Ask HN: What LLM models are you using and why?
I'm wondering what y'all are using for your daily driver these days and why?
I've found myself using GPT-5.5 more than Opus 4.7 for work; which, has been a pretty big reversal. Previously, I was using Opus 4.6 for everything, and GPT-5.4 was only ever in the picture to provide a second opinion (with Grok a distant 3rd only when I wanted to throw some "chaos" into the mix). The reason I've personally pivoted, is I've found GPT-5.5 to be a bit more consistent, predictable, and tends to write in a way I find less tiresome (even if the code isn't quite as good as Opus 4.7).
For personal projects, I've started experimenting with DeepSeek V4 and have been pretty blown away by it because of it's cost to quality and I've found the 1M token window to be incredibly helpful for long-running tasks. Though I may also have an over abundance of fear of compaction during tasks. DeepSeek isn't quite as good at one-shotting things as either GPT-5.5 or Opus-4.7, but with sufficient linter/static-analysis guardrails I've found it's really hard to complain or find faults (especially at the price).
Finally, if you're also making use of reranking and/or embedding models, or anything else, to augment or perform specific tasks please share those too!
fyi: I didn't have much lock on Deepseek v4 pro, with opencode + openrouter it's incredibly slow. How did op did it?
[0] https://newspeaklanguage.org
2. gpt-5.3-codex-medium for genrally most of the other coding tasks.
3. deepseek-v4-flash for heavy agentic research/loops (non-coding related).
4. mimo-v2.5-pro for crunching/summarizing large texts.
5. gemini-3.1-flash-lite for image understanding.
6. opus-4.7 very occasionally when gpt-5.5 fails, or vice-versa, and sonnet-4.6 when codex-5.3 fails.
7. deepseek-v4-pro when I need to do a long agentic session, and want higher quality, for cheap (non-coding).
8. perplexity/pplx-embed-v1-0.6b for embeddings, via openrouter.
At work I use 4.6 because we don't have 4.7 yet...zzz...
I also do a LOT of personal/portfolio work with self-hosted models.
Ministral-3-14B-Reasoning for validating concepts, MVPs, etc and some prod systems (punches above its weight class). Qwen3.6-35B-A3B for self-hosted coding (custom harness). GPT-OSS-120B for self-hosted coding or more reasoning-intensive agentic flows. Qwen3.5-122B-A10B currently in evals for agentic coding.
For more interactive/discussion/planning or orchestration stuff, I find myself going back and forth between Opus 4.7 and GPT 5.5. Still not sure which one I prefer.
Opus 4.7, or 4.6 where it's still available at work: For spec'ing up projects or changes. The 15x multiplyer on Copilot means I rarely do this.
Sonnet 4.6 everywhere else. It rarely fails me.