OpenCode

MiMo-V2-Pro and MiMo-V2-Omni are now free in OpenCode many of you have tried them in stealth - Hunter Alpha and Healer Alpha. Mystery solved worth mentioning - MiMo-V2-Pro: - ~1T params - 1M context - optimized for coding

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

In the next release of OpenCode, github copilot ENTERPRISE login will finally work properly

MiniMax M2.7 available in Go - Better at complex tasks over M2.5 - Fast - give it a plan and it runs with it - Self-evolution - do a task > check results > fix mistakes > try again

Zen × GPT-5.4 Mini / Nano - Both more expensive than prev gen - Mini is priced about the same as GLM5 and Kimi K2.5 - Nano is about 30% cheaper than MiniMax M2.5

To show this off I slopforked the @opencode server so it runs entirely inside a @CloudflareDev Durable Object. No servers. No containers. Hibernates when idle. Try it: opencode attach opencode-do.southpolesteve.workers.dev Code: github.com/southpolesteve…

I'm heading to @NVIDIAGTC next week Perfect timing with the release of Nemotron 3 Super which you can use with @opencode DM me to meet up

NVIDIA's new open source model is now free on OpenCode Zen Nemotron 3 Super is a mid sized model that is - fast - fully open source - 1M context

Zen × MiMo V2 Flash - free this week we've been seeing ppl pair GLM-5 / K2.5 for planning, and a fast model like M2.5 for implementation MiMo V2 Flash is very fast try it and let us know how it performs

Now in @opencode desktop.

stupid sexy composer

in opencode 1.2.18 we believe we solved the issue where processes would hang in the background in many terminals when you close the tab it sends a SIGHUP that wasn't being handled by our runtime automatically so had to manually handle it

I've been using 5.4 for a few weeks now and here are some loose thoughts: I had 5.4 early and you didn't ha ha ha ha h ah ah ah ah haaaaaaa ha h aha ha haaaaaaa

using 5.3-codex-spark inside of @opencode natively has been AMAZING try it out in opencode zen now!

Zen x GPT-5.3-Codex-Spark - fast - very fast - text only - 128K context first drop from the OpenAI x Cerebras collab - link in comment

We looked at the OpenCode Go usage and decided to increase its limits by 3x Learn more:

My submission to be the next @opencode CEO. thank you for your consideration