How to Use Kimi K2 Thinking in Instinct
Kimi K2 Thinking is built for research, coding, and writing that require multiple reasoning steps. Unlike Kimi K2 Instruct, it combines extended reasoning with tool calls to work through complex tasks.
Prompts to try with Kimi K2 Thinking in Instinct
Copy an example into Instinct, or ask in your own words.
Each Monday, use Kimi K2 Thinking to review official PostgreSQL release announcements from the previous seven days. Summarize changes that affect application developers, cite each announcement, and say when none were published.
Each weekday, use Kimi K2 Thinking to research new primary studies on battery recycling published during the previous day. Explain the methods, findings, and limitations in a brief under 600 words.
Every Friday, use Kimi K2 Thinking to compare official React announcements with the previous weekly summary. Explain new changes, unresolved questions, and any action a development team should consider.
Each month, use Kimi K2 Thinking to review the official Python security advisories published that month. Explain affected versions and recommended fixes, with a source for every advisory.
Every Tuesday, use Kimi K2 Thinking to investigate one unresolved question from the previous research brief. Check primary sources, explain conflicting evidence, and report whether the question can now be answered.
How to set up Kimi K2 Thinking in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Kimi K2 Thinking
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "moonshotai/kimi-k2-thinking", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Kimi K2 Thinking on Spiral, shows the price and runs it.
Kimi K2 Thinking providers and prices
Spiral runs Kimi K2 Thinking through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.01334 per run at the default inputs. $0.78 per 1M input tokens, $3.25 per 1M output tokens.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 98304 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of MoonshotAI: Kimi K2 Thinking is on its tool page: open its card above.
What can you do with Kimi K2 Thinking in Instinct?
Kimi K2 Thinking can turn recurring research and analysis into briefs that explain what changed and why it matters. Define the sources, comparison period, and evidence required for each conclusion.
Investigate a software bug
Use Kimi K2 Thinking to trace a failure through relevant code, propose a focused fix, and check it against a reproducible test.
Plan a code migration
Ask Kimi K2 Thinking to map dependencies, identify behavior that must survive the migration, and propose an ordered implementation and verification plan.
Research a difficult question
Give Kimi K2 Thinking a precise question and ask it to investigate primary sources using available research tools, resolve conflicting claims, and cite its conclusions.
Compare technical approaches
Have Kimi K2 Thinking compare designs against explicit constraints, explain tradeoffs, and identify which unanswered questions could change the recommendation.
Check a mathematical argument
Ask Kimi K2 Thinking to examine assumptions, look for counterexamples, and verify numerical steps with an available calculation tool.
Draft an analytical report
Supply source text and an audience brief, then ask Kimi K2 Thinking to build an argument, support each conclusion, and flag gaps in the evidence.
Review a terminal workflow
Use Kimi K2 Thinking to investigate a failed build or command sequence, test an explanation, and document the commands and results that support it.
Turn research into a recurring brief
Ask Kimi K2 Thinking to compare newly retrieved information with a previous summary and explain which changes affect a specific decision.
More on Kimi K2 Thinking and Instinct
Overview
Kimi K2 Thinking in other agents
More Instinct guides
Questions about Kimi K2 Thinking in Instinct
Can Instinct use Kimi K2 Thinking?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Kimi K2 Thinking like any built-in tool.
How much does Kimi K2 Thinking cost in Instinct?
Up to $0.01334 per run at the default inputs. $0.78 per 1M input tokens, $3.25 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an OpenRouter account to use Kimi K2 Thinking in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Kimi K2 Thinking on its own OpenRouter account.
How long does it take to set up Kimi K2 Thinking in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Kimi K2 Thinking runs?
Kimi K2 Thinking runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Kimi K2 Thinking good at?
It is designed for research, coding, and writing that involve several reasoning steps and tool calls. Try tasks with a clear outcome, such as investigating conflicting sources, diagnosing a bug, or developing an evidence-backed report.
How much context can Kimi K2 Thinking handle?
Its published context window is 256K tokens. When preparing a long task, leave room for reasoning, tool results, and the final answer.
Can Kimi K2 Thinking analyze images or video?
It accepts text and tool definitions rather than images, audio, or video directly. Supply a transcript, extracted text, or a written description for analysis.
Why can a short answer need a large generation budget?
Reasoning and the final answer draw from the same generation budget. Set the desired answer length in your prompt, and leave enough generation room for the reasoning needed to produce it.
What temperature should I use?
Moonshot recommends 1.0 for Kimi K2 Thinking. Start there, and assess results using representative tasks with clear checks for correctness.
Start using Kimi K2 Thinking in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


