Kimi K2.5: what 41 developers actually say.
41 Hacker News opinions from 38 developers, Nov 2025 – Nov 2026. 28 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Kimi K2.5, in one paragraph.
Kimi K2.5 earns 74% approval across 41 opinions. Developers are divided on it.
Pick it if you
- Want strong coding value at a low price
- Mostly run small, well-scoped tasks
- Want an open-weight model for agentic coding and research
Look elsewhere if you
- Depend on reliable tool calling in OpenCode
- Need consistent architecture on complex work
- Expect fast local coding on your own hardware
Where it wins and loses.
Mentions across 41 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 |
|---|---|---|---|
| Cost & pricing | 13 | 1 | 14 |
| Code quality | 9 | 2 | 11 |
How opinion has moved.
Monthly approval, Jan 2026 – Apr 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Jan 2026 | 64% | 7 |
| Feb 2026 | 74% | 21 |
| Mar 2026 | 100% | 3 |
| Apr 2026 | 92% | 6 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedLists Kimi K2.5 among favorite open models used via API before moving to a $100 subscription.
Has run Kimi K2.5 for a day through a proxy; it works well enough for their workflow.
Finds Kimi K2.5 good enough for most work, giving about 80% of Opus's value at a fraction of the cost.
Kimi K2.5 via synthetic.new works surprisingly well for small tasks they still direct.
Complaints
4 selectedFound Kimi K2.5 in OpenCode a step behind their previous setup.
Kimi K2.5 often gets tool-calling arguments wrong in OpenCode.
Kimi K2.5 on OpenCode falls well short of Claude Code, losing architecture and producing inconsistent code.
Kimi K2.5 often hangs on tool use, hallucinating commands and getting syntax wrong.
Questions developers ask.
Is Kimi K2.5 worth it?
Is Kimi K2.5 better than Claude Code?
Is Kimi K2.5 good for coding?
The data behind this page.
Kimi K2.5 has 74% approval from 41 opinions by 38 authors, with 28 firsthand. Cost is the main draw at 13 positive and 1 negative, and users put it at roughly 80% to 90% of Claude Opus quality for much less money; code quality is positive at 9 to 2, while reliability is mixed at 5 to 3 and complaints cite tool-calling errors, hangs, and inconsistent output. No 90-day approval figure is available, and monthly samples are small: approval was 64% in January, 74% in February, 100% in March, and 92% in April, with only four opinions from May through October. The recent trend is therefore thin.
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.