{"slug": "ai-gateway-adds-unified-fast-mode-support", "title": "AI Gateway adds unified fast mode support", "summary": "Vercel's AI Gateway has launched a unified fast mode abstraction in beta, allowing users to request lower-latency or higher-throughput serving for any supported model by setting speed to 'fast' under providerOptions.gateway, with automatic fallback to standard speed when unavailable. Fast mode trades higher per-token cost for performance and is accessible via a 'speed' option or direct fast slugs like 'anthropic/claude-opus-5-fast', with support for a growing set of models marked by a lightning bolt in the models list.", "body_md": "AI Gateway has a unified fast mode abstraction, now in beta.\n\nYou can now request [fast mode](https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode) the same way for every model on AI Gateway. Set speed to `fast`\n\n, and the gateway serves the fast tier when it's available and falls back to standard speed when it isn't.\n\nFast mode trades a higher per-token cost for lower latency or higher throughput. You get it wherever it is available, without pinning a provider or wiring anything up yourself.\n\nSet `speed`\n\nto `fast`\n\nunder `providerOptions.gateway`\n\nto upgrade the model to its fast serving path when one is routable:\n\nYou can also address a fast variant directly with its fast slug, such as `anthropic/claude-opus-5-fast`\n\n, which is the same as setting `speed: 'fast'`\n\non the base model.\n\nUse the `speed`\n\noption when you want to stay on the base model ID and fall back to standard speed. Use a fast slug when you want to name the fast variant directly, for example in a `gateway.models`\n\nfallback list. The `speed`\n\noption works across every AI Gateway API format.\n\nFast mode is available for a growing set of models. Find them in the [models list](https://vercel.com/ai-gateway/models?features=fast) with a lightning bolt next to the slug. Requesting fast mode on a model with no fast tier has no effect, and the request runs at standard speed. Fast variants of models are usually more expensive than the base model: check [pricing](https://vercel.com/ai-gateway/models?features=fast) for more details.\n\nIn Claude Code, toggle fast mode with `/fast`\n\nfor Anthropic Opus models after [setup](https://vercel.com/docs/ai-gateway/coding-agents/claude-code#enabling-fast-mode). For other agents, select a fast slug in your model configuration, such as `anthropic/claude-opus-5-fast`\n\n.\n\nFor more information about fast mode, read the [documentation](https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode).", "url": "https://wpnews.pro/news/ai-gateway-adds-unified-fast-mode-support", "canonical_source": "https://vercel.com/changelog/ai-gateway-adds-unified-fast-mode-support", "published_at": "2026-07-29 00:00:00+00:00", "updated_at": "2026-07-29 18:42:51.326457+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-products", "developer-tools"], "entities": ["Vercel", "AI Gateway", "Anthropic", "Claude Code"], "alternates": {"html": "https://wpnews.pro/news/ai-gateway-adds-unified-fast-mode-support", "markdown": "https://wpnews.pro/news/ai-gateway-adds-unified-fast-mode-support.md", "text": "https://wpnews.pro/news/ai-gateway-adds-unified-fast-mode-support.txt", "jsonld": "https://wpnews.pro/news/ai-gateway-adds-unified-fast-mode-support.jsonld"}}