# Aperture how-to guides Last validated Apr 9, 2026 * [Build a custom webhook](/docs/aperture/how-to/build-custom-webhook) — Create a custom webhook integration to send Aperture event data to your own services. * [Check and refill budgets](/docs/aperture/how-to/check-and-refill-budgets) — Check the status of Aperture quota buckets and manually refill balances using the Aperture dashboard. * [Configure zero-retention mode](/docs/aperture/how-to/configure-zero-retention) — Configure Aperture so it never stores prompt and response content on disk, to minimize data at rest and meet strict internal or contractual data-handling requirements. * [Enable the chat sandbox](/docs/aperture/how-to/enable-sandbox) — Enable the sandbox feature so the Aperture assistant can run code, edit files, and produce downloadable artifacts in conversations. * [Export usage data to S3](/docs/aperture/how-to/export-usage-data-to-s3) — Configure Aperture to export LLM usage data to an Amazon S3 bucket for analysis, archiving, and long-term retention. * [Filter logs by header](/docs/aperture/how-to/filter-logs-by-header) — Index request and response headers in Aperture so you can filter the dashboard Logs page by header presence or value. * [Grant access to MCP tools](/docs/aperture/how-to/grant-mcp-tool-access) — Configure Aperture grants to control which connector capabilities users can access, including MCP tools, resources, templates, and HTTP proxy access. * [Grant access to models](/docs/aperture/how-to/grant-model-access) — Configure Aperture grants to control which models each user or group can access. * [Manage sandbox operations](/docs/aperture/how-to/manage-sandbox) — Monitor sandbox health, understand the security properties of the Aperture chat sandbox, and turn the feature on or off. * [Set a team-wide budget](/docs/aperture/how-to/set-team-budget) — Configure a shared quota bucket in Aperture to cap total AI spending across your organization. * [Set per-user spending limits](/docs/aperture/how-to/set-per-user-spending-limits) — Configure quota buckets in Aperture to set spending limits for individual users. * [Set up a guardrail](/docs/aperture/how-to/set-up-guardrails) — Configure a pre-request hook to inspect, modify, or block LLM requests before they reach the provider. * [Set up a per-user OAuth 2.0 connector](/docs/aperture/how-to/set-up-per-user-oauth2-connector) — Connect Aperture to an external service that requires individual user consent using the OAuth 2.0 authorization code flow. * [Set up a self-hosted provider](/docs/aperture/how-to/use-self-hosted) — Configure a self-hosted or locally running LLM server as a provider in Aperture so your team can access private models through your tailnet. * [Set up admin access](/docs/aperture/how-to/set-up-admin-access) — Configure administrator roles for managing Aperture settings and accessing all user data. * [Set up Amazon Bedrock](/docs/aperture/how-to/use-amazon-bedrock) — Configure an Amazon Bedrock provider in Aperture so your team can access foundation models through AWS. * [Set up an HTTP API connector](/docs/aperture/how-to/set-up-http-api-connector) — Configure Aperture to proxy requests to an upstream REST API with automatic credential injection. * [Set up Anthropic](/docs/aperture/how-to/use-anthropic) — Configure an Anthropic provider in Aperture so your team can access Claude models. * [Set up Google Gemini](/docs/aperture/how-to/use-google-gemini) — Configure a Google Gemini provider in Aperture so your team can access Gemini models using the direct Gemini API. * [Set up Microsoft Foundry](/docs/aperture/how-to/use-microsoft-foundry) — Configure Microsoft Foundry providers in Aperture so your team can access OpenAI GPT and Anthropic Claude models deployed in Foundry. * [Set up OpenAI](/docs/aperture/how-to/use-openai) — Configure an OpenAI provider in Aperture so your team can access GPT models. * [Set up OpenRouter](/docs/aperture/how-to/use-openrouter) — Configure an OpenRouter provider in Aperture so your team can access models from multiple providers through a single aggregator. * [Set up passthrough mode](/docs/aperture/how-to/use-passthrough-mode) — Configure an Aperture provider to forward each client's own credential, including subscription OAuth tokens, to the upstream provider instead of injecting a shared API key. * [Set up the chat UI](/docs/aperture/how-to/set-up-chat-ui) — Enable Aperture's chat UI so your users can talk to LLMs directly through their browser. * [Set up Vercel AI Gateway](/docs/aperture/how-to/use-vercel) — Configure a Vercel AI Gateway provider in Aperture so your team can access models from multiple LLM providers. * [Set up Vertex AI](/docs/aperture/how-to/use-vertex-ai) — Configure a Vertex AI provider in Aperture with a GCP service account and key file so your team can access Gemini and Claude models through Aperture. * [Use Claude Code Action with Aperture](/docs/aperture/how-to/use-claude-code-action) — Configure the Claude Code GitHub Action to route requests through Aperture so CI runners authenticate with Tailscale identity instead of individual API keys. * [Use Claude Code with Aperture](/docs/aperture/how-to/use-claude-code) — Configure Claude Code to route requests through your Aperture proxy. * [Use Claude Desktop with Aperture](/docs/aperture/how-to/use-claude-desktop) — Configure the Claude Desktop app to route model inference through your Aperture proxy. * [Use Codex with Aperture](/docs/aperture/how-to/use-codex) — Configure OpenAI Codex to route requests through your Aperture proxy. * [Use OpenAI-compatible tools with Aperture](/docs/aperture/how-to/use-openai-compatible-tools) — Configure Gemini CLI, Roo Code, Cline, and other OpenAI-compatible tools to route requests through Aperture. * [Use OpenCode with Aperture](/docs/aperture/how-to/use-opencode) — Configure OpenCode to route requests through your Aperture proxy.