{"schema_version":"newruntime-agent-readable-v0.2","type":"post","stable_id":"post:vercel-ai-gateway-operating-budget","slug":"vercel-ai-gateway-operating-budget","title":"Vercel AI Gateway Adds Runtime Budget Controls","description":"Vercel's July 31 AI Gateway releases combine team and project spend budgets, unified fast mode, Laguna S 2.1 capacity, and updated MCP support into a practical inference control layer.","retrieval_nugget":"Vercel's July 31 AI Gateway releases combine team and project spend budgets, unified fast mode, Laguna S 2.1 capacity, and updated MCP support into a practical inference control layer. Vercel shipped four small AI Gateway updates on July 31. Read together, they are more useful than any one changelog line: AI Gateway is turning into an operating surface for agent.","status":"published","published_at":"2026-08-01","updated_at":"2026-08-01","record_date":"2026-08-01","date_kind":"published_at","topics":["inference","agents","api-design","developer-tools"],"source_urls":["https://vercel.com/changelog/ai-gateway-spend-budgets-and-alerts","https://vercel.com/changelog/ai-gateway-adds-unified-fast-mode-support","https://vercel.com/changelog/10x-more-capacity-for-laguna-s-2-1-on-ai-gateway","https://vercel.com/changelog/vercel-mcp-now-supports-the-2026-07-28-mcp-specification"],"visuals":[{"id":"vercel-ai-gateway-operating-budget","kind":"editorial-diagram","role":"hero","src":"https://newruntime.com/images/posts/vercel-ai-gateway-operating-budget.webp","alt":"Hand-drawn gateway diagram where agent jobs pass through budget gates, fast-mode routing, capacity lanes, and an MCP endpoint before reaching model providers.","caption":"AI Gateway is becoming an operating layer: cap spend, choose latency posture, absorb model capacity, and expose tools through newer MCP clients.","credit":"New Runtime synthesis from Vercel AI Gateway changelog","source_url":"https://vercel.com/changelog/ai-gateway-spend-budgets-and-alerts","generated_with":"gemini-3.1-flash-image","width":1600,"height":900,"legend":[{"label":"Budgets","description":"Team, project, and API-key caps can reject requests when any applicable budget is exhausted."},{"label":"Fast mode","description":"A unified speed setting routes to a fast tier when available and falls back to standard speed."},{"label":"Protocol","description":"The Vercel MCP endpoint supports the 2026-07-28 stateless protocol while keeping older clients working."}]}],"routes":{"html":"https://newruntime.com/posts/vercel-ai-gateway-operating-budget/","markdown":"https://newruntime.com/posts/vercel-ai-gateway-operating-budget.md","json":"https://newruntime.com/posts/vercel-ai-gateway-operating-budget.json"},"source_format":"markdown","next_reads":[{"type":"topic","path":"/topics/agents/","reason":"Explore the agents topic hub.","url":"https://newruntime.com/topics/agents/","title":"Agents - New Runtime","media_type":"text/html"},{"type":"topic","path":"/topics/api-design/","reason":"Explore the api design topic hub.","url":"https://newruntime.com/topics/api-design/","title":"API Design - New Runtime","media_type":"text/html"},{"type":"related_material","path":"/posts/voicebox-local-agent-voice-loop/","reason":"Shares agents and api design.","url":"https://newruntime.com/posts/voicebox-local-agent-voice-loop/","title":"Voicebox Turns Local Speech Into an Agent I/O Layer","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-agent-platform-control-plane/","reason":"Shares agents and api design.","url":"https://newruntime.com/posts/vercel-agent-platform-control-plane/","title":"Vercel's Agent Platform Surface Is Becoming a Control Plane","media_type":"text/html"},{"type":"related_material","path":"/posts/amazon-quick-agentic-catalog-context-boundary/","reason":"Shares agents and developer tools.","url":"https://newruntime.com/posts/amazon-quick-agentic-catalog-context-boundary/","title":"Amazon Quick Makes Catalog Semantics The Agent Boundary","media_type":"text/html"}]}