Record reviewed readings of the week-43 and week-44 briefs.

Week 43 keeps the Kimi K3.1 Pro catalog row and the Claude Duet navigation label. Week 44 keeps GPT-6.1 Terra, the 29 October Mistral Large 4 fields, and the 30 October Max and Ultra plan text.

Assistant: grok
Assistant-Session: 01a1925d-3496-7011-a33e-6bfb99f4f4d3

data/publications/2181566caba12b0325c604b53168a6c02acaeddcc88cefaf3963d1a46ee60f23.json

@@ -0,0 +1 @@
+{"claims":[{"capture_id":"0dfc47ac722749067c30845c598b72023ebbabc0793b386bdac961bd4e65fa28","disposition":"included","statement":"The 22 October OpenRouter models capture does not list moonshotai/kimi-k3.1-pro."},{"capture_id":"252f74fe0aa7a965a8a875817768a9c1bdda4b9b765889c985080e230230c8cd","disposition":"included","statement":"The 23 October OpenRouter models capture lists moonshotai/kimi-k3.1-pro as MoonshotAI: Kimi K3.1 Pro, context 1048576, prompt 0.000002 and completion 0.00001 per token. The row does not state a percentage price cut, a parameter count, a weights-release date, or an index score."},{"capture_id":"97562814bb3287f7d90aac8e61bc8ae1d3e72c29d5c41438c65a22ca8c9c56c0","disposition":"included","statement":"The 25 October OpenRouter models capture lists moonshotai/kimi-k3.1-pro as MoonshotAI: Kimi K3.1 Pro, context 1048576, prompt 0.000002 and completion 0.00001 per token."},{"capture_id":"fd80ded2e526ed31478cc9c61df580c27ced3bf2cf162539fb257bd2e7f15a8f","disposition":"included","statement":"The 20 October capture of https://claude.com/pricing lists Max 5x and Max 20x. Its visible text does not contain Claude Duet or Ultra. Opus 5.5 is input $4 and output $20 per million tokens. Sonnet 5.5 is input $2 and output $10, with prompt-cache read $0.10."},{"capture_id":"8ed6957ba7cc0775dcaf10806865ba6e805a4d61930b6173d2612ac6b6a75dd2","disposition":"included","statement":"The 21 October capture of https://claude.com/pricing contains the navigation label Claude Duet in the header and footer. No other visible line names Duet. The page lists Max 5x and Max 20x and does not contain Ultra. Opus 5.5 is input $4 and output $20 per million tokens. Sonnet 5.5 is input $2 and output $10, with prompt-cache read $0.10."},{"capture_id":"4c3605a4ec142c2d51984278c2cfc49837398ef6f9bc2e8f6dbd922411a87182","disposition":"included","statement":"The 25 October capture of https://claude.com/pricing lists Opus 5.5 at input $4 and output $20 per million tokens, with prompt-cache read $0.20 and cache write $5. Sonnet 5.5 is input $2 and output $10, with prompt-cache read $0.10 and cache write $2.50. Haiku 5.5 is input $0.10 and output $0.50 per million tokens for prompts of at most 100,000 tokens, and input $0.50 and output $2.50 for longer prompts, with cache read $0.01 and $0.05 and cache write $0.125 and $0.625 on those two tiers. The page lists Max 5x and Max 20x, contains the navigation label Claude Duet, and does not contain Ultra."},{"disposition":"excluded","exclusion_reason":"The OpenRouter row is a separate included claim. It does not establish a percentage cut, a cost per task, a parameter count, a weights date, or an index score. No Moonshot, Artificial Analysis, or Epoch capture is in the ledger.","statement":"Kimi K3.1 Pro's Highspeed variant, the promised full weights, the 33% price cut, the cost of about $2.11 per task, the 2.8T/104B mixture-of-experts description, and the Artificial Analysis rank, Elo, and Terminal-Bench scores."},{"disposition":"excluded","exclusion_reason":"The pricing page adds a navigation label and does not describe the product. No Anthropic Duet announcement is captured.","statement":"Claude Duet as a research preview on a waitlist for US Pro and Max, a proactive Opus 5.5 agent with connected apps, its own cloud VM, and approval for consequential actions."},{"disposition":"excluded","exclusion_reason":"None of those primaries are captured in the ledger.","statement":"OpenAI's end of live-internet access for frontier-model training, the PHP disclosures, the OpenAI financing reports, the AWS capacity statement, the UK announcement, the EU harmonized standard, Anthropic's draft bill, and Moonshot's statement about training material together with China's draft export controls."},{"disposition":"excluded","exclusion_reason":"No Artificial Analysis or Epoch capture is in the ledger. The named Claude rates are a separate included claim.","statement":"The brief's Frontier cluster ordering, Epoch Capabilities Index figures, and the claim of no major broad price cuts."},{"disposition":"excluded","exclusion_reason":"Those labels need a task, five instruments, and comparable profiles. The compendium proposals, economics narrative, task-router notes, and look-ahead items depend on uncaptured announcements and index scores.","statement":"The brief's Frontier, Efficient, and Budget labels, its compendium accept, watch, and reject proposals, the economics narrative beyond the captured token fields, the task-router atlas notes, and the look-ahead items."}],"reviewed_at":"2026-10-31T17:22:56+01:00","reviewer":"grok","schema_version":1,"title":"Week 43 brief against ledger captures"}