[{"data":1,"prerenderedAt":29},["ShallowReactive",2],{"nr-en-anthropic-message-threads-time-to-first-token":3},{"slug":4,"title":5,"dek":6,"date":7,"time":8,"publishedAt":9,"updated":10,"updatedAt":10,"dateFmt":11,"updatedFmt":10,"kind":12,"tier":13,"author":14,"authorName":15,"topics":16,"tracker":21,"trackerLabel":22,"headlineStat":23,"image":24,"ogImage":25,"imageAlt":5,"csv":10,"minutes":26,"words":27,"html":28},"anthropic-message-threads-time-to-first-token","Anthropic launches Message Threads for Claude – according to the provider, 35 percent faster first response in long conversations","The new public beta aims to speed up long-running AI agents by transmitting only what is new since the last message. According to the company, token usage remains unchanged.","2026-11-03","14:20","2026-11-03T14:20:00+01:00","","November 3, 2026","news","standard","ideal-syka","Ideal Syka",[17,18,19,20],"Anthropic","Claude","AI agents","Latency","\u002Fki-latenz","Measure AI latency","35% shorter time to first token (per Anthropic, 500,000–1M tokens)","\u002Fnewsroom\u002Fimg\u002Fanthropic-message-threads-time-to-first-token.webp","\u002Fog-nr\u002Fanthropic-message-threads-time-to-first-token.en.png",1,186,"\u003Cp>Anthropic has released Message Threads as a public beta on its Claude platform. Until now, every request had to resend the entire conversation history. With Message Threads, only what is new since the last message is transmitted.\u003C\u002Fp>\n\u003Ch2>What the provider measured\u003C\u002Fh2>\n\u003Cp>According to Anthropic, time to first token falls by about 35 percent for requests between 500,000 and one million tokens. Coding agents, computer-use agents, and workflows processing many documents or images are said to benefit most.\u003C\u002Fp>\n\u003Ch2>Limitations\u003C\u002Fh2>\n\u003Cp>The thread stays encrypted in memory between requests and expires after five minutes of inactivity. Token usage remains unchanged, since Claude still reads the full conversation history. The 35 percent figure is the provider's own claim for the stated token range.\u003C\u002Fp>\n\u003Ch2>Classification\u003C\u002Fh2>\n\u003Cp>Teams running long agent workflows can evaluate the change once the feature is available in their environment. Whether it delivers a noticeable benefit depends on conversation length and latency requirements and should be assessed with your own measurements.\u003C\u002Fp>\n\u003Ch2>Sources\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fthe-decoder.de\u002Fanthropic-beschleunigt-langlaufende-ki-agenten-mit-neuen-message-threads\u002F\">The Decoder (DE)\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fthe-decoder.com\u002Fanthropics-message-threads-cut-time-to-first-token-by-35-percent-for-long-conversations\u002F\">The Decoder\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cem>Editorially owned by \u003Ca href=\"\u002Fen\u002Fautor\u002Fideal-syka\">Ideal Syka\u003C\u002Fa>. Sources and method: \u003Ca href=\"\u002Fen\u002Fredaktion\">Newsroom & method\u003C\u002Fa>. Tips and corrections: \u003Ca href=\"mailto:ai@i6eal.de\">ai@i6eal.de\u003C\u002Fa>.\u003C\u002Fem>\u003C\u002Fp>\n",1793719846233]