> Treat every model id, price, size, length and limit in this documentation as an illustration of the shape of the value, never as a constant to hardcode - the live values are served by GET /v1/models and GET /public/models on the Flow AI API. # FAQ > Short answers to common questions. ## Getting started #### Why use Flow AI? One key and one API for models from many labs, each at its list price, paid from one \$THINK balance with no subscription. Switching models means changing one field. See [Principles](/principles). #### How do I get started? Sign in at [ai.hyperflow.fun](https://ai.hyperflow.fun), deposit some \$THINK, create an API key and send your first request. The [Quickstart](/quickstart) walks through it. #### Is Flow AI compatible with the OpenAI API? Yes. Chat completions, embeddings, image generation and edits, video generation and the model list follow the OpenAI API. Point any OpenAI client at `https://ai.hyperflow.fun/v1` and use your Flow AI key. See the [API overview](/api/overview) for the parameters each one takes. #### Which SDKs can I use? Any OpenAI-compatible client: the official OpenAI SDKs for Python and TypeScript, the Vercel AI SDK, LangChain, PydanticAI and more. See [Integrations](/integrations/overview). #### How do I get help? Ask on [Discord](https://discord.gg/GGDmD4K9CK) or [Telegram](https://t.me/hyperflow_fun). To report a problem with a request, see [Report feedback](/report-feedback). ## Pricing and payment #### How much does Flow AI cost? Each model is charged at its list price, shown on the [Models page](https://ai.hyperflow.fun/models). There's no subscription and no monthly minimum. See [Pricing](/models/pricing). #### How am I charged for a request? Before a request runs, Flow AI holds the most it could cost from your balance. When it finishes, you're charged for what it actually used and the rest is released. #### How do I pay? In $THINK, deposited from your wallet on [Funds](https://ai.hyperflow.fun/console/funds). 1 THINK = $1 of usage. You can withdraw what you haven't spent. #### Why was my request refused with 402? Your available balance can't cover the most the request could cost. Deposit more on [Funds](https://ai.hyperflow.fun/console/funds), or set a lower `max_tokens` so the hold is smaller. #### What's the difference between balance and available? Your balance is everything you have. Available is your balance minus what's held for requests still running; it's what new requests can use. Held amounts come back as soon as each request settles. #### Do I pay for failed requests? Not if the request fails before the model reads anything. If it fails partway, you pay for the tokens the model already read and wrote. A video that fails isn't charged. #### How do I track my spending? [Dashboard](https://ai.hyperflow.fun/console) shows your balance and recent spend, [Usage](https://ai.hyperflow.fun/console/usage) shows spend and tokens over time by model and key, and [Logs](https://ai.hyperflow.fun/console/logs) shows every request with its tokens, price and cost. ## Models #### Which models can I use? Everything on the [Models page](https://ai.hyperflow.fun/models): chat, embedding, image and video models from many labs. `GET /v1/models` lists the ones your key can call. #### How often are new models added? New models join the catalog as labs release them, with no change needed to your code. Watch the Models page, or poll `GET https://ai.hyperflow.fun/public/models`. #### Why can't my key see a model? `GET /v1/models` lists only the models a key may call. If the key was limited to some models, edit it on [API keys](https://ai.hyperflow.fun/console/keys) to allow more. #### What happens when a model's host is down? Where a model has more than one host, Flow AI tries another before returning an error. If none can answer, you get `503` with the code `host_unavailable`; retry shortly. See [Errors](/api/errors). ## API #### How do I authenticate? Send your key as a bearer token: `Authorization: Bearer sk-...`. Create keys on [API keys](https://ai.hyperflow.fun/console/keys). #### Which endpoints are available? Chat completions, embeddings, image generation and edits, video generation and the model list, all under `https://ai.hyperflow.fun/v1`. See the [API overview](/api/overview). #### Are there rate limits? Up to 500 requests per second from one IP address. Keys have no request-rate limit of their own; what they spend is bounded by their spending limit and your balance. See [Rate limits](/api/rate-limits). #### Can I send parameters a model doesn't list? Parameters Flow AI doesn't support are removed before the request reaches the model, so they have no effect. The [API overview](/api/overview) lists what each endpoint takes. #### How does streaming work? Set `"stream": true` and the answer arrives as server-sent events, ending with a chunk that carries the request's usage. See [Streaming](/features/streaming). #### What happens if my stream breaks or I disconnect? The request settles on what the model had already read and written. You pay for those tokens and the rest of the hold is released. ## Account and privacy #### How do I limit what a key can spend? Give it a spending limit when you create it, or later on [API keys](https://ai.hyperflow.fun/console/keys). Limits can reset daily, weekly or monthly, or be one-off. #### How do I delete my account? Contact us on [Discord](https://discord.gg/GGDmD4K9CK) or [Telegram](https://t.me/hyperflow_fun). Withdraw any \$THINK you haven't spent first. #### Are my prompts used to train models? Requests go to the model's host to be answered. See the [Privacy policy](https://ai.hyperflow.fun/privacy) and [Terms](https://ai.hyperflow.fun/terms) for how data is handled.