Kimi-Researcher is the research agent that powers Kimi Deep Research. Ask a question and it plans, searches, reads hundreds of pages, checks its facts and writes a long report with sources, usually in 10–25 minutes. Here's how it works and how to get the best from it.
On average per task, planned by the agent itself.
Searched and read for each research task.
Typical time for one Deep Research report.
A top score at launch in June 2025.
| Spec | Kimi-Researcher |
|---|---|
| Launched | 20 June 2025 (gradual rollout in Kimi) |
| Developer | Moonshot AI |
| What it is | An autonomous research agent model, built on an internal Kimi k-series model |
| Training | End-to-end agentic reinforcement learning on whole research runs |
| Tools | Parallel real-time search, a text-based web browser and code execution |
| Typical run | About 23 reasoning steps and over 200 web pages per task |
| Where you use it | Kimi Deep Research on kimi.com and in the Kimi apps |
| Output | A 10,000+ word Markdown report with sources, plus an interactive visual report |
| Time per report | Usually 10–25 minutes |
| Cost | Agent credits: about 5–10% of a Plus plan's monthly credits per report |
| API | Not available as an API |
From Moonshot's Kimi-Researcher launch post and the Kimi Help Center's Deep Research and credits pages. Moonshot hasn't published the model's size.
Instead of following a fixed script, Kimi-Researcher learned the whole research process by trial and reward.
One model runs the whole task, from planning to the final answer. It tries many strategies, gets rewarded for correct answers and learns from the full run, not from isolated examples.
A parallel real-time search tool, a text-based browser for interactive web pages, and a code tool for calculations and data work.
Training mixed tasks that force good tool use with maths, coding and very hard search questions that need many rounds of searching and checking.
Correct answers reached in fewer steps earned more, so it learned to research efficiently rather than wander.
It learned to keep what matters and drop the rest, so it can run long tasks with dozens of steps without running out of context.
Moonshot saw it cross-check conflicting sources and verify even simple-looking answers before replying, without being told to.
| Test | Result | Note |
|---|---|---|
| Humanity's Last Exam | 26.9% pass@1, 40.17% pass@4 | Up from 8.6% before RL training |
| xbench-DeepSearch | 69% pass@1 | Average of 4 runs; ahead of o3 with search tools |
| FRAMES, Seal-0 | Strong results | Multi-step search and reasoning tests |
| SimpleQA | Strong results | Short factual questions |
Moonshot-reported, tested 17–18 June 2025. Search-based results can vary as search engines change.
Reinforcement learning took Kimi-Researcher past the leading research agents of mid-2025.
Sign in at kimi.com, then choose Deep Research in the sidebar or switch to Deep Research mode in the app.
Say what you want to know, who it's for, the time period and the sources you trust.
Kimi-Researcher asks clarifying questions first. Your answers set the direction, so take a moment over them.
You can follow the search terms, reasoning and pages it visits as it goes. It usually takes 10–25 minutes.
Read the report, open key sources, then ask follow-up questions in the same chat.
Credits and plans: Kimi pricing and is Kimi AI free? Researching your own files instead? See how to analyze PDFs.
Copy a prompt into Deep Research and replace the [brackets]. Detailed questions get better reports.
Research the [market] in [region] from [year] to today: size, growth, main players, pricing trends and what experts expect to [year]. Prefer official statistics and company filings, and flag any figures that sources disagree on.
Review the research since [year] on [topic]. Group studies by finding, note sample sizes and methods, explain where results disagree and list the open questions. Link every study.
Compare [option A], [option B] and [option C] for [use case]. Cover cost, features, risks and who each suits, with a comparison table and a clear recommendation for [my situation].
Explain how [policy or law] works in [country], who it affects, recent changes and the main arguments for and against, using official and news sources from the last [12 months].
Research [company]: business model, revenue trends, leadership, competitors, recent news and main risks. Use filings and reputable news, and note the date of each figure.
Investigate the claim that [claim]. Find the original source, check it against independent evidence, and give a verdict with your confidence level and the strongest counter-evidence.
More ideas in the Kimi prompt library.
Its benchmark results date from June 2025. Newer models score much higher on the same tests, and Moonshot hasn't published newer Kimi-Researcher scores.
Reports cite sources, but sources can be outdated or misread. Open the citations behind any number you rely on.
One report uses about 5–10% of a Plus plan's monthly credits, so free and low-tier plans only get a few a month.
Moonshot said it planned to open-source the models behind Kimi-Researcher, but we haven't found a public release. It's only available inside Kimi.