{"id":"clm_8C4E7C53434C","entity":"claude","predicate":"feature_added","value":"max_tokens parameter","value_json":{"feed":"claude-platform-release-notes","item":"https://platform.claude.com/docs/en/release-notes/overview#2026-06-02","tags":{"v":2,"ai":true,"by":"claude-haiku-5-5","on":"2026-11-10","themes":["developer_platform"]},"check":{"on":"2026-11-10","url":"https://platform.claude.com/docs/en/release-notes/overview#2026-06-02","pages":1,"quote":"June 2, 2026  The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses.","outcome":"checked"},"evidence":"The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses. Set tools[].max_tokens on the advisor tool definition; see Capping advisor output . · On the Claud","extracted_by":"claude-haiku-5-5","primary_source":true},"valid_from":"2026-06-02","valid_to":null,"published":"2026-06-02","recorded":"2026-11-10","citation":{"plain":"AsOf. \"Claude feature added: max_tokens parameter\", as of 2026-06-02. Claim clm_8C4E7C53434C, https://asof.is/claim/clm_8C4E7C53434C, accessed 2026-11-11. Source: https://platform.claude.com/docs/en/release-notes/overview#2026-06-02.","url":"https://asof.is/claim/clm_8C4E7C53434C","accessed":"2026-11-11"},"confidence":0.7,"status":"valid","assertable":true,"superseded_by":null,"supersedes":[],"first_seen_at":"2026-11-10T21:27:34.938652+00:00","updated_at":"2026-11-10T22:17:19.713939+00:00","sources":[{"url":"https://platform.claude.com/docs/en/release-notes/overview#2026-06-02","tier":"primary","publisher":"Anthropic","published_at":"2026-06-02T00:00:00+00:00"}],"evidence":{"by":"page-read","on":"2026-11-10","quote":"June 2, 2026  The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses.","url":"https://platform.claude.com/docs/en/release-notes/overview#2026-06-02","excerpt":"The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses. Set tools[].max_tokens on the advisor tool definition; see Capping advisor output . · On the Claud"},"legend":{"dates":"valid_from: when the claim took effect (a period figure: the day its period closed). published: the earliest day a source on the record published it (a filing's filing date, a post's date; null when no source carries one). recorded: the day AsOf first held it. A figure can take effect weeks before it is published.","citation":"citation: how to cite the row (plain: one sentence with the value, its as-of date, the claim id and URL, the day answered and the primary source; url: the claim page; accessed: the day answered). APA and BibTeX forms are on the claim page.","why_not":{},"checked_by":{"page-read":"its source page states the value and the date"}}}