18.3K
OpenRouter
OpenRouter@OpenRouter·
Sneak peak of the new multimodal Rankings page 👀 Google's Veo 3.1 climbing the video leaderboard
OpenRouter tweet media
English
3
10
160
10.4K
Shashank Goyal
Shashank Goyal@shashankgoyal95·
Le chaton fat is now #1 on OpenRouter! Need to urgently fix our axes!
Shashank Goyal tweet media
English
29
31
865
37.6K
OpenRouter ری ٹویٹ کیا
Alex Atallah
Alex Atallah@alexatallah·
If you're a researcher looking to: → conduct rigorous studies on how multiple models can outperform the frontier → leverage data from the largest LLM marketplace (150+ trillion tokens processed per month) ... DM me with your work! We have an exciting role coming in the future, but might fill it opportunistically.
OpenRouter@OpenRouter

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

English
26
22
304
61K
OpenRouter
OpenRouter@OpenRouter·
Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇
OpenRouter tweet media
English
681
1.7K
14.6K
5.8M
OpenRouter
OpenRouter@OpenRouter·
Note: we have only evaluated one deep research benchmark so far, which did not include long-horizon tasks. Fable's long-horizon abilities were extremely impressive, and it calls for future work to benchmark both on long-horizon tasks.
English
11
1
364
72.6K
Jeremy
Jeremy@JeremyD513·
@jjacky @OpenRouter Fusion in the api? Is that available and I can't find it or not yet?
English
1
0
1
103
jacky
jacky@jjacky·
what would you like to see next in @OpenRouter ? what doesn't work well for you? what is causing you friction? what do you hate about it? what's stopping you from recommending or to your friends/coworkers? we're always trying to improve, drop em all below 👇🏻
English
3
1
3
430
Willy Drucker
Willy Drucker@WillyDrucker·
@OpenRouter I believe the results! Built an extension for VS Code that allows Claude and Codex to iterate back and forth and the results are mind blowing.
English
16
4
394
59.2K
OpenRouter
OpenRouter@OpenRouter·
@IkeVictor Cost comparisons were performed including cache hits
English
1
0
212
43.6K
OpenRouter
OpenRouter@OpenRouter·
@YashasGunderia We ran these benchmarks earlier in the week, before Fable was taken down
English
3
1
332
42K
Yashas
Yashas@YashasGunderia·
@OpenRouter But fable is not available anymore
English
3
0
33
45.2K
OpenRouter
OpenRouter@OpenRouter·
This month is, unsurprisingly, Cost Reduction Month. In our data from the last 3 yrs, we commonly see major cost crunches right after the latest breakthrough. We'll ship major features to help you cut inference costs at least once a week, starting with today. Running list 👇
OpenRouter@OpenRouter

New server tool: Advisor Let smaller models consult a higher-intelligence "advisor" model. Helps them escape doom loops, and helps you migrate to cheaper models! 🧵

English
8
21
312
53.1K