max_tokens parameter to cap the advisor model's output per call, reducing latency and output token cost for workloads that don't need full-length responses.stop_reason: "refusal" without generated output are no longer billed.Fetched June 4, 2026
Claude Fable 5 ( ) and Claude Mythos 5 ( ) launched with 1M token context window by default, 128k max output tokens, and always-on adaptive…
Anthropic · Claude Platform- The code execution tool now supports , which discloses the 90-second per-cell execution time limit in the tool description so Claude can…
Anthropic · Claude PlatformChatAnthropic requests no longer send when the user never configured thinking, fixing 400 errors on adaptive-only models like claude-fable-…
LangChain · LangChain.jsProduct changes - IP address filtering for enterprise plans -- Enterprise organizations can now restrict all API key usage to approved IP a…
OpenRouter · Changelog