Kimi Code
Shares rank 10 of 41 coding agents by recommenders
People recommend it as a capable, cheap coding agent that rivals Claude Opus in planning, though critics say usage limits run out fast.
People recommend it as a capable, cheap coding agent that rivals Claude Opus in planning, though critics say usage limits run out fast.
38 people gave an opinion
- recommend it
- 25
- criticize it
- 13
- approval share
- 66%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 25 people recommend itNeeds 10 or more, met.
- 1.9 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Generous usage limits on plans
“the limits are so generous that you can use it every day all the time for everything”
Comment from 15 May 2026 in “Cut Off: why access to frontier AI will soon be scarce and selective” “their $20 per month plan had a lot more than Anthropic's”
Comment from 21 Apr 2026 in “Claude Code removed from Anthropic's Pro plan” “Apparently 5x usage when using Kimi Code too.”
Comment from 13 Aug 2026 in “SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index” - Comment from 11 Jun 2026 in “OpenAI mulls slashing prices as it competes with Anthropic for users”
Lower cost than rival plans
“If I can use that same model from kimi.com/Kimi Code, for less money”
Comment from 3 May 2026 in “Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge” “Kimi code with the .99 Cent plan is not to bad if you're savy”
Comment from 25 Feb 2026 in “Pi – a minimal terminal coding harness” “their $20 per month plan had a lot more than Anthropic's”
Comment from 21 Apr 2026 in “Claude Code removed from Anthropic's Pro plan” - Comment from 27 Jan 2026 in “Karpathy: A few random notes from Claude coding quite a bit last few weeks”
Strong coding model quality
“In planning, I'd say it's almost on par with Claude Opus.”
Comment from 3 May 2026 in “Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge” “the model looks very promising”
Comment from 17 Jul 2026 in “Kimi K3 is now #1 in the Front end Code Arena with 1679 pts, surpassing Fable 5” “Kimi Code is also very good.”
Comment from 13 Aug 2026 in “Qwen/Qwen3.8-2.4T-A95B” - Comment from 15 Jun 2026 in “Anthropic's Safety Superpower”
Daily driver for coding
“I've been running K2.5 (through the API) as my daily driver for coding through Kimi Code CLI”
Comment from 18 Feb 2026 in “Why AI Velocity Is Becoming a Debt Accelerator” “Installed kimi code on my mac and trying it out. Honestly, I am kind of liking it.”
Comment from 27 Jan 2026 in “Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model” “that's basically everything I need”
Comment from 31 Aug 2026 in “OpenClaw 2.0, Accidentally”
What people warn about
Each mark is one comment
Usage limits run out fast
“stupidly low rate limits for and cost, compared to OpenAI which has massive rate limits”
Comment from 11 Aug 2026 in “GPT 5.6 Cyber” “it burned a bazillion tokens, burned through the 5-hour limit, burned through $100 in extra usage I'd allocated”
Comment from 24 Jul 2026 in “Claude Opus 5” “It thought for about 12 minutes and then told me I had exhausted my daily quota.”
Comment from 19 Jul 2026 in “Moonshot AI suspends new subscriptions due to Kimi K3 demand” - Comment from 27 Jul 2026 in “Open-weight AI is having its Kubernetes moment. Let's not ruin it”
- Comment from 18 Jul 2026 in “The Kimi K3 Moment”
Requires phone number or Google login
“making me login with Google or a phone number”
Comment from 16 Jul 2026 in “Kimi K3 is now live” “Kimi wants my phone number on signup”
Comment from 24 Apr 2026 in “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support” Plans cost more than expected
“I'm getting a worse pricing on the Pro (19$) subscription than I would with regular API pricing.”
Comment from 28 Oct 2026 in “Ask HN: Kimi Code hit its 5-hour limit after $1.37 of API usage” “Absolutely do not pay for the kimi plans thinking they will be cheaper.”
Comment from 18 Jul 2026 in “The Kimi K3 Moment” Desktop and web apps feel unfinished
“Kimi Code and OpenCode desktop/web offerings still aren't great, but are functional”
Comment from 22 Jul 2026 in “Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA” “Though it's ever so slightly broken”
Comment from 20 Jul 2026 in “Kimi Work”
Other coding agents people recommend
The four most recommended other coding agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-pi | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| Kimi CodeThis page | 25 | 13 | 66% | 9 | — | — |
What people said
40 of the 46 comments that mention it, newest first. Each links to the original comment.
“I'm getting a worse pricing on the Pro (19$) subscription than I would with regular API pricing.”
“Pretty everyone is complaining about it on the X or atleast was yesterday.”
“they refused to help and said you used it heavily”
“Kimi Code and Pi kept winning”
“the model diversity does help with adversarial code review loops”
“creating these is just a checkbox that's being ticked rather than a need being met”
“that's basically everything I need”
“Kimi Code is also very good.”
“Apparently 5x usage when using Kimi Code too.”
“stupidly low rate limits for and cost, compared to OpenAI which has massive rate limits”
“I'd have preferred you use kimi code, not opencode”
“its limits are pretty abysmal compared to ChatGPT/Claude plans”
“I wonder if the harness itself is not token-efficient?”
“it burned a bazillion tokens, burned through the 5-hour limit, burned through $100 in extra usage I'd allocated”
“Kimi Code and OpenCode desktop/web offerings still aren't great, but are functional”
“kimi code feels like claude code from ... september 2025”
“Though it's ever so slightly broken”
“It thought for about 12 minutes and then told me I had exhausted my daily quota.”
“Absolutely do not pay for the kimi plans thinking they will be cheaper.”
“usage was nearly gone after the trivial task”
“the model looks very promising”
“making me login with Google or a phone number”
“inside kimi code finds the most”
“Kimi code 2.6 is crazy good”
“unless you mean their own native clis like kimi code”
“I've tried this too, and was disappointed.”
“I never run out of quota.”
“the limits are so generous that you can use it every day all the time for everything”
“If I can use that same model from kimi.com/Kimi Code, for less money”
“In planning, I'd say it's almost on par with Claude Opus.”
“Kimi wants my phone number on signup”
“their $20 per month plan had a lot more than Anthropic's”
“hard to see why I want to use Kimi over Claude”
“Kimi code with the .99 Cent plan is not to bad if you're savy”
“I've been running K2.5 (through the API) as my daily driver for coding through Kimi Code CLI”
“I feel like monetarily its worth it”
“Moonshot AI developers are actively update the agent and every active.”
“It also has a zsh hook, allowing you to switch to agent mode wherever you're.”
“Installed kimi code on my mac and trying it out. Honestly, I am kind of liking it.”
“it is capable agent with stable harness.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.