Opus 4.6 Fast Mode available on AI Gateway
By Steven Van ·
Vercel's AI Gateway adds an experimental Fast Mode for Claude Opus 4.6, running 2.5x faster at 6x the standard price.
Vercel's AI Gateway now offers Fast Mode for Claude Opus 4.6, a premium option that runs the model at 2.5x faster output token speeds with the same intelligence. Vercel describes it as an early, experimental feature aimed at human-in-the-loop workflows, such as running large coding tasks without a context switch or getting planning results without a long wait.
- Fast Mode is enabled by setting speed: 'fast' in the Anthropic provider options when calling the model through the AI SDK.
- It also works with Claude Code via AI Gateway, by setting the CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK variable in a shell configuration file or in ~/.claude/settings.json.
- It can be tried directly in the AI Gateway playground for Opus 4.6.
- Fast Mode is priced at 6x standard Opus 4.6 rates: $30 per million input tokens and $150 per million output tokens, compared with $5 and $25 standard. Normal pricing multipliers, such as prompt caching, still apply on top.
The announcement notes this is an early release.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →