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

# FAQ

> Answers to the questions we get most often about Guardway.

<AccordionGroup>
  <Accordion title="Is the gateway self-hosted or cloud?">
    **Self-hosted.** You run the gateway container inside your own network (VPC, on-prem, or even a laptop). Your applications call your gateway, not Guardway. The **dashboard** at [app.guardway.ai](https://app.guardway.ai) is SaaS — it configures and observes gateways but never proxies inference traffic.
  </Accordion>

  <Accordion title="Do my prompts or completions ever leave my network?">
    No. The gateway forwards requests directly to the provider you configured (OpenAI, Anthropic, etc.). Prompts and completions stay on the gateway — only aggregate telemetry (token counts, latency, cost) and administrative audit logs flow to the cloud dashboard. See [Privacy and Security](/resources/privacy-and-security).
  </Accordion>

  <Accordion title="Which LLM providers does Guardway support?">
    20+ presets out of the box — OpenAI, Anthropic, Google Gemini, Groq, Mistral, DeepSeek, xAI, Perplexity, Together, Fireworks, OpenRouter, Cohere, AWS Bedrock, Azure OpenAI, HuggingFace TGI, NVIDIA NIM, Ollama, LM Studio, vLLM, plus specialty providers (Voyage, AssemblyAI, ElevenLabs, Fal.ai). Anything else that speaks the OpenAI API works via the **Custom** preset. See [Connect a provider](/platform/configuration/providers).
  </Accordion>

  <Accordion title="What's the difference between the Gateway API keys and the Platform API keys?">
    Today they are the same keys, issued from **Configuration → API keys** and valid on every gateway in your organization. Per-gateway scoping is on the roadmap. See [API keys](/platform/configuration/api-keys).
  </Accordion>

  <Accordion title="How do guardrails work?">
    Guardrails run on the gateway before the request reaches the provider (and can also inspect the response). Built-in checks cover PII, hate speech, prompt injection, keyword lists, and IP allow/block-lists. Detection uses small language models (SLMs) — see [Guardrails](/platform/configuration/security#guardrails).
  </Accordion>

  <Accordion title="Does Guardway support MCP?">
    Yes. Register MCP servers with the gateway and assign per-key access rules from **Configuration → API keys → MCP** tab. Tool calls are logged separately — see [MCP](/platform/configuration/security#mcp) and [Logs → MCP logs](/platform/logs#mcp).
  </Accordion>

  <Accordion title="Can I run more than one gateway?">
    Yes. You can register as many gateways as you want — production, staging, per-region, etc. Providers and models are attached per-gateway, so each gateway holds its own credentials and model inventory. Usage dashboards roll up across all of them. See [Gateways](/guardway-gateway/activate).
  </Accordion>

  <Accordion title="Does the gateway need internet access?">
    It needs:

    * Outbound HTTPS to `api.guardway.ai` (control plane).
    * Outbound HTTPS to the LLM providers you use.
    * Inbound access on port 8080 from whoever calls it.

    No inbound from the internet is required. See [Requirements](/guardway-gateway/requirements).
  </Accordion>

  <Accordion title="What happens when a provider is down?">
    Routing rules support **fallback strategies** — `next-priority`, `lowest-cost`, `lowest-latency`, `fail`. You can chain fallbacks so a single provider outage doesn't break your traffic. See [Routing](/platform/configuration/routing).
  </Accordion>

  <Accordion title="How do budgets and quotas work?">
    Set them at three levels: per **API key**, per **team**, or per **routing rule**. Requests are blocked when a hard cap is hit; alerts fire at configurable thresholds (50 / 80 / 100 %). See [API keys](/platform/configuration/api-keys) and [Access](/platform/configuration/members).
  </Accordion>

  <Accordion title="Is there an API for managing gateways programmatically?">
    The public management API is on the roadmap. The gateway itself already exposes a stable OpenAI-compatible inference API today. See [API reference](/api-reference/coming-soon).
  </Accordion>

  <Accordion title="What browsers does the dashboard support?">
    Latest Chrome, Firefox, Safari, and Edge. Internet Explorer is not supported. See [Limitations](/resources/limitations).
  </Accordion>

  <Accordion title="How do I report a bug or security issue?">
    Bugs: email [support@guardway.ai](mailto:support@guardway.ai) with repro steps. Security: email [security@guardway.ai](mailto:security@guardway.ai) privately — do not open a public issue. See [Support](/resources/support).
  </Accordion>
</AccordionGroup>