Pinned Tweet
DeepSeek dropped V4.1-Flash-1017 on Saturday. It's been in Qoder since day one.
Now it's FREE through Oct 24. 0.0x credits for free and paid users. Just select it and go.
Community Boost is live.
Join to claim 1,024 SOTA Credits for Sonus, then boost once a day with the community to unlock more
20K boosts → 2,048 30K boosts → 3,072 50K boosts → 4,096
Pro and above join automatically. Free users can apply. Claim by Oct 30, 23:59 UTC+8.
Double Credits on your first subscription — plus extra Credits when you renew.
Starting Oct 21 at 00:00 (UTC+8), every Personal plan renewal earns a bonus.
Lite +500 · Pro +1,000
Pro+ +2,000 · Ultra +3,000
Lite plan also includes:
- The full agent harness: Goal, Browser Use, Computer Use, Cloud Agents and more
- One credit pool across Qoder Desktop, IDE, JetBrains and CLI
- Skills, hooks, MCP and BYOK
- New Qwen, DeepSeek, Zhipu, Kimi and MiniMax models on day one
Card, PayPal or Alipay.
qoder.com/pricing
Ends Oct 24, 23:59 (UTC+8), then back to 0.1x.
Get Qoder👇
qoder.com
Space Bunny just landed in Qoder.
MiniMax M3.1 Flash is available from Day 0 across the Qoder suite. Switch models and put it to work.
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
Day-0 support: MiniMax M3.1 Flash is now in Qoder.
Yes, it's the model that ran anonymously as Space Bunny and processed 200T+ tokens. Now it's unmasked and ready in your model picker.
Nearly 3× faster, 70% cheaper, and stronger at agentic tasks, coding and Computer Use.
No endless prompt tuning. State your goal, stay in control, and turn ideas into working code.
Give it a try if you’re a builder 🛠️
Been testing @qoder_ai_ide over the past few weeks and the agentic approach feels noticeably different from most AI coding tools I’ve tried.
Instead of going back and forth with prompts, you can describe the end goal and let it plan the steps, write the code, and keep moving forward while you stay in control of the direction. It reduces the friction between having an idea and actually getting something working.
Still early in my usage, but this style of working - less constant prompting, more outcome-focused execution - is starting to make a lot of sense, especially if you’re building regularly.
Curious to see how far this direction goes.
We have day0 support on Qoder.
Come and try it out.
Free access to Qwen3.8-Flash is still ongoing, experience it on Qoder.
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
DeepSeek V4.1 Flash has been updated to version V4.1-Flash-1017, and the entire Qoder suite now supports it.
We invite you to give it a try!
Apply to the Qoder Ambassador Program.
We’re looking for builders who believe in Qoder, share what they build, and inspire others to create.
A year of free Qoder Credits, early access, event support & more.
Create Anything. Together.
Apply:ambassador-program-6pmlhfuf2…
Proud to be the first cloud-hosted agent runtime on HarnessRouter.
Qoder Cloud Agents runs the agent loop, sandbox and delivery for you — your product just calls one API and gets finished work back.
That's the point of an Agents API: Qoder's capabilities can be plugged into anything, anywhere.
Huge thanks to @HARNESSROUTER for a thoughtful review that shaped the "remote runtime" spec.
More to come.
Qoder (@qoder_ai_ide) by @alibaba_cloud has officially adopted the Unified Harness Protocol (UHP).
You can now run Qoder as your product’s agent backend through the HarnessRouter API.
No agent loop, sandbox, orchestration, or tracing to build. Let Qoder handle your users’ tasks and deliver finished work, from generated files to completed actions, out of the box.
Spec: unifiedharnessprotocol.org
Open Source (Apache 2.0): github.com/HarnessRouter/har…
HarnessRouter cloud: harnessrouter.ai
This October, the Sonus credits are back!
Every Qoder individual subscriber can claim 2,000 SOTA Credits for Sonus.
Claim and use by Oct 24, 10AM UTC+8.
This is just the appetizer. Something bigger lands Oct 24.
Qoder Happy Hour: 80% off the Ultimate, every day through October.
No code, no hoops — it auto-applies at checkout on Pro Trial and paid plans.
10PM–8AM UTC+8, which is 10AM–8PM in New York, 7AM–5PM in San Francisco, late afternoon into night in Europe.
3s response. That's the new Qoder Fast. Is it the fastest out there? Race it yourself and find out.
Rewards:
🚀 Takeoff (100+ likes, 1 winner picked weekly) → 3,000 Credits.
🏎️ Drift (30+ likes or 60s+ video) → 2,000 Credits.
⚡ Boost (just post a comparison) → 600 Credits.
How to join:
- Pick a task, same prompt, run it on Qoder Fast and another AI tool
- Screenshot or record the screen, show the clock
- Tell us where Fast actually felt faster (and where it didn't)
- On X, tag @qoder_ai_ide with #FastRunChallenge #QoderFast
Oct 13 – Oct 30.
Starting every task from scratch is what happens when your tools don't remember your project.
Qoder workspaces fix that. A folder you already have becomes a workspace as is — nothing to move or copy. Your Claude Code instructions migrate to AGENTS.md. Qoder asks before it touches anything, and memory builds as you work.
One workspace per project. 1:40 walkthrough below.



















