Kimi K3: what 94 developers actually say.
94 Hacker News opinions from 78 developers, Nov 2025 – Nov 2026. 67 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Kimi K3, in one paragraph.
Kimi K3 earns 73% approval across 94 opinions. Developers praise its code quality. In the last 90 days it sits at 74%.
Pick it if you
- Want strong code quality, rated 27 positive to 3 negative
- Want a daily driver that some developers prefer over Claude Opus 4.8 and GPT-5.6 Sol
- Do routine business programming and want a cheaper option than frontier US models
Look elsewhere if you
- Need generous usage limits, rated 2 positive to 5 negative
- Need fast responses, rated 1 positive to 3 negative
- Need consistent output; reviewers report more variance than the top US models
Where it wins and loses.
Mentions across 94 opinions. Bars are counts, not votes; a tool can be both praised and criticized on the same topic.
View data table
| Topic | Praise | Complaints | Mentions |
|---|---|---|---|
| Code quality | 27 | 3 | 30 |
| Cost & pricing | 20 | 8 | 28 |
How opinion has moved.
Monthly approval, Jul 2026 – Oct 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Jul 2026 | 72% | 43 |
| Aug 2026 | 72% | 30 |
| Sep 2026 | 73% | 11 |
| Oct 2026 | 80% | 10 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedKimi K3 became their daily driver over frontier models, with no complaints.
Kimi K3 is their go-to for writing style; they use it to tidy Opus's verbose code comments.
Prefers Chinese models like Kimi K3 for routine work, since they need little post-processing.
They get excellent results with Kimi K3 when running it inside the Pi harness.
Complaints
4 selectedFinds GLM and Kimi K3 expensive and slow, and not much better than DeepSeek Flash here.
Found Kimi 3.0 functional but boring and says its recent results have been patchy.
Kimi K3's value is weak now that Sol's price dropped, and wants Kimi's pricing lowered.
Found Kimi K3 slower and more verbose than GLM 5.2 in recent testing.
Questions developers ask.
Is Kimi K3 worth it?
Is Kimi K3 better than GLM 5.2?
Is Kimi K3 expensive?
The data behind this page.
Developers give Kimi K3 73% approval across 94 opinions from 78 authors, and 67 of those opinions are firsthand. Code quality carries the score at 27 positive to 3 negative. Cost splits at 20 positive and 8 negative, and speed is the weak spot at 1 positive to 3 negative. Approval went from 72% in July to 80% in October, while monthly opinions fell from 43 to 10, so the recent reading rests on a small sample.
Every number comes from public Hacker News comments collected through the HN Search API. A language model tagged each comment for sentiment, first-hand use, topic and switches; a human spot-checks samples. No vendor can pay for placement.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.