Zoneveld retweeted
Introducing Image Studio on Minirouter 🏞️
→ 25+ image models
→ GPT Image, FLUX, Seedream, Recraft
→ Starts at under $0.01/image
→ Generate up to 4 images at a time
→ Turn any image into a video in 1 click
Zoneveld retweeted
solana:CGEDT9QZDvvH5GmVkWJH2BXiMJqMJySC9ihWyr7Spump now burns every 24 hours. For as long as people trade.
Half of all pump.fun creator fees buy solana:CGEDT9QZDvvH5GmVkWJH2BXiMJqMJySC9ihWyr7Spump off the open market every day and burn it on chain.
More volume, more burn. The Central Committee has a plan ☭ 🧵
Zoneveld retweeted
Introducing Video on Minirouter 🎬
→ 23 models (Veo, Seedance, Grok, Kling)
→ From $0.03 per second
→ Generate clips up to 30s
→ Failed videos are free
→ Remix 100+ templates in Video Studio
Zoneveld retweeted

ALT Bernie Sanders blames "corporate greed" for high gas prices, but his platform called for a nationwide fracking ban. Fracking made the U.S. the world's largest oil producer. If you ban it, supply drops and prices rise. That's basic economics, not greed. Price controls didn't work either: in the 1970s they brought gas lines and rationing. Cheaper gas takes more drilling, more refining and more competition, not banning production and then blaming the producers.
Zoneveld retweeted
staying calm and bidding for one of the fastest growing on chain inference marketplaces @miniroutersh
just broke ATH again with more than 3b token usage yesterday
- gud narrative
- gud dev @iamzhe
- gud product
- gud bid
Zoneveld retweeted
2/ @miniroutersh won the meteco supernova infra award
one api key gets you 296 models from 39 AI labs. pay in crypto from $0.50, no account needed.
in under a month, it went from 1 billion to 10 billion tokens served.
xitter.gq/iamzhe/status/21106862…
Zoneveld retweeted
GPT-6.1 Terra is now available on minirouter.sh.
>matches Astra on Agents’ Last Exam
>90% cheaper than Astra
>3x faster than Astra and Sol
>best value at low and medium effort
Zoneveld retweeted
I think on chain open router is the biggest opportunity in crypto right now
And @miniroutersh @iamzhe is building towards it
Zoneveld retweeted
3rd consecutive day of ATH token usage by @miniroutersh
Yet another ATH by @miniroutersh breaking more than 2B tokens for the first time
Fastest growing inference marketplace @iamzhe
Zoneveld retweeted
Kimi K3.1 Pro is now live in Minirouter.
→ Latest model from @Kimi_Moonshot
→ Smarter than GPT-6.1 Sol & Fable 5.1
→ Beats GPT-6 Astra for less
→ 1M context window
→ Text and image input
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
Zoneveld retweeted
Wow @miniroutersh just hit their highest token usage ATH once again
Inference marketplaces are heating up and what @iamzhe is building has the highest potential on Solana
Zoneveld retweeted
DeepSeek-V4.1-Flash-1017 is now live in Minirouter.
→ Latest version from @deepseek_ai
→ Smarter than GPT-5.6 Sol
→ 17x cheaper than GPT-5.6 Sol
→ 1M context window
→ Multimodal input
→ Faster than GPT-6.1 Sol Ultrafast 🤯
🚀 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
10 billion tokens served by minirouter.sh.
Next stop, 100 billion.
Zoneveld retweeted
Gemini 4 Argon is now live on Minirouter.
→ @GoogleDeepMind's latest model
→ As smart as GPT-6 Astra & Fable 5.1
→ Great for long horizon tasks
→ 50% off until Dec 1st






























