Gemini 3.6 Flash docs added: Google’s newest speed-tier Flash model with stronger reasoning, 1M context, $1.50/1M input and $7.50/1M output, and 90% cached-input discount; draws from the API usage pool.
Changelog
Models
Gemini 3.6 Flash docs added: Google’s newest speed-tier Flash model with stronger reasoning, 1M context, $1.50/1M input and $7.50/1M output, and 90% cached-input discount; draws from the API usage pool.
Gemini 3.5 Flash and Gemini 2.5 Flash updated to recommend Gemini 3.6 Flash (3.5 is now previous-generation; 3.6 has a lower output price than 3.5).
SDK
SDK Changelog page added for @cursor/sdk (npm) and cursor-sdk (PyPI), covering 1.0.20–1.0.24: aligned TS/Python releases, token usage on runs, per-send cloud env vars, structured run errors, more reliable long streams, and Bun support.