Ask HN: What default model do you use and why?
I'm curious about which default AI model other developers rely on for their daily work and the reasoning behind their choice. I've been using Claude for most tasks, but I've found that Fable is often overkill and quickly consumes my Max plan's session credits—for example, during an initial mobile app planning session with 4 agents, it burned through credits in minutes, and after a 6-hour timeout, the cache expired and used 2% of the session in under a minute. So I've switched to Opus 4.8 as my goto and plan to avoid 5 until I see a compelling reason to switch back; 4.8 is 'good enough' for my needs and has been a great value, mostly getting things right for my web, mobile, and cloud backend work.
I use claude for most of what I do, and Fable is largely overkill for me and frequently burns through my Max plan's session credits in minutes (!) when just doing an initial mobile app planning with 4 agents. After I waited out the timeout period 6 hours later, and I picked up again, the cache had timed out so it burned through 2% of the session in less than a minute. Opus 4.8 is now my goto and I will be avoiding 5 until I see a reason to switch back. 4.8 is 'good enough' for what I need and has been a great value. It mostly gets things right. Most of what I do is web and mobile , largely cloud backend.
- o_m
I used to main Claude, but I can't stand how it writes. I feel like I'm wasting too much time trying to decipher the output. Adding writing rules does not seem to work. Now I use GPT 5.6 Terra high fast mode, with Luna for everything else. I might consider using Sol for planning. I can't stand using Sol or smarter models for coding, because they will eventually try to rewrite everything in the codebase.
I also don't want to use the Claude Code and Codex agent harnesses. The good thing with Codex subscription is that it can be used in other harnesses, unlike Claude. As far as I know, only Anthropic has this restriction.
- hgoel
For personal needs I use a local Qwen3.8-Next-Flash setup on a GB10 cluster. For work, Github Copilot with either GPT 5 mini or toss up between Opus/Sol depending on the complexity of the task.
Used to pay for a Claude 20x plan and did everything in Opus, but I hate how it talks now and recent events (OAI scooping, Anthropic's spying, third party Chinese model hosts stealing and selling credentials) have really pushed me towards local AI for personal needs. Am not allowed to use Chinese models for work even if self-hosted so not much choice there.
- vallerie
I've found good success with the new Gemini models on Antigravity. Granted I use my models either:
- like a fancy auto complete (here are some stub methods, they should do X, fill them in)
- using fairly detailed plans and test harnesses, so blowing up the world is hard
The 3.X Flash family have been fairly capable models, and the selling point for me is just raw speed. Gemini is noticeably faster than the competition, about 3-4x, and I just get work done faster with it.
That said I'm keeping an eye on Open Weights. DS4 Flash was good until price hikes, and finding a provider that serves at high speed and without quantisation at the prior price is tricky.
- montroser
It pains me to read these answers so far. Listen, for 99%+ of your web and mobile tasks, deepseek-v4.1-flash is all you need. It is blazing fast, super cheap, and quite proficient. It acts responsibly, has top-notch vision for evaluating its own UI work, and is far less smug and flowery than any of the Anthropic models.
For what it's worth, here's a take on its speed vs cost vs intelligence: https://artificialanalysis.ai/models/deepseek-v4-1-flash
I can go all day and night with this thing with multiple sessions going, and I spend like $2 per day retail. With opencode-go, that fits within the $10/mo subscription, so that's what it ends up costing in real life.
- karmakaze
Personally I'm using Qwen3.8-27B (MXFP4 quant W4A8) locally hosted on a pair of AMD GPUs (with DeepSeek Harness). It starts at 250 tokens/sec down to 120 past 128k context.
At work mostly Opus 4.8 (sometimes a GPT or Gemini 3.1 Pro). I find Opus 5 chatty/slower and Fable can venture into over-engineering itself into unnecessary complications.