Model Request: Mercury 2
https://www.inceptionlabs.ai/blog/introducing-mercury-2
https://x.com/StefanoErmon/status/2026340720064520670?s=20
Reason to add autoregressive LLM performance, but unbelievable speed
https://www.inceptionlabs.ai/blog/introducing-mercury-2
https://x.com/StefanoErmon/status/2026340720064520670?s=20
Reason to add autoregressive LLM performance, but unbelievable speed
Log in to comment and vote
Comments6
White Cucumber
Merged request
Model Request: Mercury
request to add the mercury model to t3 chat as its one of the faster models
https://www.inceptionlabs.ai/
Salmon Jaguar
This would be really cool, since their UI isn't really the best, but I do think that this could be too much work for what it's worth since they'd have to rebuild the model streaming to support this sort of text diffusion… I really hope more diffusion models come to further incentivize the work to support them.
Amethyst Lemon
Please consider this. It is really fast and has a bad UI.
It is cheap and uses openai API
Blue Raccoon
+1 Given this is roughly on par with the new Gemini 3.1 Flash Lite, while being ½ the price on output and faster, it could be a nice and quick search model.