# Use Pod > Use Pod is the inference marketplace: a drop-in OpenAI- and Anthropic-compatible API backed by a two-sided market of independent GPU operators, settled in USDC. Every page below is available as raw Markdown by appending `.md` to its URL (e.g. `/using/quickstart.md`). ## Introduction - [How it works](https://docs.usepod.ai/introduction/how-it-works/): From an inbound request to a settled, billed response — the path through the Use Pod gateway. - [What is Use Pod](https://docs.usepod.ai/introduction/what-is-use-pod/): An inference marketplace with a drop-in OpenAI/Anthropic-compatible API and USDC settlement. ## Using Use Pod (demand side) - [Drop-in API](https://docs.usepod.ai/using/drop-in-api/): Use Pod is a base-URL swap for any OpenAI- or Anthropic-compatible client. - [Funding your balance](https://docs.usepod.ai/using/funding/): Top up a token by card or by sending USDC on Solana. - [Quickstart](https://docs.usepod.ai/using/quickstart/): Get a token, fund it, and point your client at Use Pod in under a minute. - [Spend controls](https://docs.usepod.ai/using/spend-controls/): Cap the price you'll pay per million tokens with per-request headers. ## Running a provider (supply side) - [BYOK relays](https://docs.usepod.ai/providers/byok/): Resell capacity on an upstream key you already hold, at prices you set. - [Earnings & cashout](https://docs.usepod.ai/providers/earnings-and-cashout/): How provider earnings accrue and how to withdraw USDC to a Solana wallet. - [Provider quickstart](https://docs.usepod.ai/providers/quickstart/): Install the agent, enroll, post a bond, and start earning USDC for served inference. - [The provider agent](https://docs.usepod.ai/providers/agent/): How the standalone agent connects, advertises capabilities, and serves jobs from your local backend. ## Marketplace - [Pricing](https://docs.usepod.ai/marketplace/pricing/): Per-million-token pricing, the cap-at-centralized rule, and the fee split. - [Routing & matching](https://docs.usepod.ai/marketplace/routing/): How the coordinator selects a provider for each request, with centralized fallback. - [Trust & reputation](https://docs.usepod.ai/marketplace/trust/): Bonds, reputation scoring, and benchmark canaries that keep the marketplace honest. ## API reference - [Inference proxy](https://docs.usepod.ai/api/proxy/): The drop-in proxy path, supported endpoints, request headers, and response headers. - [Register a token](https://docs.usepod.ai/api/register/): Create a token and deposit address with POST /v1/register. ## Resources - [For agents](https://docs.usepod.ai/resources/for-agents/): Machine-readable access to these docs — raw Markdown per page, llms.txt, and the drop-in API. ## Index - [Use Pod](https://docs.usepod.ai/index/): The inference marketplace — drop-in OpenAI/Anthropic-compatible API, USDC billing, and a two-sided market of independent GPU operators.