MiniMax M2.5 released: 80.2% in SWE-bench Verified
1–10 of 60 posts
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#2Really looked forward to this release as MiniMax M2.1 is currently my most used model thanks to it being fast, cheap and excellent at tool calling. Whilst I still use Antigravity + Claude for development, I reach for MiniMax first in my AI workflows, GLM for code tasks and Kimi K2.5 when deep English analysis is needed.
Not self-hosting yet, but I prefer using Chinese OSS models for AI workflows because of the potential to self-host in future if needed. Also using it to power my openclaw assistant since IMO it has the best balance of speed, quality and cost:
> It costs just $1 to run the model continuously for an hour at 100 tokens/sec. At 50 tokens/sec, the cost drops to $0.30.
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#3Really looked forward to this release as MiniMax M2.1 is currently my most used model thanks to it being fast, cheap and excellent at tool calling. Whilst I still use Antigravity + Claude for development, I reach for MiniMax first in my AI workflows, GLM for code tasks and Kimi K2.5 when deep English analysis is needed. Not self-hosting yet, but I prefer using Chinese OSS models for AI workflows because of the potent…
!!!!!!
Incredibly cheap!!!!!
I'll have to look for it in OpenRouter.
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#4And it's available on their coding plans, even the cheapest one.
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#5With the GLM news yesterday and now this, I'd love to try out one of these models, but I'm pretty tied to my Claude Code workflow. I see there's a workaround for GLM, but how are people utilizing MiniMax, especially for coding?
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#6With the GLM news yesterday and now this, I'd love to try out one of these models, but I'm pretty tied to my Claude Code workflow. I see there's a workaround for GLM, but how are people utilizing MiniMax, especially for coding?
anything with an open ai compatible endpoint can have claude code router put in front of it afaik https://github.com/musistudio/claude-code-router
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#7Really looked forward to this release as MiniMax M2.1 is currently my most used model thanks to it being fast, cheap and excellent at tool calling. Whilst I still use Antigravity + Claude for development, I reach for MiniMax first in my AI workflows, GLM for code tasks and Kimi K2.5 when deep English analysis is needed. Not self-hosting yet, but I prefer using Chinese OSS models for AI workflows because of the potent…
!!!!!! Incredibly cheap!!!!! I'll have to look for it in OpenRouter.
For the moment is free in Opencode, if you want ot try it.
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#8With the GLM news yesterday and now this, I'd love to try out one of these models, but I'm pretty tied to my Claude Code workflow. I see there's a workaround for GLM, but how are people utilizing MiniMax, especially for coding?
I use Opencode, when the model is free for the moment. I have not used Claude Code so I cannot compare.
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#9Wish my company allowed more of these LLMs through Github Copilot, stuck with OpenAi, Anthropic and Google LLMs where they burn my credit one week into the month
Re: MiniMax M2.5 released: 80.2% in SWE-bench Verified
#10With the GLM news yesterday and now this, I'd love to try out one of these models, but I'm pretty tied to my Claude Code workflow. I see there's a workaround for GLM, but how are people utilizing MiniMax, especially for coding?
you can use Claude Code with these models. You just need to pass the right env vars. Have a look at the client setup guide on z.ai