Anthropic Message Threads cut first-token time by about 35% on very long API chats
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Anthropic released Message Threads in public beta on Claude’s Messages API so each turn sends only new messages instead of the full history. For requests of 500,000 to one million tokens, time to first token drops by about 35%. Coding, computer-use, and heavy document or image workflows gain most; threads stay encrypted in memory, expire after five minutes idle, and token use is unchanged because Claude still reads full history. It runs on Claude, AWS, Microsoft Foundry, and Google Cloud.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu