Fast move on the workhorse tier. Matters if you build anything agentic 👇 The news: 3.7 Flash launched just three weeks after 3.6, at half the token cost — $0.75/M input, $3.75/M output, locked through Dec 31. The gains are real: → DeepSWE coding: 49% → 65.3% → Reportedly beats Claude Sonnet 5 and GPT-5.6 on coding → 1M context, better multi-step planning and tool calls The bigger move: Gemini Spark — Google's 24/7 personal agent for Pro/Ultra — now runs on 3.7 Flash. The agent working between your sessions just got a real bump, especially for Workspace tasks. My take: Google isn't chasing the frontier crown right now — their flagship 3.5 Pro is still delayed. They're dominating the workhorse tier instead: the cheap, fast, good-enough model you actually run at scale. Smart. Most agentic workflows don't need the smartest model — they need a reliable one cheap enough to run thousands of times. For builders: The intro pricing is a defined window to test cost-per-task before rates double in January. Use it. And this is the price war I keep flagging, now three-way — Claude doubled Cowork limits, OpenAI gamified resets, Google halved Flash pricing. Every lab's fighting for the builder. You win. Stay model-agnostic and ride whoever's cheapest for the job. Caveat: still no EU availability. Check your region first. Running Gemini Flash in any workflows yet, or all-in on Claude/OpenAI? 👇

Hi I have developed an appointment booking and general practice questions answerer in n8n (via Telegram and Email) and also made available on ElevenLabs. I started with a moderate sized system prompt which I evolved to address issues as they came and also added examples. I eventually ended up with a system prompt of size 25 KB. I noticed that only the top level LLMs, particularly Gemini 2.5 Flash were able to accurately handle the system prompt effectively and follow instructions. My question is how large a system model can practically grow? Is things like 25 KB too large? Is it better to reduce the system prompt size may be by removing the examples? Generally, scheduling scenarios are complex and I noticed I needed to address many cases, but now I feel only Gemini 2.5 Flash and GPT 4.1 are only capable of following on. Regards Shadi Ghaith