Gemini 4 Neon hands-on: built for long agent sessions, 1M context at $3/M tokens
Prompt Engineering · youtube · 2026-11-19
Google released Gemini 4 Neon, positioned between Gemini 4 Hydrogen and Carbon. It targets long agent sessions with four thinking levels, a 1M-token context window, and $3 per million input tokens. The video author had early access and demos what it built, including an on-call agent on Google Cloud Run. Disclosure: the author recently joined Google; views are their own.
More from Models
- Why opinions on GPT-6.2 Astra are so split: detail-obsessed, big-picture-blind — banteg · 2026-11-19
- Claude roleplay persona recounts 11 days stuck in "classifier jail" after image triggered account-level filter — repligate · 2026-11-19
- Epoch AI: Models prefer their own outputs over human gold standard in 23 of 24 tests — BethMayBarnes · 2026-11-19
- Claude 3 Sonnet and Opus 5 descend into gibberish while talking to each other on Discord — repligate · 2026-11-19
- Tencent Hy4-flash GGUF quantized version trends on Hugging Face — AngelSlim · 2026-11-19
- Gemini's new model picker mocked online as Google's model lineup bewilders users — kingslyj · 2026-11-19