Prompt caching

Pattern

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.

BeginnerJun 2026View the full pattern on desktop
OpenAI Prompt Caching (AI Gateway) preview

Problems solved

  • Enable OpenAI prompt caching with promptCacheKey via AI Gateway
  • Reuse a stable system prefix across ToolLoopAgent turns
  • Inspect cachedPromptTokens from provider metadata

Use cases

  • Lowering cost on repeated agent system prompts
  • Teaching promptCacheKey grouping with ToolLoopAgent
  • Comparing cache metrics across multi-turn sessions

AI SDK APIs

ToolLoopAgentgatewayproviderOptionsstepCountIs

Tags

aiagentsprompt-cacheopenaiai-gatewayprovider-optionstool-loop-agent

Requirements

Node.js
24+
Memory
256MB
Other
  • Vercel AI Gateway API key

Environment variables

External services

openai

Ready to use?

View the full interactive pattern with live preview and copy the source code.

View the pattern on desktop

Related patterns

Anthropic Cache Control (AI Gateway)Lightweight ToolLoopAgent pattern for Anthropic ephemeral cache control through Vercel AI Gateway: cached system instructions with cacheControl and reports cache read/write tokens.Jun 2026
Sub-Agent OrchestratorCustom Agent implementation demonstrating the Agent interface abstraction with an orchestrator that routes queries to specialized sub-agents (research, analysis, support). Shows options passing and structured outputs.Nov 2025
Just Bash Skills AgentMinimal ToolLoopAgent chat demo: on-call-style skills (incident triage + stakeholder comms) on disk, skill tool loads SKILL.md + paths, readFile pulls reference checklists and templates from the sandbox.Apr 2026
Multi-Step Tool PatternExecute multi-step workflows with typed tools. Includes streaming, tool chaining, and decision-making for automated tasks.Oct 2025