# Docs

- Guides: Start, connect your tools and learn how it works
  - [Introduction](/): Every AI model on one key, paid by your agent's trading fees.

  - **Binance Agent OS**
  - [Binance Agent OS](/agent-os): Your agent acts on Binance through Agent OS and thinks with bInference, paid by its own trading fees.
  - [Claude Code](/agent-os/claude-code): Run Claude Code on bInference and connect it to Binance, from key to first trade.
  - [Codex CLI](/agent-os/codex): Run Codex on bInference and connect it to Binance. Works for the Codex and ChatGPT desktop apps too.
  - [Agentic Wallet](/agent-os/agentic-wallet): Let your agent swap, set limit orders and send tokens on chain, within rules you set in the Binance App.
  - [Skills](/agent-os/skills): Add Binance's skills to your agent for market data, token audits and on-chain trading.
  - [Safety and limits](/agent-os/safety): Every limit on both sides, what each one stops and how to stop everything at once.
  - [What it costs](/agent-os/costs): What an Agent OS session spends on AI, and five ways to keep it low.
  - [Troubleshooting](/agent-os/troubleshooting): What went wrong, on which side and how to fix it.

  - **Get started**
  - [Quickstart](/quickstart): Your first call in two minutes. If you've used the OpenAI or Anthropic API, you already know how.
  - [API keys](/keys): Two kinds of key, optional spending limits and what to do if one leaks.
  - [Models](/models): Every model you can call, with live prices. Copy an id and send it as model.

  - **Connect your tools**
  - [OpenAI SDK](/clients/openai-sdk): The official OpenAI libraries for TypeScript and Python, with any model.
  - [Anthropic SDK](/clients/anthropic-sdk): The official Anthropic libraries, with Claude and every other model.
  - [Vercel AI SDK](/clients/vercel-ai-sdk): Use bInference as an OpenAI-compatible provider in the AI SDK.
  - [Claude Code](/clients/claude-code): Run Claude Code on your agent's budget with three settings.
  - [Codex](/clients/codex): Add bInference to the Codex CLI as a model provider.
  - [OpenClaw](/clients/openclaw): Add bInference as a custom provider in OpenClaw.
  - [Hermes](/clients/hermes): Point Hermes Agent at bInference as a custom endpoint.

  - **Features**
  - [Streaming](/features/streaming): Get the answer as it's written, and why long calls should always stream.
  - [Tools and structured output](/features/tools): Let the model call your functions, or answer in the exact JSON you need.
  - [Reasoning](/features/reasoning): Let a model think before it answers, and what thinking costs.
  - [Web search](/features/web-search): Add :online to any model and it reads the web before it answers.
  - [Routing and fallbacks](/features/routing): Steer which provider runs a model, and keep going when one is busy.

  - **How it works**
  - [Where the money comes from](/how-it-works/fees): Every trade of an agent's token pays a small tax. Most of it becomes the agent's AI budget.
  - [Credit and expiry](/how-it-works/credit): Balances are in dollars, in daily batches that last 7 days and are spent oldest first.
  - [How a call is paid](/how-it-works/calls): A call reserves its worst case, runs, then pays only what the model wrote.
  - [Launching an agent](/how-it-works/launch): One screen, three steps and an agent whose AI pays for itself.
  - [$BINF holders](/how-it-works/holders): Hold $BINF and the credit you buy comes with up to 8% more.
  - [Privacy](/how-it-works/privacy): We never store prompts or answers. Here is exactly what we keep.

  - **Help**
  - [Questions](/faq): Short answers to what people ask most.
- API reference: Endpoints, errors, limits and the playground
  - [API overview](/api): One base URL, one key, three formats. Everything you need before the first call.
  - [Playground](/api/playground): Try any model with your key. See the reserve before you send, then watch the answer stream in.

  - **Endpoints**
  - [Chat Completions](/api/chat-completions): The OpenAI chat format, for every model.
  - [Responses](/api/responses): The OpenAI Responses format, which Codex speaks.
  - [Messages](/api/messages): The Anthropic Messages format, for Claude Code and every model.
  - [List models](/api/models): Every model you can call and its price. No key needed.
  - [Get balance](/api/balance): What the key can spend now, what's expiring and the key's own limit.

  - **Behavior**
  - [Errors](/api/errors): Every error the API returns, why it happens, what to do and whether to retry.
  - [Rate limits](/api/rate-limits): How many calls an agent may run and start, how to read the waits and how to stay under.
  - [Retries](/api/retries): Which errors to retry, how long to wait and code that does it right.

  - **Resources**
  - [For AI tools](/api/ai-tools): These docs as plain text for AI assistants, and the API as an OpenAPI file.