This is a scannable reference for prompting Kimi K2.7, Moonshot AI's June 2026 flagship in the Kimi K2 family. It is a 1-trillion-parameter mixture-of-experts model with about 32B active parameters per token, a 256K-token context window, multimodal input, and open weights under a Modified MIT license. It runs free at kimi.com on web and app. Bookmark this page and copy straight from the tables and prompt blocks below.
Kimi's strengths are agentic coding, long-horizon tasks, and careful reasoning, and it responds best to a real problem with rich context and a clear goal. Key controls: Thinking (deeper reasoning that catches edge cases), Web search (live results you can ask it to cite), Agent Mode / OK Computer (an agentic workspace that builds deliverables), and Deep Research (multi-source cited reports). If you want fully written prompts instead of a reference, jump to our best Kimi prompts roundup.
1. The universal prompt formula
Every strong Kimi prompt follows one shape: [Role] + [Task] + [Context] + [Constraints] + [Output format]. You do not need all five every time, but the more real context you give, the better Kimi reasons and the further it can run on an agentic task.
| Part | What it sets | Example fragment |
|---|---|---|
| Role | The expertise Kimi adopts | "You are a senior backend engineer." |
| Task | The one action to perform | "Find the bug causing this timeout." |
| Context | Background, inputs, real data | "Node 20, Postgres 16, code pasted below." |
| Constraints | Limits, must-do, avoid, length | "No new dependencies, keep it under 40 lines." |
| Output format | Exact shape of the answer | "Return the fix as one code block, then a 2-line note." |
You are a senior backend engineer. Find the bug causing intermittent timeouts in the function I paste below. Context: Node 20, Postgres 16, the timeout only happens under load. Constraints: no new dependencies, keep the fix under 40 lines. Think step by step, then verify your fix against the described symptom before answering. Output the corrected code as one block, followed by a two-line note on the root cause. Code: [PASTE CODE]Best for: any analysis, coding, writing, or planning task where you can describe the problem and picture the ideal answer's shape.
2. Modes & toggles
Pick the mode and toggles to fit the task. Instant handles quick work, but Thinking, Web search, Agent Mode, Deep Research, and upload each unlock a different capability.
| Mode / toggle | What it does | When to use |
|---|---|---|
| Instant | Fast replies without deep reasoning | Quick questions, drafting, everyday chat where speed matters |
| Thinking | Reasons more carefully first; catches edge cases and missing requirements | Hard reasoning, math, tricky code — when accuracy matters more than speed |
| Web search | Pulls live web results in real time | Current facts, recent news, anything time-sensitive; ask it to cite |
| Agent Mode / OK Computer | Agentic workspace that autonomously builds Websites, Docs, Slides, and Sheets and can run an Agent Swarm of sub-agents over many steps | When you want a finished deliverable built end to end, not just a chat reply |
| Deep Research | Multi-source investigation that returns a cited report | Briefings, market scans, literature reviews — sourced, current answers |
| File & image upload | Reads PDF, DOCX, spreadsheets, code, and images (design-to-code from a screenshot) | Summarizing or analyzing a document, codebase, or UI screenshot |
Best for: deciding in one glance whether a prompt needs deeper reasoning (Thinking), live data (Web search), a built deliverable (Agent Mode), or a sourced report (Deep Research).
3. Reasoning modifiers
Add one of these lines to push Kimi to reason carefully and check itself. They pair especially well with Thinking turned on. For long-running agentic work, see how to prompt Kimi for agentic tasks.
| Phrase to add | What it does |
|---|---|
| "Think step by step." | Forces an explicit chain of reasoning before the answer |
| "Show every step of your work." | Exposes intermediate steps so you can audit the logic |
| "List the requirements first, then solve." | Makes Kimi surface hidden requirements before it acts |
| "Consider one alternative approach and compare." | Guards against a single flawed approach by cross-checking |
| "Verify against the constraints before answering." | Makes it re-read your rules and confirm the answer fits them |
| "Rate your confidence and flag any assumptions." | Surfaces shaky steps instead of a falsely confident answer |
Best for: math, logic, debugging, and any answer you plan to act on and need to trust.
4. Role modifiers
Open with a role to set the expertise and voice Kimi uses. Be specific — "senior Python engineer" beats "expert".
| Role phrase | Best for |
|---|---|
| "You are a senior [LANGUAGE] engineer." | Debugging, refactoring, code review, architecture calls |
| "You are a sharp copy editor." | Tightening prose, fixing tone, cutting filler without losing meaning |
| "You are a data analyst." | Reading numbers, spotting trends, building comparison tables |
| "You are a patient tutor." | Explaining a hard concept simply, step by step, with examples |
| "You are a pragmatic strategist." | Business plans, prioritization, blunt trade-off analysis |
| "You are a research analyst." | Synthesizing sources into a briefing (pair with Deep Research) |
Best for: steering the level of detail and vocabulary so the answer matches your audience.
5. Output-format modifiers
Add one line to control how Kimi returns the answer. These stack cleanly on top of any prompt above.
| Phrase to add | Result |
|---|---|
| "Output in clean Markdown." | Headed sections and lists you can paste anywhere |
| "Return a table with columns X, Y, Z." | Structured comparison instead of prose |
| "Give a numbered list of steps." | An ordered checklist you can follow in sequence |
| "Output valid JSON only, no prose." | Machine-readable output for a downstream script |
| "Summarize in one paragraph." | A tight answer with no headings or bullets |
| "Build it as a Doc / Slides in Agent Mode." | A finished deliverable instead of raw text |
Best for: reusing a good prompt across contexts — keep the core, swap the last line to change the shape of the output.
6. Tone modifiers
One tone line changes the whole feel of the reply. Add it near the end of the prompt so it does not get lost.
| Phrase to add | Effect |
|---|---|
| "Keep it plain and direct." | Cuts hedging and filler; gets to the point |
| "Be blunt about weaknesses." | Honest critique instead of reflexive agreement |
| "Explain it like I'm new to this." | Simple language, defined terms, worked examples |
| "Formal, no contractions." | Professional register for reports and docs |
| "Keep it warm and encouraging." | Supportive framing for coaching or feedback |
| "No hype words, no clichés." | Strips marketing fluff from the output |
Best for: matching the reply to where it's going — a Slack message, a client report, or a study session.
7. Putting it together: 5 example prompts
Five ready-to-run prompts that combine the modifiers above. Edit the bracketed parts and send. For a coding-specific set, see Kimi prompts for coding.
Reasoning (Thinking on)
You are a patient tutor. Solve this problem and teach me the method: [PASTE PROBLEM]. List the requirements first, then think step by step and show every step of your work. Consider one alternative approach and confirm both give the same answer. Verify the result against the constraints before answering. Output a numbered worked solution, then a one-line summary of the key idea.Note: turn on Thinking so Kimi reasons more carefully and catches edge cases before it commits to an answer.
Coding
You are a senior [LANGUAGE] engineer. Here is my code: [PASTE CODE]. Task: find the bug causing [SYMPTOM]. Think step by step, then verify your fix against the symptom before answering. Constraints: keep it idiomatic, add no new dependencies. Output the corrected code as one block, then a two-line note on the root cause and how to prevent it.Note: paste the real code and the exact error — Kimi reasons far better with concrete inputs than with a description.
Agent Mode build (OK Computer)
Using Agent Mode, build a one-page marketing website for [PRODUCT]. Audience: [AUDIENCE]. Include a hero, three feature blocks, a pricing table, and a contact section. Constraints: clean responsive layout, no placeholder lorem ipsum — write real copy from the details I give. Work step by step, then hand me the finished site. Details: [PASTE DETAILS]Note: Agent Mode / OK Computer builds the deliverable end to end and can spin up an Agent Swarm for larger multi-part jobs.
Research (Deep Research on)
You are a research analyst. Run Deep Research on [TOPIC] as of this month. Cover the current state, the 3 biggest recent developments, key players, and open questions. Cite every claim with a link and prefer recent primary sources. Output a bulleted brief under 400 words, then a one-line bottom line. Keep it plain and direct.Note: Deep Research pulls from many sources and returns a cited report rather than a single quick answer.
Writing
You are a sharp copy editor. Rewrite the text below to be clearer and more direct without losing meaning: [PASTE TEXT]. Keep my key terms, cut filler, and fix weak verbs. Target a confident, plain tone with no hype words or clichés. Return the rewrite first, then a short bullet list of the main changes you made.Note: asking for the change list separately keeps the rewrite clean while still showing its work.
Want the full set of written-out prompts? Bookmark the roundup at /best-kimi-prompts and keep this cheat sheet open beside it.
Frequently Asked Questions
Which Kimi model do these prompts target?
Kimi K2.7, Moonshot AI's June 2026 flagship, and the wider Kimi K2 family (including K2.6 from April 2026). It is a 1-trillion-parameter mixture-of-experts model with about 32B active parameters per token, a 256K-token context window, multimodal input, and open weights under a Modified MIT license. It runs free at kimi.com on web and app. Everything here also works on earlier Kimi releases.
When should I use Thinking instead of Instant?
Instant answers fast without deep reasoning; Thinking reasons more carefully before replying and is better at catching edge cases and missing requirements. Turn on Thinking for hard reasoning, math, tricky code, and any task where accuracy matters more than speed.
What is Agent Mode / OK Computer?
Agent Mode, also called OK Computer, is Kimi's agentic workspace. It autonomously builds Websites, Docs, Slides, and Sheets, and can run an Agent Swarm of sub-agents that work across many steps to complete a larger task. Use it when you want Kimi to produce a finished deliverable rather than just chat.
What is Kimi's Deep Research mode?
Deep Research runs a multi-source investigation and returns a cited report. Kimi searches across many sources, cross-checks them, and writes up findings with links. Use it for briefings, market scans, and anything where you need sourced, current information rather than a single quick answer.
Is Kimi free to use?
Yes. Kimi has a free basic tier at kimi.com on web and app. Thinking, web search, Agent Mode, Deep Research, and file and image upload are available at no cost, and the model weights are open under a Modified MIT license so you can also self-host.
How do the [BRACKET] placeholders work?
Anything in square brackets is a swap-in. Replace [TOPIC], [LANGUAGE], or [AUDIENCE] with your own details before sending. The rest of each prompt is written to be copy-paste ready.
What is the Kimi prompt formula?
Role + Task + Context + Constraints + Output format. Tell Kimi who to be, what to do, the background it needs, the limits, and the exact shape of the answer. Kimi is strong at agentic coding and long-horizon tasks, so rich context and a clear goal matter more than rigid formatting.
Can Kimi read images and files?
Yes. Kimi is multimodal and reads both images and files. Use the upload button to add PDFs, DOCX, spreadsheets, code, or screenshots, then ask questions or request design-to-code conversion from a UI screenshot.