Ravi Raushan

@CommandCodeAI Last time when you brought something for free, it wasn't usable at all, continuous server error.

MiniMax M3 is now FREE in Command Code! We're partnering up with MiniMax. One of the best open models. LIVE NOW • all subscribers $1 Go, Pro, Max, Ultra • June 15-17 till capacity lasts HOW $ npm i -g command-code $ cmd /model MiniMax M3 (FREE) What are you building?

@nahid_pro09 5M tokens are very less, it will be exhausted in few prompts.

DeepSeek just dropped 5M FREE tokens — no credit card, no gimmicks😳 If you’re still paying for baseline LLM access to test your apps, you’re burning cash. DeepSeek is currently the hottest model in the space, and they’re letting developers test their infrastructure for free. what you get for $0: -5M free tokens on signup -No credit card required to start -Opt-out settings for data privacy (training-prompt exclusion) -30-day window to build and test before moving to pay-as-you-go -what you can build right now: -High-reasoning AI coding assistants -Custom R1-powered applications -RAG pipelines for private data -Complex agentic toolchains that actually think why this matters: >most developers are locked into expensive provider tiers >this is perfect for prototyping, benchmarking, and local dev >gives you the runway to prove your concept before hitting the API bill how to get started (1 min): ->go to the DeepSeek platform ->sign up with your email ->verify your account ->grab your API key and start prompting important: >5M tokens expire after 30 days — use them or lose them >perfect for testing the limits of R1 reasoning >community-vetted, widely used in the open-source ecosystem >keep your API keys secure (never commit them to public repos) >don't wait for your trial to end >start building with DeepSeek for $0 while everyone else is still debating costs, you should be shipping bookmark this before payying for extra api link in comment↓

@rachpradhan All the native CLI agents/harness have AST built in. Isn't codeDb doing the same?

Your AI agent burns tokens reading whole files it barely needs. We are releasing codedb v0.2.5825, which reads the exact symbols, callers, and lines instead. Up to 98% fewer tokens. Same answers. Fewer per trajectory. Faster than ever. Use it w Claude Code/Codex/Cursor/Devin

@anshrathodfr Did you try Unity3d?

god is givin me signs that i'll never be a game developer

@MrAhmadAwais @GoogleAIStudio @CommandCodeAI Wow, is it live? Which models are supported?

@GoogleAIStudio shipped 21x cost savings in @CommandCodeAI 18hrs+ of work, weekends are the best time for this.

What are you vibe coding this weekend?

@Maddyy660263 @shokhkarim1212 It looks promising. One question, for scanning vulnerabilities do you use any third party services or you have in house service?

@shokhkarim1212 Building rottenpack.com

Hey builders! 👋 Looking to connect with people building in: 🍽️ SaaS 🚀 Tech 📲 Automation 🧠 AI tools 📱 Product Development 🔥 Web APP 💻 Devs Drop what you're working on 👇 (and your link — I'll check it out)

@priyanshudotsol I have a 8GB RAM MacBook air from 2021, and it's going well.

never buy a 16GB RAM laptop in 2026. you’ll regret it within a week

@LexnLin @kris Is this the domain that was bought for $70 million?

guys, does anyone remember ai.com? what tf is happening with it. I even entered my credit card on this shit, it's been 5months @kris ???

@sin4ch Kotlin for Android & Swift for ios

If you're a mobile dev, I need your help. I have to build a mobile app for work. Which stack would you suggest for best performance & cross-platform compatibility: - React Native + TypeScript (with Expo EAS) - Flutter + Dart - Kotlin for Android, Swift for iOS?

@MrAhmadAwais Could you please share what use cases you are using this model for?

NVIDIA has done it all. This is AWESOME!!

I have been building a VS code extension for JS/TS that shows the output inline in real time.

@thesayannayak Node Express and FastAPI

As a dev, which backend framework do you prefer?

@CommandCodeAI After every 2-3 message, "Error: 429 This model is temporarily at capacity. Please try again shortly." or "Connection Issue. Retrying (attempt 3).. "

Qwen 3.7 Max is now FREE in Command Code. One of the most premium open models! LIVE NOW • for all subscribers $1 Go, Pro, Max, Ultra!! • live June 1st to June 3rd till capacity lasts LFG! $ npm i -g command-code $ cmd /model Qwen 3.7 Max (Free) What will you build?

@MrAhmadAwais @vipulgupta2048 @CommandCodeAI Thanks for the information.

@RaviRaushanWeb @vipulgupta2048 @CommandCodeAI also not 4B, it should do around 600M same as deepseek.

You can now get like 100x more usage on MiMo models on Command Code. MiMo-V2.5-Pro & MiMo-V2.5 are now ~99% off. Command Code $1 Go plan with $10 in credits will effectively stretches to $50 usage now. On all plans and even extra top-ups. Pick from /model and let's go!

@XiaomiMiMo Hi @CommandCodeAI @MrAhmadAwais when can we expect MiMo 2.5 Pro in CommandCode?

🚀 Better inference efficiency, lower costs, broader access. MiMo-V2.5 Series API pricing is now permanently reduced — by up to 99% compared to previous pricing. ✨ Unified pricing across all context lengths. MiMo Token Plans have also been upgraded: • 5–8× more usable tokens at the same price • Simpler and more transparent billing rules 🎁 As a thank-you to current users, all current Token Plan credits will be fully reset. 🎧 MiMo-V2.5-TTS remains free for a limited time. ⏰ Effective May 26 at 6:00 PM PDT. These improvements are powered by continued inference optimization and serving efficiency upgrades across the MiMo stack. 🛠️ We’ll also publish a detailed technical blog on the inference optimizations later — stay tuned.

@deepseek_ai @CommandCodeAI 4x

We are making our discount permanent! 🎉 Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀

@CommandCodeAI @AbdMuizAdeyemo How soon? I am heavily using @CommandCodeAI currently. It's consuming a lot of tokens. I want to see where these tokens are being consumed. And if I can build a custom plugin to fox it.

@AbdMuizAdeyemo Soon.

AI is taking over. AI coding agents are getting powerful, but the workflow around them is still messy. Codex. Claude Code. Gemini. OpenCode. Command Code. I see everyone is running agents now, but very few builders can clearly see cost, context, cache, failure points, and workflow quality. I have decided to start building @talocode to fix that.

@corline0 @MrAhmadAwais @CommandCodeAI I am using deepseek v4 pro, it is performing really well in @CommandCodeAI I think you are using Deepseek V4 Flash, for what tasks you are using it?

Thanks @MrAhmadAwais,its beyond what I imagined for $1 could give me this many tokens. DeepSeek in @CommandCodeAI behaves exactly like Claude and follows my instructions perfectly. you should introduce a feature like who ever consume the full 4x stretch will get the reward 😆

@0xBossmang @MrAhmadAwais How did you get banned?

@MrAhmadAwais Any plan on unbanning me? Haha!

Command Code is scaling super fast. As Anthropic raises prices, developers are switching to open-source models, and they're not looking back. We're adding thousands of new devs every day, the community is growing, and the Discord feed is pretty lit. Big ships coming next week!!