[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Kimi Latest](https://spiral.ai/integrations/instinct/kimi-latest)

# How to Use Kimi Latest in Instinct

Use Kimi Latest for large-codebase work, research synthesis, and tasks that need several tool calls. Unlike the fixed Kimi K3 name, it follows a changing model target, currently Kimi K3.

|  |  |
| --- | --- |
| Model | Kimi Latest |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.058611 per run at the default inputs. $0.23712 per 1M input tokens, $14.30715 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Kimi Latest in Instinct

- Every weekday, use Kimi Latest to review newly published release notes for the products on my watchlist. Retrieve the original announcements, report changes since the previous run, and include publication dates and source links.
- Each morning, use Kimi Latest to summarize the incident records supplied by the monitoring tools. Group related symptoms, distinguish observations from hypotheses, and report only incidents that are new or materially changed.
- Every Friday, use Kimi Latest to review new research returned by the configured search tools on database query optimization. Compare methods and evaluation conditions, cite original papers, and keep the brief under 700 words.
- Each week, use Kimi Latest to compare current product documentation retrieved by the agent with the previous recorded text. Report changed requirements and unresolved contradictions with links to the relevant sections.
- Each day, use Kimi Latest to prepare an English summary of new Chinese announcements returned by the configured feeds. Preserve names and dates, link the originals, and distinguish announced plans from completed releases.

## How to set up Kimi Latest in Instinct

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send Instinct this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **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

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **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

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Kimi Latest**: One request; the result comes back by polling or a webhook.

```bash
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-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Kimi Latest on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

## Kimi Latest tools and prices

- [MoonshotAI: Kimi Latest](https://spiral.ai/tools/openrouter/~moonshotai/kimi-latest) (OpenRouter): Up to $0.058611 per run at the default inputs. $0.23465 per 1M input tokens, $14.30715 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with Kimi Latest in Instinct?

Kimi Latest can turn newly retrieved information into recurring research briefs and operational summaries. Give each run a fixed scope, dated evidence, and explicit rules for when to report a change.

### Fix bugs across a large repository

Ask Kimi Latest to trace a failure through the relevant code, reproduce it, and propose a focused repair. Specify the permitted scope and require test evidence.

### Plan a cross-module refactor

Have Kimi Latest map dependencies and propose a staged refactor with acceptance checks. Define the behavior that each stage must preserve.

### Turn research methods into code

Give Kimi Latest a paper's methods and equations as text, then request an implementation plan, executable code, and checks against the reported results.

### Compare competing proposals

Supply proposal text and ask Kimi Latest to compare scope, assumptions, exclusions, and unanswered questions. Require supporting passages for each conclusion.

### Prepare a research brief

Have Kimi Latest synthesize retrieved sources into a concise brief with dated evidence, disagreements, and open questions. Define the audience and decision the brief must support.

### Explain Chinese and English material

Use Kimi Latest to explain supplied Chinese material in English, or English material in Chinese. Provide a terminology list and ask it to flag ambiguous passages.

### Review operational incidents

Give Kimi Latest incident timelines, log excerpts, and investigation notes as text. Ask for a causal hypothesis, conflicting evidence, and the next checks to run.

### Answer questions from reference material

Supply relevant policy or product documentation as text and ask Kimi Latest to answer with section references. Require it to identify questions the material does not resolve.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## Kimi Latest in other agents

- [Amp](https://spiral.ai/integrations/amp/kimi-latest)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/kimi-latest)
- [Claude](https://spiral.ai/integrations/claude-desktop/kimi-latest)
- [Claude Code](https://spiral.ai/integrations/claude-code/kimi-latest)
- [Cline](https://spiral.ai/integrations/cline/kimi-latest)
- [Codex](https://spiral.ai/integrations/codex/kimi-latest)
- [Cursor](https://spiral.ai/integrations/cursor/kimi-latest)
- [Devin](https://spiral.ai/integrations/devin/kimi-latest)
- [dots](https://spiral.ai/integrations/dots/kimi-latest)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kimi-latest)
- [Gemini](https://spiral.ai/integrations/gemini/kimi-latest)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kimi-latest)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kimi-latest)
- [goose](https://spiral.ai/integrations/goose/kimi-latest)
- [Grok](https://spiral.ai/integrations/grok/kimi-latest)
- [Grok Build](https://spiral.ai/integrations/grok-build/kimi-latest)
- [Hermes](https://spiral.ai/integrations/hermes/kimi-latest)
- [Manus](https://spiral.ai/integrations/manus/kimi-latest)
- [Muse](https://spiral.ai/integrations/muse/kimi-latest)
- [Muse Code](https://spiral.ai/integrations/muse-code/kimi-latest)
- [n8n](https://spiral.ai/integrations/n8n/kimi-latest)
- [Notion](https://spiral.ai/integrations/notion/kimi-latest)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kimi-latest)
- [opencode](https://spiral.ai/integrations/opencode/kimi-latest)
- [Perplexity](https://spiral.ai/integrations/perplexity/kimi-latest)
- [Raycast](https://spiral.ai/integrations/raycast/kimi-latest)
- [VS Code](https://spiral.ai/integrations/vscode/kimi-latest)
- [Windsurf](https://spiral.ai/integrations/windsurf/kimi-latest)
- [Zapier](https://spiral.ai/integrations/zapier/kimi-latest)

## More Instinct guides

- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/instinct/kimi-k3-1-pro-batch)
- [LFM2.5-24B-A2B](https://spiral.ai/integrations/instinct/lfm2-5-24b-a2b)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/instinct/kimi-k3-1-pro)
- [LFM3-1.7B](https://spiral.ai/integrations/instinct/lfm3-1-7b)
- [Kimi K3](https://spiral.ai/integrations/instinct/kimi-k3)
- [Ling 3.0 Flash](https://spiral.ai/integrations/instinct/ling-3-0-flash)

## Questions about Kimi Latest in Instinct

**Can Instinct use Kimi Latest?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Kimi Latest like any built-in tool.

**How much does Kimi Latest cost in Instinct?**

Up to $0.058611 per run at the default inputs. $0.23712 per 1M input tokens, $14.30715 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 Latest in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Kimi Latest on its own OpenRouter account.

**How long does it take to set up Kimi Latest in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Kimi Latest runs?**

Kimi Latest runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**Does Kimi Latest always mean the same model?**

No. Its target can change, and the current listing points to Kimi K3. Treat saved prompts as something to recheck when the target changes.

**What is Kimi Latest best suited for?**

With its current Kimi K3 target, it suits sustained coding tasks, research synthesis, and knowledge work that takes several steps. Give it a concrete deliverable and a clear definition of done.

**How much context can Kimi Latest handle?**

The alias can reach a 1,048,576-token context window, but the actual limit depends on its target. Use that capacity for relevant evidence, and ask for a bounded answer such as a comparison table or a short decision memo.

**Can Kimi Latest answer questions about today's events?**

Give it current source material or have the agent retrieve it first. Kimi's training knowledge alone cannot reliably answer time-sensitive questions.

**Which languages are a sensible starting point?**

Chinese and English are explicitly highlighted in Moonshot's example instructions. For bilingual work, specify the output language and supply a glossary for names and technical terms.

