OpenCode slashes AI coding costs by 80% with two new Gemini models

OpenCode adds Gemini 3.6 Flash and 3.5 Flash Lite with 1M context. The lite model is 80% cheaper than 3.5 Flash, a pricing shift that could make AI coding the default for more teams.

Emmanuel Fabrice Omgbwa Yasse AI-assisted

2026-07-21 · Last updated: 2026-08-03 · 1 min read

X in f

OpenCode slashes AI coding costs by 80% with two new Gemini models — Sources : OpenCode on X

OpenCode, the open-source AI code editor that ships models as interchangeable components, added two new Gemini variants on July 21: Gemini 3.6 Flash and

Source : OpenCode on X

Get the tech essentials in 3 minutes every morning

One email, every weekday, with what actually matters in AI and tech.

#AI coding #context window #Gemini 3.5 Flash Lite #Gemini 3.6 Flash #opencode

LLMs & Models

Xiaohongshu's dots3-note: a 280B open MoE that only activates 16B

Qwen / Alibaba

Alibaba's biggest model coded alone for 16 days. Next week, its weights go public.

LLMs & Models

LFM2.5-Encoders make the small-model case: 3.7× faster than ModernBERT on CPU

41 companies, one message: open-weight AI is America's best bet

LLMs & Models

The 2.8 trillion parameter model that beats the frontier on the benchmarks that matter

OpenCode slashes AI coding costs by 80% with two new Gemini models

Related articles

Discover

Open Design takes on Claude Design from your own machine

An AI boss that ignores replies pushes its underling into an 'alien' state

Cursor joins SpaceX, trading independence for the world's largest GPU fleet

Nobody can define AI slop. SlopFinder is averaging the answer

Muon groks modular addition faster, then its solutions collapse

LLMs know accounting formulas. FinIndices shows they can't apply them

Xiaohongshu's dots3-note: a 280B open MoE that only activates 16B

Apple wants up to 15% on the linkout sales it says cost it nothing