AI BriefingOpus 4.6 Fast Mode Now Available on AI Gateway
Key point
AI Gateway now supports Fast mode for Claude Opus 4.6, boosting output speed by 2.5x.
Details
AI Gateway now supports Fast mode for Claude Opus 4.6. This feature is a premium option that increases output token speed by 2.5x while maintaining the same model intelligence, and it is currently an early-stage experimental feature.
The faster output is especially useful in workflows that require human involvement. It's tailored for continuing large-scale coding tasks without context switching, or receiving planning results without long waits.
Here's how to enable it:
- In the AI SDK, add
speed: 'fast'to theanthropicprovider options. - For Claude Code via AI Gateway, set
"fastMode": trueinsettings.json. - You can try Opus 4.6's fast mode directly in the AI Gateway playground.
Pricing is 6x the standard Opus rate. While the standard rate is $5 / 1M tokens for input and $25 / 1M tokens for output, Fast mode is priced at $30 / 1M tokens for input and $150 / 1M tokens for output. Standard pricing multipliers, such as prompt caching, are applied on top of this rate.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Claude Code Fails to Load AGENTS.md When Telemetry Is Disabled, With WorkaroundClaude Code Update: Memory Warnings, MCP Timeout Controls, and Stability Improvements