commandcode just launched a $10 plan.
More posts
word is DeepSeek might be jacking up prices soon
. their API already crashed once from the surge. guess they're short on GPUs raising prices to deal with the flood of callers.

9router just got auto vision + audio model routing.
Configure it once. Any non-multimodal model called through 9router now detects vision/audio tasks and silently swaps to a combo model behind the scenes. Reminds me of the vision subagent approach I tried before but this solves it at the API layer. No glue code, no orchestration headaches. My take: models will keep getting narrower. The winning product is multiple specialists stitched together, not one jack-of-all-trades model.

Three $10 plans compared.
Last post I mentioned broker sites for flagship models, where you can get pricing down to about a tenth of list. Still too rich for subagents or anything you run all day. For normal use, unless you're doing development or research, I keep landing on the ~30 tier of Artificial Analysis: deepseek-v4.1-flash. Step up to ~40, which is Kimi K3.1 Pro, and the price goes 10x. For DS itself, these three subscriptions are the cheapest route today. OpenDesign Go says $120 of usage, OpenCode Go and Command Code GOAT say $100. Those aren't the same number though. OpenDesign's $120 is one pool shared by 12 models, with a $10 cap per 5 hours. The other two give DS its own allowance and $20 per 5 hours.

SpaceX quietly trimmed Grok Bot's usage limits this weekend.
A lot of users woke up to find their weekly quota had shot from about 50% to a flat 100%, and they hadn't even touched it. Musk confirmed on X it wasn't a glitch. His words: serving Grok Bot "was unsustainably high relative to revenue." So the thing really does cost a fortune to run. That said, I'm seeing the limits roll back to the earlier version. Yesterday it showed 50% used; today I'm at 30%.
