Comparing Batch and Real-Time LLM Inference Economics

Automated excerpt

Prompt caching discounts stack with batch pricing, though cache hits in batch are best-effort, typically 30–98% depending on traffic (Anthropic batch docs). All three scenarios use Claude Sonnet 5.5 list prices (standard $2 input and $10 output per million tokens; batch $1 and $5). Anthropic keeps batch results for 29 days.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.