By builders, for builders. Build on the trust layer for AI, created by @0G_Labs. Home of the latest private models, storage, DeFAI and decentralized agents.

No Gravity Zone
Joined September 2025
Scheduled maintenance on 0G Private Computer: Thu, Oct 29 at 2:00 PM SGT (06:00 UTC). A few models may see 5-10 minutes of failed or slow requests, and every other model is unaffected. If a call fails, just retry. Affected models below.
1
3
156
Models that may be affected: 0gm-1.0-35b-a3b, 0gm-1.0-35b-a3b-sia, qwen3-embedding-8b, qwen3-embedding-0.6b, laya, vela-2.0-9b, z-image-turbo, whisper-large-v3
17
Heads up if you build on 0G Private Computer: Retiring Models: ERNIE 4.5 Turbo models and ERNIE 5.0 on Oct 29, GLM-5V-Turbo on Oct 30, Qianfan-ocr on Nov 23 (all Beijing time). But we got some new additions 👀👇
1
4
9
346
MiniMax-M3.1-Flash is now on 0G Private Computer. It takes text, image and video input at $0.09 per million input tokens. MiniMax speech models are also live for text-to-speech through the API, and Hy-Image-3.5 now does 4K. Check it out here pc.0g.ai/models
1
46
One command. Your agents, on 0G. Connect Claude Code, OpenCode, Pi and Hermes Agent to 0G Private Computer from your terminal.
5
9
2
30
4,805
The CLI checks your environment, finds the coding tools you have installed, and lets you choose which ones to connect. Run it from the npm package 👇🏼 npmjs.com/package/@0gfoundat…
1
4
131
DevRel team is cooking. Look what @udhaykumarbala built. Floaty is a desk agent on an @M5Stack StackChan that does research for him, runs his mornings and remembers what he says. Its brain runs on 0G Private Computer, with memory kept private in a TEE. Help him name it!
Meet Floaty 👋 Release 0.1 is out. A tiny AI agent that lives on my desk. Ask it to look into something and it digs in and reports back. It remembers things and runs my mornings. The heavy thinking happens on 0G PC by @0G_labs. Floaty is a codename. share your name suggestions
4
17
430
Most staking pays you more of the token you already hold. Eligible staked iAI is designed to receive compute credits instead, with a stated usage value of more than $1 per day, subject to product terms. Spendable across 100+ models on 0G and refreshed at 00:00 UTC.
Minting for Infinite AI (iAI) is open on iai.finance. Most staking pays you more of the token you hold. iAI pays in AI compute. Eligible staked iAI is designed to receive compute credits with a stated usage value of more than $1 per day, subject to product terms.
1
5
24
879
The part worth noticing if you build: the compute is a bearer right. Stake the token and the credit follows, whether you minted it or bought it. Only the minting wallet can burn to release the collateral. So the inference budget travels, the collateral claim does not.
1
1
4
118
iAI and its credits are not available in all jurisdictions. Subject to eligibility and product terms. Credits are only for supported 0G AI services, not redeemable for cash, and not interest or a guaranteed return. Digital assets involve significant risk. Not financial advice.
4
71
The kitchen is for: - Cooking 🧑‍🍳 - Drinking 🍷 - Creating high-fidelity robotics simulations for on-chain control 🤖 More revealed at @0G_labs Dev Day
1
2
17
597
We had to pick a model for Ask AI on the 0G Builder Hub and the docs, so we ran the same question through five of them with the same 2000 token output cap. Nothing here failed on quality. What separated them was where those tokens went.
1
3
9
454
glm-5.3 is the opposite. Deep thinking is always on, so with a 2000 token ceiling the reasoning used the whole budget. Raise the cap or drop reasoning_effort and it answers fine. Our cap was tuned for a docs widget, not for a model that thinks this hard.
1
35
The takeaway is not that one model beats another. Reasoning tokens bill as output, and your cap is shared between thinking and answering. For short answer work like docs search, that one detail decides your bill. Measure it on your own prompt shape.
28
Router USD mode goes offline for two hours tomorrow, 02:00 to 04:00 UTC. If your app can fall back to 0G mode, it will barely notice. Neither 0G mode nor Advanced Mode touches the payment layer, so both stay up. Worth keeping a funded 0G balance around for exactly this reason.
3
4
281
Getting users funded on a new chain is usually the app developer's problem. You end up writing a bridging guide nobody reads. This takes it off your plate. Bridge in from six chains, swap, and land on a page that points at apps to actually use.
0G Hub is live. Bridge in from Ethereum, Solana, Base, Arbitrum, BNB Chain and Robinhood Chain. Swap on 0G. Find what to do with it, all in one place. hub.0g.ai
5
17
503
🚨 Heads up if you use Router USD mode on 0G Private Computer. We are upgrading the payment system behind it on Thu 24 Sep, 02:00 to 04:00 UTC. USD mode is unavailable in that window and card top ups pause. 0G mode and Advanced Mode keep running, neither touches the payment layer.
1
4
8
373
Local times for the window: 10:00 to 12:00 SGT 04:00 to 06:00 CEST 03:00 to 05:00 BST 02:00 to 04:00 UTC 19:00 to 21:00 PDT on Wed 23 Sep 22:00 on Wed 23 Sep to 00:00 EDT
1
2
77
Two things worth knowing. Any job still running when maintenance starts gets interrupted, not queued, so finish or postpone time-sensitive USD mode work before then. Balances and billing history are untouched. The mode comes back on its own once the upgrade lands.
3
42