DevConsensus
Models / Kimi K3
Model · HN opinions Nov 2025 – Nov 2026

Kimi K3: what developers actually say

We read every Hacker News comment from Nov 2025 – Nov 2026 that gave a real opinion on Kimi K3. 67 of the 94 opinions come from people who say they use it themselves.

73%approval, all opinions
74%approval, last 90 days
#14of 45 models ranked
78different developers

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.

Pick it if

  • 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

  • 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

Strengths and weaknesses

Each row counts opinions that mentioned the topic. Bars to the right of the line are praise, bars to the left are complaints.

PraiseComplaints
Code quality
3
27
Cost & pricing
8
20
Usage limits
5
2
Reliability
2
3
Speed
3
1

How opinion has moved

050100Jul '26Aug '26Sep '26Oct '26
Monthly approval (line) and number of opinions (bars). Months with fewer than 3 opinions are left out.

What developers say

Praise

Says Kimi K3 became their daily driver over frontier models, with no complaints.HN comment · Oct 26, 2026
Kimi K3 is their go-to for writing style; they use it to tidy Opus's verbose code comments.HN comment · Oct 23, 2026
Prefers Chinese models like Kimi K3 for routine work, since they need little post-processing.HN comment · Oct 18, 2026
Says they get excellent results with Kimi K3 when running it inside the Pi harness.HN comment · Oct 6, 2026
Says they use Kimi K3 on their coding team and rate it as good.HN comment · Oct 2, 2026
Says Kimi K3 is roughly on par with Claude for SWE work, at least for routine business programming.HN comment · Sep 23, 2026
Uses Kimi K3 via OpenRouter for everyday work, avoiding sending data to China.HN comment · Sep 22, 2026
Uses Kimi K3 for the better part of a year and recommends switching to it.HN comment · Sep 12, 2026

Complaints

Finds GLM and Kimi K3 expensive and slow, and not much better than DeepSeek Flash here.HN comment · Oct 24, 2026
Found Kimi 3.0 functional but boring and says its recent results have been patchy.HN comment · Oct 24, 2026
Says Kimi K3's value is weak now that Sol's price dropped, and wants Kimi's pricing lowered.HN comment · Sep 27, 2026
Found Kimi K3 slower and more verbose than GLM 5.2 in recent testing.HN comment · Aug 15, 2026
Found Kimi K3 very expensive as a spec-writing model in a spec-driven workflow.HN comment · Aug 13, 2026
Rated below GLM 5.2 at coding in the author's own evaluation.HN comment · Aug 13, 2026
Says the official Kimi subscription is often out of stock with weak limits.HN comment · Aug 12, 2026
Says Kimi K3 is inconsistent, with much more output-quality variance than the best US models.HN comment · Aug 6, 2026

Summaries are paraphrased. Each links to the original comment.

FAQ

Is Kimi K3 worth it?

Approval is 73% over 94 opinions and 74% over the last 90 days. Code quality is the main reason, at 27 positive to 3 negative. Cost is the main caution, at 20 positive to 8 negative.

Is Kimi K3 better than GLM 5.2?

The head-to-head data favors GLM. Two developers preferred GLM 5.2 and one preferred GLM 5.3, and none in the set preferred Kimi K3 over GLM. Reviewers also called Kimi K3 slower and more verbose than GLM 5.2 in recent testing.

Is Kimi K3 expensive?

Cost opinions lean positive at 20 to 8, so many developers find the price acceptable. Complaints center on the official subscription being out of stock with weak limits. One reviewer said the value weakened after Sol's price dropped, and another called it very expensive for spec writing.