According to Anthropic, Fast Mode delivers responses approximately 2.5× faster than the standard configuration while maintaining the same output quality. The company positions the feature for latency-sensitive workflows such as live debugging, rapid code iteration, and other time-critical tasks.

Anthropic emphasizes that the standard mode remains better suited for long-running autonomous tasks, batch processing, CI/CD pipelines, and cost-sensitive workloads.

Pricing comparison

Standard Fast Mode
Input ≤ 200K tokens $5 / MTok $30 / MTok
Input > 200K tokens $10 / MTok $60 / MTok
Output ≤ 200K tokens $25 / MTok $150 / MTok
Output > 200K tokens $37.50 / MTok $225 / MTok

Availability

Fast Mode can be enabled in Claude Code using the /fast command and is also available through integrations with Cursor, GitHub Copilot, Figma, and Windsurf.

Anthropic is offering a 50% introductory discount on Fast Mode until February 16.

The feature is not supported on Amazon Bedrock, Google Vertex AI, or Microsoft Azure Foundry. Anthropic plans to expand API availability, with interested users able to join a waiting list.