MiMo-V2.5-Pro & MiMo-V2.5 are now ~99% off on Command Code. This is like 100x more usage! Input, output, and cache pricing are all lower. Works on every plan + extra top-ups. Pick the /model and go! Our $1 Go plan with $10 in it is perfect for this. Let's go!

@CommandCodeAI So cheaper than deepseek?

@CommandCodeAI I purchased the same plan but only received $10. Also, token usage is extremely high, even for small tasks it uses 40× more than required. Other CLI tools use far fewer tokens. Bug 🐞 or intentional? 🤔

Shop luxury fashion finds at Amazon 👜

@CommandCodeAI Hey man i really like the art style of your posts can you tell me what its called?

@CommandCodeAI gotta give it to Deepseek for changing the game, now all these Chinese models are going to be way cheaper

@CommandCodeAI Was asking for this as news broke out for price cut great its available now , lets see how this works in this harness

@CommandCodeAI Is this PR from you guys? github.com/NousResearch/h…

@CommandCodeAI But for your actual usage, the math is harsh. Your known ship profile is about 82,000 requests/month, with roughly 1.6B input tokens, 25M output tokens, and 3.8B cache-read tokens/month. At Command Code’s MiMo-V2.5-Pro token rates, that estimates to about $730/month if your token

@CommandCodeAI I've tried subbing with multiple cards but i keep getting an error "unable to autenticate payment method". Any help?

@CommandCodeAI Hey why not allow api access to go users also?? Why only for pro nd above.

@CommandCodeAI It's kinda slow, it took up about 10mins just to update a CHANGELOG.

Meet Go. Gopuff's AI shopping genius, co-developed with SpaceXAI. Just say what you need. It's already on its way. Try Go free today in the Gopuff app.

@CommandCodeAI So like in 1 dollar we were getting around 40 dollar usage of deepseek so how much would this be for Mimo v2.5 pro

@CommandCodeAI you will do the same fixes like deepseek or dont need?

@CommandCodeAI So is this like hermes on steroids?

@CommandCodeAI neXt is Kimi 🥳

@CommandCodeAI the token consumption is unreal with any of your models

@CommandCodeAI You guys are handsome

@CommandCodeAI @Teknium can we use command code as a provider in hermes ?

@CommandCodeAI Awesome

Bring ideas to life with Grok Imagine. Introducing the fastest video and image generation experience.

@CommandCodeAI why is so slow mimo-v2.5-pro

@CommandCodeAI when we will get /goal ? :P

@CommandCodeAI good news

@CommandCodeAI That level of price compression basically changes how people experiment with models 👀 When input/output/cache all drop together, it stops being “optimize usage” and becomes “just build and iterate.” Going to see a lot more high-volume workflows emerge from this ⚡

@CommandCodeAI Garbage models

@CommandCodeAI I'm using opencode go and they didn't do that, I think cmd my really be better

@CommandCodeAI time to run cmd update...