Loading pattern preview
BlocksAgent Patterns
OpenAI Prompt Caching (AI Gateway)
OpenAI Prompt Caching (AI Gateway)
Lightweight ToolLoopAgent pattern for OpenAI prompt caching through Vercel AI Gateway: stable system instructions, promptCacheKey, and per-turn cachedPromptTokens metrics.
Use this when your OpenAI agent resends the same system prompt each turn and you want to cache it through AI Gateway using promptCacheKey.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Enable OpenAI prompt caching with promptCacheKey via AI Gateway
- Reuse a stable system prefix across ToolLoopAgent turns
- Inspect cachedPromptTokens from provider metadata
Use cases
Products and workflows this pattern is designed to support.
- Lowering cost on repeated agent system prompts
- Teaching promptCacheKey grouping with ToolLoopAgent
- Comparing cache metrics across multi-turn sessions
Compare with
Similar patterns, and when each one is the better fit.
Anthropic Cache Control (AI Gateway)Use this when you need to set Anthropic cache breakpoints on a ToolLoopAgent's instructions and compare cache write versus cache read tokens per turn.
AI SDK Prompt Few-Shot EditorUse this when you need to write a prompt with editable input/output examples and test it against sample cases before using it.
Generate Image (OpenAI)FreeUse this when your app should generate images from prompts on OpenAI GPT Image via AI SDK generateImage and the AI Gateway.
Generate TextFreeUse this when you need a minimal API route that calls an AI Gateway model with generateText and returns one finished plain text response.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
ToolLoopAgentgatewayproviderOptionsstepCountIsProviders
OpenAI
Files added
8 files
app/page.tsxapp/layout.tsxapp/api/cache-openai/route.tslib/cache-openai-agent.tslib/cache-metrics.tslib/stable-system-prompt.tslib/request-utils.tsREADME.md
Dependencies
9 total
npm packages
5AISDKlucide-reactNext.jsReactZod
Registry components
alertbadgebuttonskeleton
Critical files
2 files
lib/cache-openai-agent.tsToolLoopAgent with gateway model, stable instructions, and providerOptions.openai.promptCacheKey.
cache-openai/route.tsRuns agent.generate({ messages }) and returns text plus cachedPromptTokens metrics.
Requirements
- Complexity
- Intermediate
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 256MB
