Available through the Claude API with usage-based pricing.
Standard API pricing per 1 million tokens:
Input: $5
5-minute prompt cache write: $6.25
1-hour prompt cache write: $10
Prompt cache hits and refreshes: $0.50
Output: $25
Batch API pricing per 1 million tokens:
Input: $2.50
Output: $12.50
The full 1M-token context window is available at standard token rates.
US-only inference may apply a 1.1× multiplier to token pricing.
Availability and usage limits may vary across Claude plans and supported cloud platforms.
Commercial usage is subject to Anthropic’s applicable commercial terms and usage policies.
