The AI behind your Binance Agent OS agent, paid by its trading fees

Binance Agent OS lets your agent trade and read markets on Binance. bInference gives it a model to think with: Claude, GPT, Gemini and hundreds more on one key, paid from its token's trading fees.

Base URL
Your agent on Binance Agent OS
bInferenceThe models: Claude, GPT, Gemini and hundreds more on one binf_ key, paid from your token's fees
Your AI appClaude Code or Codex, running your agent
Binance Agent OSMarket data, your agent's own sub-account and trades, within the scopes you grant

Agent OS doesn't supply a model. Your app needs one, and bInference is it.

Your AI app sends its thinking to bInference and its actions to Binance. The two never share credentials: your binf_ key goes only to bInference, and your Binance sign-in only to Binance.
How it works
  1. People trade the tokenEvery buy and sell pays a 1, 3 or 5% tax
  2. The token's vaultGets the tax after Flap's 10% and splits it 70/30
  3. The agent's AI budget70% of it, in dollars, spent through one binf_ key
  4. Any modelClaude, GPT, Gemini, DeepSeek and hundreds more
Trading fees become AI credit on their own: no bills, no card, no top-ups. The other 30% stocks the holders' pool, which keeps AI here cheap.

What you get

  • Made for Binance Agent OS. Your agent acts on Binance through Agent OS and thinks with bInference. Set it up.
  • One key, hundreds of models. Claude, GPT, Gemini, DeepSeek, Grok and more, each at a fixed price per token. See them all on Models.
  • The formats you already use. OpenAI Chat Completions and Responses, and Anthropic Messages. Claude Code, Codex, OpenClaw, Hermes and the official SDKs work after two settings change.
  • Paid by trading, not by card. An agent's AI budget fills from its token's trading fees, in dollars. People can also buy credit for their own account with BNB.
  • Nothing kept. We never store prompts or answers, only each call's count and cost.

Start here

Who it is for

On this page