> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hopscotchlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Short answers to the questions this API gets asked most, each pointing at the page that answers it properly.

Every answer here is short on purpose and links to the page that carries the
detail. Where the honest answer is "not yet" or "we do not publish that", it says
so rather than being left out.

## Getting started

<AccordionGroup>
  <Accordion title="How much of my code has to change?">
    Two settings: the base URL and the key. Then one edit that is not optional, which
    is putting a provider in front of every model id. See
    [Migrate from OpenAI](/resources/migrate-from-openai).
  </Accordion>

  <Accordion title="Why was my model id refused?">
    A bare id such as `gpt-4o-mini` is not a Hopscotch model id. Ids name the provider
    that serves them, so it is `openai/gpt-4o-mini`. A bare id is refused with `400`
    and the code `model_id_not_pinned` rather than being routed to whichever provider
    we happen to carry it under. See [Models](/concepts/models).
  </Accordion>

  <Accordion title="Which models can I call?">
    Ask `GET /v1/models`, or browse the Models screen in the dashboard. This site
    publishes no model list, because any list written here would be wrong the first
    time the catalog changed.
  </Accordion>

  <Accordion title="Which endpoints are documented?">
    `POST /v1/chat/completions`, `GET /v1/models` and `GET /v1/models/{id}`. Those
    are the operations this site documents and the API reference publishes. A path
    this site does not document is one we make no promise about, in either
    direction. See [OpenAI compatibility](/get-started/openai-compatibility).
  </Accordion>

  <Accordion title="Do the official OpenAI SDKs work?">
    The instructions on this site set only the base URL and the key, which is the
    whole intended change. We have not published a proof run of an unmodified SDK
    against the production hostname, so we describe that as instructions rather than
    as a certification.
  </Accordion>
</AccordionGroup>

## Features

<AccordionGroup>
  <Accordion title="Does tool calling work?">
    Yes, as OpenAI defines it. `tools`, `tool_choice` and the `tool_calls` that come
    back all travel unchanged, streamed and not. Nothing is executed on our side. See
    [Tool calling](/concepts/tool-calling).
  </Accordion>

  <Accordion title="Does response_format work?">
    Yes, both forms, forwarded as written. Nothing here validates your schema or the
    reply against it. See [Structured outputs](/concepts/structured-outputs).
  </Accordion>

  <Accordion title="Can I send images?">
    Yes, in OpenAI's message-part shape, to a model that takes one. See
    [Image inputs](/concepts/image-inputs).
  </Accordion>

  <Accordion title="How do I know whether a model supports something?">
    Every catalog entry carries five capability words, each answering `yes`, `no` or
    `unknown`. Read `unknown` as "nobody has established this" rather than as "no".
    See [Model capabilities](/concepts/model-capabilities).
  </Accordion>

  <Accordion title="Does prompt caching work?">
    Provider prompt caching passes through unchanged, and the cached-token counts
    come back separately and are priced as their own kind. There is nothing of ours
    to enable. See [Prompt caching](/concepts/prompt-caching).
  </Accordion>

  <Accordion title="Can I set a fallback order across models?">
    Yes, with a routing profile: your own ordered list of `provider/model` lines,
    requested as `profile/{identifier}` in the `model` field. See
    [Routing profiles](/concepts/routing-profiles).
  </Accordion>

  <Accordion title="Can I pin which provider serves a request?">
    That is what a model id is. The part before the first slash names the provider,
    and we never substitute a different one behind your back. A model carried by two
    providers is two ids with two prices.
  </Accordion>

  <Accordion title="Is there an embeddings endpoint?">
    Nothing is documented here for one. Embeddings stay off this site until the
    tracker says they serve real responses, and until then we would rather say
    nothing than describe a call you cannot rely on.
  </Accordion>
</AccordionGroup>

## Money

<AccordionGroup>
  <Accordion title="Is there a markup on requests?">
    No. A request deducts the provider's rate at face value. The platform fee is
    added when you buy credit, not when you spend it. See
    [Credits and billing](/concepts/credits-and-billing).
  </Accordion>

  <Accordion title="Why did my request return 402?">
    Your account cannot pay for it. Either the balance is empty, or a ceiling
    somebody set has been reached. The `code` says which. Nothing is charged for the
    refusal. See [Errors](/api-reference/errors).
  </Accordion>

  <Accordion title="What is the difference between the 429 codes?">
    `rate_limit_exceeded` is your key's request rate, and it carries `Retry-After`.
    `spend_rate_exceeded` is your account spend rate cap, and the lever for it is
    sending `max_tokens`. See
    [Rate limits and spend controls](/concepts/rate-limits-and-spend-controls).
  </Accordion>

  <Accordion title="Why does sending max_tokens help?">
    Credit is held against a ceiling while a request runs. With no `max_tokens` the
    ceiling is the model's published maximum output, so the request occupies more of
    your spend rate cap while it is in flight. The hold comes back in full at
    settlement either way. See [Request parameters](/api-reference/parameters).
  </Accordion>

  <Accordion title="Where do I see what a request actually cost?">
    On the Activity screen, one row per request. The usage record is the authority on
    what a request cost, not a rate in the catalog. See
    [View activity](/guides/view-activity).
  </Accordion>

  <Accordion title="Can I use my own provider key?">
    Yes, for a provider we already serve. Your key then answers every request to that
    provider and the provider bills you directly. It does not add models to your
    catalog. See [Bring your own key](/concepts/bring-your-own-key).
  </Accordion>
</AccordionGroup>

## Data and operations

<AccordionGroup>
  <Accordion title="Do you store my prompts and replies?">
    No. What is recorded is metadata about a request: what was called, what it cost,
    how long it took, what happened. Never the content. See
    [Data and privacy](/concepts/data-and-privacy).
  </Accordion>

  <Accordion title="Can you show me my API key again?">
    No. We keep only a hash of it, so it cannot be shown again or recovered. Replace
    it. See [Authentication](/get-started/authentication).
  </Accordion>

  <Accordion title="Why are provider rate-limit headers missing?">
    They are not forwarded, because they describe a pool we hold rather than a limit
    that applies to you. Your own limits arrive as `429` codes you can branch on. See
    [Headers](/api-reference/headers).
  </Accordion>

  <Accordion title="What should I include when I ask about a request?">
    The request id. It is on every response on `x-hopscotch-request-id` and on
    `x-request-id`, and inside every error body as `request_id`. Quote it rather than
    describing the symptom.
  </Accordion>

  <Accordion title="Do you publish an uptime or latency figure?">
    No. No figure for availability, for throughput, or for the latency the hop adds
    has been measured here in a way we are willing to publish, so this site claims
    none.
  </Accordion>

  <Accordion title="Is the API versioned?">
    There is no version to pin beyond the `/v1` in the path. The surface grows by
    addition, and the error envelope is the stable contract. See
    [API reference](/api-reference/introduction).
  </Accordion>
</AccordionGroup>