Command Code retweeted
Ornith-1.5-122B is now live & free in Command Code.
125B params, 262K context, ZDR by default
Open-weight strong and fast agentic coding model
Available for all plans, all subscribers.
🐐
Ornith-1.5-122B is now live & free in Command Code.
125B params, 262K context, ZDR by default
Open-weight strong and fast agentic coding model
Available for all plans, all subscribers.
🐐
Solid ship, looks like an impressive model.
Congrats to team @ornith_ on the launch.
xitter.cf/ornith_/status/2112553…
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
Introducing the Mods Hub for Command Code.
An open-source registry to discover, install, and publish mods for Command Code.
· Add tools, commands, hooks, rules, or build and share your own.
· 30+ mods already live. Time to mod your agent.
Explore and publish your Command Code Mods: commandcode.ai/mods
Command Code retweeted
MiniMax M3.1 Flash (aka Space Bunny) is now live and FREE in Command Code for limited time!
· 1M token context window
· Frontier level coding performance
· Available all plans, all subscribers
Command Code retweeted
⌘ + 🐰 = 🚀
Thanks @CommandCodeAI! M3.1 Flash is free for all subscribers for a limited time.
Command Code retweeted
DeepSeek V4.1 Flash 1017 now live in Command Code
· All DeepSeek 4.1 requests use the latest 1017 version
· Matches Opus 5 level perf at 60x cheaper cost
· Beats Kimi K3 (max) at 10x lower cost
Available across on all plans and api right away.
Statusline is now live in Command Code.
Run /statusline to customize line below your prompt.
Show model, usage, reasoning level, costs, and more. Reorder items and toggle indicators your way.
DeepSeek V4.1 Flash 1017 now live in Command Code
· All DeepSeek 4.1 requests use the latest 1017 version
· Matches Opus 5 level perf at 60x cheaper cost
· Beats Kimi K3 (max) at 10x lower cost
Available across on all plans and api right away.
MiniMax M3.1 Flash (aka Space Bunny) is now live and FREE in Command Code for limited time!
· 1M token context window
· Frontier level coding performance
· Available all plans, all subscribers
MiniMax M3.1 Flash beats DeepSeek V4.1 Flash 1017, GLM 5.3, and Kimi K3 on cowork AutomationBench v1.0.6.
It also scores 73.7% on DeepSWE v1.1, delivering frontier-level coding and engineering performance.
Thanks to team @MiniMax_AI on partnering for their day 0 launch.
Last week in Command Code, a quick recap.
· IDE extensions for VS Code and Cursor
· DeepSeek V4.1 Flash ($80 usage in $10 GOAT)
· GLM 5.3 Flash ($80 usage in $10 GOAT)
· Ling 3.1 Flash ($100 usage in $10 GOAT)
· Cat Jam (new free stealth model)
· Beam 1.0 (new free model)
· Gemini 4 Argon (latest from Google)
· Muse Wonder (latest from Meta AI)
· Codemode for parallel tasks & MCP heavy contexts
· 52+ new updates, improvements, fixes in desktop app
This week, we shipped 52 updates, improvements, and fixes to make the Command Code desktop app faster and better.
• Save state: 755ms → 12ms (63x faster)
• Save freezes: 833ms → 22ms
• Project switching freezes: 923ms → 79ms
• Chat navigation freezes: 905ms → 41ms
• Startup: 4.3s → 2.6s
Plus Agent Todos, new models, and much more.