Stake-to-Privacy AI, or not private AI backed by BSC revenue. Stake $BINF and get private AI every day, sealed in NVIDIA Hopper and Intel TDX.
Joined September 2026
- Tweets79
- Following3
- Followers938
- Likes10
Pinned Tweet
Introducing bInference.
AI credits backed by BSC revenue.
Plug bInference Router into a Binance Agent OS agent or into Claude Code, Codex, Muse, OpenClaw or Hermes.
Use them for trading, Agent OS features or R&D.
Recap: bInference, less than a month live.
16 launches. 152 users. Almost 30 Billion tokens routed.
Router, agents, private AI, Clips, Audio, Inference DEX, free models and more. All live.
Next: bGPU.
Introducing bInference ZeroRoute: free AI models, one endpoint.
Call "binference/free" and Capability-Matched Rotation picks a free model that can handle your request: images, tools or JSON.
17 free models from NVIDIA, Google, MiniMax and more. $0, a new key works.
bGPU waitlist is open.
bInference GPU market, anonymous by design. No account, no KYC, just your BSC wallet.
Rent RTX 4090 to H100, to train models, run your own LLMs or generate images and video.
Host your idle GPU, get paid daily in USDT.
Join the bGPU waitlist and get first access when the market opens:
binference.io/gpu/waitlist
bInference Router.
12 Billion tokens routed.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi and more. One key.
(built by bInference Clips)
bInference DEX launches with bInference Router credits: buy, sell and trade them like any other asset.
Next, we're opening submissions for AI providers to list their own inference on bInference DEX, so you can trade it too.
Set your bid. Set your ask.
Trade AI like crypto.
binference.io/dex
Introducing bInference DEX.
The simplest way to think about it: a decentralized Binance for AI inference.
Limit orders, market fills, a live order book for AI credit.
Every trade settles on BNB Chain. Your USDT stays yours, backed 1:1.
Bid. Fill. Build.
Prompt caching is now on the bInference Router.
Long system prompts, tools and documents are paid for once, then read from cache on every call after.
Up to 90% less cost for repeated input. Faster answers, same models.
All Claude models are 30% off on bInference for the next 3 days.
Opus 5.5 drops to $2.24 in and $11.20 out per million tokens.
Fable 5.1, Sonnet 5.5, Haiku 5.5 and every other Claude model, the same 30%.
To support all the creativity Opus 5.5 is capable of. Works through the API, in Claude Code and in the AI chat, with the AI credit you already have.
Ends Sunday 12:00 UTC.
Your AI chats now live only on your device.
Encrypted and locked with your passkey. No copy on our servers.
Export to one sealed file or move phone to laptop with a QR code.
250+ models from providers that keep nothing.
See every request for yourself.
See every request your chat sends, live from your own browser tab: where it goes, how big it is, and what our servers keep.
binference.io/transparency
bInference Agent, week one recap.
6 days. 430+ commits. 17 packages.
Built in the open so far: trading engine, Telegram bot, Privy wallets that sign only inside your limits, the signer, an MCP server and the CLI.
Builders, join us. bInference is MIT open source and contributors are welcome: read CONTRIBUTING .md, pick a part you know and open a PR.
github.com/bInference-Lab/bI…
