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

# FinalRun FAQ: accounts, AI providers, pricing, and CI/CD

> Answers to common FinalRun questions: BYOK vs FinalRun Cloud, supported AI providers, platform compatibility, CI/CD usage, and artifact storage.

FinalRun is an open-source, CLI-based tool. You can run it with your own AI provider key (BYOK), or sign up for FinalRun Cloud for managed AI without provisioning a provider account. The questions below cover the most common things people ask.

<AccordionGroup>
  <Accordion title="Do I need to create a FinalRun account?">
    Only if you want to use **FinalRun Cloud** for managed AI. Cloud accounts are free to create and include \$5 of credits — sign up at [cloud.finalrun.app](https://cloud.finalrun.app) and set `FINALRUN_API_KEY`. See [Cloud API Key](/configuration/cloud-api-key).

    If you'd rather **bring your own AI provider key** (Google, OpenAI, or Anthropic), no FinalRun account is needed — install the CLI, set the provider key, and run. See [AI Providers](/configuration/ai-providers).
  </Accordion>

  <Accordion title="What's the difference between BYOK and FinalRun Cloud?">
    Both run the same CLI and produce the same test artifacts. They differ in how AI access is provisioned and billed:

    |                  | FinalRun Cloud                                                       | BYOK                                                           |
    | ---------------- | -------------------------------------------------------------------- | -------------------------------------------------------------- |
    | Account needed   | FinalRun account at [cloud.finalrun.app](https://cloud.finalrun.app) | None for FinalRun; you supply a Google/OpenAI/Anthropic key    |
    | Env variable     | `FINALRUN_API_KEY`                                                   | `GOOGLE_API_KEY` / `OPENAI_API_KEY` / `ANTHROPIC_API_KEY`      |
    | Billing          | \$5 free credits, then per-run via FinalRun                          | Standard provider API rates, billed by Google/OpenAI/Anthropic |
    | Provider account | Not required                                                         | Required (one of the three above)                              |

    Cloud is the fastest way to get started. BYOK is useful if your team already has a provider account, wants a specific model tier, or needs provider-side billing visibility.
  </Accordion>

  <Accordion title="Which AI providers does FinalRun support?">
    Three AI providers are supported when bringing your own key:

    | Provider  | Supported models          | Environment variable |
    | --------- | ------------------------- | -------------------- |
    | Google    | Gemini 3+                 | `GOOGLE_API_KEY`     |
    | OpenAI    | GPT-5+                    | `OPENAI_API_KEY`     |
    | Anthropic | Claude Sonnet 4 / Opus 4+ | `ANTHROPIC_API_KEY`  |

    Costs are billed directly by your provider at standard API rates. Set the key in your shell, in a `.env` file at your workspace root, or pass `--api-key` for a single run.

    Prefer not to provision a provider account? Use [FinalRun Cloud](/configuration/cloud-api-key) instead — set `FINALRUN_API_KEY` and you're done.
  </Accordion>

  <Accordion title="Does FinalRun work with real devices or only emulators?">
    * **Android** — both real devices (over `adb`) and emulators are supported.
    * **iOS** — simulators only today. Physical iOS device support is on the roadmap; [join the waitlist](https://docs.google.com/forms/d/e/1FAIpQLScOTaNWjvxIG8Ywn6THHYJuqBM-b86Y-Fx39YVoBVhHuBDZ2w/viewform?usp=publish-editor) for early access.
  </Accordion>

  <Accordion title="Which platforms does FinalRun support?">
    Android and iOS.
  </Accordion>

  <Accordion title="How much does each test run cost?">
    FinalRun the CLI is free and open-source. AI execution is billed in one of two ways:

    * **FinalRun Cloud** — new accounts include \$5 of free credits. After that, runs are billed per execution. Sign up at [cloud.finalrun.app](https://cloud.finalrun.app).
    * **BYOK** — you pay your AI provider (Google, OpenAI, or Anthropic) directly for tokens consumed during test execution. Cost depends on the model you choose and how long the test takes. FinalRun adds no markup.
  </Accordion>

  <Accordion title="Can I run FinalRun in CI/CD?">
    Yes — only on FinalRun Cloud. Set `FINALRUN_API_KEY` as a CI secret and call `finalrun cloud test` as a pipeline step:

    ```sh theme={null}
    finalrun cloud test smoke.yaml --platform android
    ```

    Local emulator/simulator runs aren't supported in CI today.
  </Accordion>

  <Accordion title="How do I use FinalRun with AI coding agents like Claude Code, Cursor, or Codex?">
    FinalRun ships a set of agent skills that let you generate tests, run them, and fix failures — all from your AI coding agent chat. They work in **Claude Code, Cursor, and Codex** (and any other agent that supports the skills protocol).

    The FinalRun installer registers the skills globally. To install or update them manually:

    ```sh theme={null}
    npx skills add final-run/finalrun-agent -g
    ```

    Three slash commands are then available:

    | Command                   | What it does                                                                        |
    | ------------------------- | ----------------------------------------------------------------------------------- |
    | `/finalrun-generate-test` | Reads your source code, infers app identity, and generates complete YAML test specs |
    | `/finalrun-use-cli`       | Validates and runs your tests using the CLI                                         |
    | `/finalrun-test-and-fix`  | Runs the full generate → run → diagnose → fix loop until the test is green          |

    See [AI Agent Skills](/running/ai-agent-skills) for details.
  </Accordion>

  <Accordion title="Where are test artifacts stored?">
    Artifacts for each run — including video, screenshots, and device logs — are stored at:

    ```
    ~/.finalrun/workspaces/<workspace-hash>/artifacts/
    ```

    Use `finalrun runs` to list all recorded runs for your current workspace, and `finalrun start-server` to open the visual report UI where you can browse results interactively.
  </Accordion>
</AccordionGroup>