
Toven
7.4K posts

Toven
@pingToven
provider operations manager @openrouter. opinions my own. aka tomas. 🇦🇷🇦🇷🇦🇷
vibe/acc Katılım Ekim 2021
3.6K Takip Edilen5.7K Takipçiler
Sabitlenmiş Tweet

a few weeks ago i transitioned from IC & wearer of many hats to leading the inference provider operations team at @OpenRouter. super excited to focus my efforts and scale the team responsible for bringing you more models, providers, and modalities 🫡
English
Toven retweetledi

why did this vaguepost get me like 60 new followers? seems silly
thanks for 5700 tho
Toven@pingToven
keep an eye on the openrouter site today
English
Toven retweetledi

@OpenRouter goes hard
hard to convey optionality more cleanly than “OR”
English

@pingToven Toven can i get one of the hoodies/shirts. I absolutely would love to rep openrouter lmao
English

I think i do have to keep my current x banner tho sorry gang
OpenRouter@OpenRouter
OpenRouter has a new look. As we’ve grown into the infrastructure powering the intelligence era, our brand needed to evolve too. Built on clarity, precision, and purpose. For developers. For enterprises. For everyone turning intelligence into impact.
English

@lillian_ma_ these bloomberg interviews are almost always scams if that helps.
accounts will be newly verified, and if you scroll back far enough in post history will be very obvious the account has been hacked and taken over
English

13.2M MAU
168,435 active Go subscribers
dax@thdxr
forgot to do this for a bit june was 13,200,000 monthly actives
English

@kitlangton @anderslie @opencode @rekram11 lmk if you guys have thoughts on how we should expose this via openrouter api, we have the data
English

@anderslie @opencode Yeah! If we have that information about the provider/model we can squash everything back into the prompt. I’ll look into this :)
English

One feature I got to implement in @opencode 2.0 was allowing for HOT CONTEXT¹ without busting the cache.
Here's me explaining how it works ↓
¹ ⁿᵒᵗ ᵃ ᵗᵉʳᵐ
dax@thdxr
if you want to help beta test OpenCode 2.0 v2.opencode.ai - data in separate db which we might wipe - stuff will be broken - use /report to send us issues - v1 plugins won't work, v2 api not final there is a built in skill that you can ask for basically anything
English









