> ## Documentation Index
> Fetch the complete documentation index at: https://docs.4096bytes.com/llms.txt
> Use this file to discover all available pages before exploring further.

# User guide

> Connect 4096bytes to your AI coding clients and engineering tools

4096bytes gives developers an AI model access layer that fits real coding workflows. Create an API Key in the dashboard, then import it into clients such as Codex, OpenCode, OpenClaw, Claude Code, Cursor, and Cherry Studio, or connect it to your own workflow through Codex SDK.

<Tip>
  Use the Base URL, model name, and API Key shown in the dashboard. This documentation explains where to configure each value, so you do not copy stale settings.
</Tip>

## Who it is for

| User                       | Typical use                                                                                       |
| -------------------------- | ------------------------------------------------------------------------------------------------- |
| Terminal and IDE users     | Connect models to Codex, OpenCode, OpenClaw, Claude Code, Cursor, and other development tools.    |
| AI tool users              | Manage, switch, and organize models in clients such as Cherry Studio and CC Switch.               |
| App developers             | Use Codex SDK to connect Codex to internal tools, automation workflows, or engineering platforms. |
| Small teams                | Give members a shared model entry point with separate keys and limits.                            |
| Operations and cost owners | Review supported models, pricing, balance usage, rate changes, and request errors.                |

## Start here

<Card title="Create an account" icon="user-plus" href="/en/quickstart/create-account">
  Sign in to the dashboard and prepare to manage plans, balance, and API Keys.
</Card>

<Card title="Get an API Key" icon="key" href="/en/quickstart/get-api-key">
  Create a client API Key and learn how to store it safely.
</Card>

<Card title="Supported models and pricing" icon="badge-dollar-sign" href="/en/quickstart/models-pricing">
  Review current models, input and output costs, cache pricing, and discount notes.
</Card>

## Connect common clients

If you already have an API Key, open the client page you need.

<Card title="CC Switch" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/cc-switch.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=0ec4f82f4f92e6442054c58010338af3" href="/en/clients/cc-switch" width="128" height="128" data-path="images/logos/clients/cc-switch.png">
  Import 4096bytes into CC Switch and manage CLI providers in one place.
</Card>

<Card title="Codex" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/openai.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=d517ae42b29ac4ddd1e99bc9f874c488" href="/en/clients/codex" width="200" height="200" data-path="images/logos/clients/openai.png">
  Configure 4096bytes in Codex for terminal and local development tasks.
</Card>

<Card title="Codex Desktop" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/openai.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=d517ae42b29ac4ddd1e99bc9f874c488" href="/en/clients/codex-desktop" width="200" height="200" data-path="images/logos/clients/openai.png">
  Reuse the Codex CLI config in the Codex desktop app.
</Card>

<Card title="Codex VS Code extension" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/vscode.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=81d021b561a36b94fd002b40f6a61452" href="/en/clients/codex-vscode" width="256" height="256" data-path="images/logos/clients/vscode.png">
  Reuse the local Codex CLI config in VS Code.
</Card>

<Card title="OpenCode" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/opencode.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=f271f1689289d8722e5adafe12709779" href="/en/clients/opencode" width="48" height="48" data-path="images/logos/clients/opencode.png">
  Write the dashboard-generated Provider config into OpenCode.
</Card>

<Card title="OpenClaw" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/openclaw.svg?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=179eb8929c0b5d3100446b09b4b107b9" href="/en/clients/openclaw" width="500" height="500" data-path="images/logos/clients/openclaw.svg">
  Configure 4096bytes as a custom model Provider in OpenClaw.
</Card>

<Card title="Claude Code" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/anthropic.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=e38babdeca4ea490d2ee8f59dc2c9cef" href="/en/clients/claude-code" width="48" height="48" data-path="images/logos/clients/anthropic.png">
  Use the Claude Code compatible settings shown in the dashboard.
</Card>

<Card title="Cursor" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/cursor.svg?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=d597fb20ef60775c6e9b60bfdfa55fe5" href="/en/clients/cursor" width="512" height="512" data-path="images/logos/clients/cursor.svg">
  Configure a custom provider and model in Cursor.
</Card>

<Card title="Cherry Studio" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/cherry-studio.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=3bdb53431db4e962250e948bffcf1ff9" href="/en/clients/cherry-studio" width="1024" height="1024" data-path="images/logos/clients/cherry-studio.png">
  Add 4096bytes as a provider and test the connection.
</Card>

## Connect SDKs

<Card title="Codex SDK" icon="https://mintcdn.com/4096bytes/7pWq1xzEcc7dxxRs/images/logos/clients/openai.png?fit=max&auto=format&n=7pWq1xzEcc7dxxRs&q=85&s=d517ae42b29ac4ddd1e99bc9f874c488" href="/en/sdk/codex-sdk" width="200" height="200" data-path="images/logos/clients/openai.png">
  Call Codex from your application, internal tool, or automation workflow.
</Card>

## Troubleshooting

If configuration fails, start with [FAQ](/en/faq). If the issue is still unresolved, see [Contact us](/en/contact) for the information to include.