Browsing Tag
Prompt Caching
3 posts
LLM prompt caching, cache-read and cache-write pricing, latency, and production architecture.
Claude API Message Threads Cut Long-Agent Waits, Not Token Bills
Anthropic says Claude message threads cut first-token wait times about 35% in very long sessions. Here is how expiry, replay, caching and privacy limits work.
GPT-6.1 Terra Is Built for Computer Use at $1/$5 per Million Tokens
OpenAI's GPT-6.1 Terra lowers API prices for visual and computer-use agents, but long-context multipliers, reasoning effort and tool requirements shape the real cost.
Claude Haiku 5.5 Is Cheap Until Long Prompts Trigger a 5x Rate
Claude Haiku 5.5 starts at $0.10 per million input tokens, but prompts over 100K cost five times more. Here is how to budget and migrate.