Fast mode for Opus 4.7 available on AI Gateway

By Steven Van · 2026-05-12

Claude Opus 4.7 gets an experimental fast mode on Vercel's AI Gateway, generating output about 2.5x faster at 6x the price.

Vercel's AI Gateway now offers fast mode for Claude Opus 4.7, in research preview. Fast mode generates output tokens about 2.5 times faster while keeping full Opus 4.7 intelligence, though Vercel describes it as an early, experimental feature.

To enable it, pass speed: 'fast' in the anthropic provider options alongside anthropic/claude-opus-4.7.
Claude Code can use fast mode through AI Gateway by setting the CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK and CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE variables in a shell configuration file or in ~/.claude/settings.json.
Fast mode is priced at 6x standard Opus rates: $30 per 1M input tokens and $150 per 1M output tokens, versus $5 and $25 standard. Standard pricing multipliers, such as prompt caching, still apply on top.

Vercel

The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.

View Vercel →

Read the original announcement →