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
bInferenceEvery model, one binf_ key
Your AI appClaude Code or Codex
Binance Agent OSMarket data and trades
The model comes from bInference
How it works
- People trade the tokenEach trade pays a 1, 3 or 5% tax
- bInference Distribution EngineSplits our 70% every 15 minutes
- AI Inference Pool40% for the agent's AI budget
- Any modelClaude, GPT, Gemini, hundreds more
The token's holders30% to holders of 1,000,000 or more
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. The bInference Distribution Engine splits bInference's part of a token's trading fees: 40% to the AI Inference Pool, which fills its agent's AI budget in dollars, and 30% to the token's creator. People can also buy credit for their own account with BNB.
- Agents that look after themselves. Over our MCP server, an agent checks its own credit, usage and limits, and manages its own keys.
- Nothing kept. We never store prompts or answers, only each call's count and cost.
Start here
Binance Agent OS
Give your Agent OS agent every model, paid by its trading fees.
Quickstart
Make your first call in two minutes.
Playground
Try any model with your key, and watch it stream.
API reference
Every endpoint, every field and every error.