[Integrations](https://spiral.ai/integrations) › [Muse](https://spiral.ai/integrations/muse) › [Kimi K2.5](https://spiral.ai/integrations/muse/kimi-k2-5)

# How to Use Kimi K2.5 in Muse

Kimi K2.5 suits visual coding, software maintenance, and work across long documents. It combines image understanding with Instant and Thinking modes.

|  |  |
| --- | --- |
| Model | Kimi K2.5 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.013336 per run at the default inputs. $0.65 per 1M input tokens, $3.25 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 K2.5 in Muse

- Use Kimi K2.5 to compare the two policy texts pasted above. Make a table of changed obligations, supporting passages, and questions the texts leave unanswered.
- Use Kimi K2.5 to examine this dashboard screenshot. Explain its layout and draft a concrete interface specification, marking any behavior the image cannot establish.
- Use Kimi K2.5 with Thinking enabled to analyze the proposal pasted above. Give me the strongest case for it, the strongest objection, and the evidence needed to decide.
- Use Kimi K2.5 to turn the research pasted above into a six-slide presentation outline for an operations team. Include one claim, supporting evidence, and speaker notes per slide.
- Use Kimi K2.5 to plan a spreadsheet analysis from the column descriptions above. Explain the calculations, missing-data checks, and summary tables before proposing conclusions.

## How to set up Kimi K2.5 in Muse

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

### Use the Muse connector

1. **Create an API key**: Create one under API keys in the Spiral console.

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

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

3. **Give Muse the key**: Paste the key when Muse asks for it, never in the chat itself.

### Use the Spiral skill

1. **Send Muse 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 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 K2.5**: 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-k2.5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse finds Kimi K2.5 on Spiral, shows the price and runs it.

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

## Kimi K2.5 tools and prices

- [MoonshotAI: Kimi K2.5](https://spiral.ai/tools/openrouter/moonshotai/kimi-k2.5) (OpenRouter): Up to $0.013336 per run at the default inputs. $0.65 per 1M input tokens, $3.25 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 K2.5 in Muse?

Turn dense source material into an explanation, comparison, or decision brief with Kimi K2.5. State the audience and ask for evidence beside conclusions.

### Implement a design reference

Use Kimi K2.5 to turn a screenshot into interface code, with explicit requirements for layout, responsive behavior, and working controls.

### Investigate visual bugs

Give Kimi K2.5 the intended design and a screenshot of the current result. Request a prioritized list of mismatches and proposed fixes.

### Refactor existing code

Ask Kimi K2.5 to simplify a module while preserving its documented behavior, then explain the changes and remaining risks.

### Draft regression tests

Have Kimi K2.5 turn a bug report and relevant code into a focused regression test and a proposed repair.

### Compare long documents

Ask Kimi K2.5 to compare labeled source texts, identify disagreements, and tie each finding to a supporting passage.

### Prepare an evidence-based brief

Use Kimi K2.5 to organize collected research into findings, evidence, open questions, and a recommendation for a named audience.

### Plan spreadsheet analysis

Give Kimi K2.5 a business question and a description of the available data. Request proposed calculations, table layouts, and checks for missing data.

### Draft a presentation

Ask Kimi K2.5 to turn supplied research into a slide outline with one claim per slide, supporting evidence, and speaker notes.

## Overview

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

## Kimi K2.5 in other agents

- [Amp](https://spiral.ai/integrations/amp/kimi-k2-5)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/kimi-k2-5)
- [Claude](https://spiral.ai/integrations/claude-desktop/kimi-k2-5)
- [Claude Code](https://spiral.ai/integrations/claude-code/kimi-k2-5)
- [Cline](https://spiral.ai/integrations/cline/kimi-k2-5)
- [Codex](https://spiral.ai/integrations/codex/kimi-k2-5)
- [Cursor](https://spiral.ai/integrations/cursor/kimi-k2-5)
- [Devin](https://spiral.ai/integrations/devin/kimi-k2-5)
- [dots](https://spiral.ai/integrations/dots/kimi-k2-5)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kimi-k2-5)
- [Gemini](https://spiral.ai/integrations/gemini/kimi-k2-5)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kimi-k2-5)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kimi-k2-5)
- [goose](https://spiral.ai/integrations/goose/kimi-k2-5)
- [Grok](https://spiral.ai/integrations/grok/kimi-k2-5)
- [Grok Build](https://spiral.ai/integrations/grok-build/kimi-k2-5)
- [Hermes](https://spiral.ai/integrations/hermes/kimi-k2-5)
- [Instinct](https://spiral.ai/integrations/instinct/kimi-k2-5)
- [Manus](https://spiral.ai/integrations/manus/kimi-k2-5)
- [Muse Code](https://spiral.ai/integrations/muse-code/kimi-k2-5)
- [n8n](https://spiral.ai/integrations/n8n/kimi-k2-5)
- [Notion](https://spiral.ai/integrations/notion/kimi-k2-5)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kimi-k2-5)
- [opencode](https://spiral.ai/integrations/opencode/kimi-k2-5)
- [Perplexity](https://spiral.ai/integrations/perplexity/kimi-k2-5)
- [Raycast](https://spiral.ai/integrations/raycast/kimi-k2-5)
- [VS Code](https://spiral.ai/integrations/vscode/kimi-k2-5)
- [Windsurf](https://spiral.ai/integrations/windsurf/kimi-k2-5)
- [Zapier](https://spiral.ai/integrations/zapier/kimi-k2-5)

## More Muse guides

- [Kimi K2 Thinking](https://spiral.ai/integrations/muse/kimi-k2-thinking)
- [Kimi K2.6](https://spiral.ai/integrations/muse/kimi-k2-6)
- [Kimi K2 0905](https://spiral.ai/integrations/muse/kimi-k2-0905)
- [Kimi K2.7 Code](https://spiral.ai/integrations/muse/kimi-k2-7-code)
- [Kimi K2 0711](https://spiral.ai/integrations/muse/kimi-k2-0711)
- [Kimi K3](https://spiral.ai/integrations/muse/kimi-k3)

## Questions about Kimi K2.5 in Muse

**Can Muse use Kimi K2.5?**

Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Kimi K2.5 like any built-in tool.

**How much does Kimi K2.5 cost in Muse?**

Up to $0.013336 per run at the default inputs. $0.65 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 Muse plan is separate.

**Do I need an OpenRouter account to use Kimi K2.5 in Muse?**

You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs Kimi K2.5 on its own OpenRouter account.

**How long does it take to set up Kimi K2.5 in Muse?**

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

**Does Muse wait while Kimi K2.5 runs?**

Kimi K2.5 runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.

**What is Kimi K2.5 good at?**

Moonshot emphasizes visual coding, software maintenance, and work across dense documents. Practical uses include implementing a screenshot, investigating a layout bug, and turning source material into a report.

**How much context can Kimi K2.5 handle?**

The documented context window is 256K tokens. For long tasks, ask for a source map first and work through named sections so you can check what the answer covers.

**What are Instant and Thinking modes?**

Kimi K2.5 supports both modes. Try Thinking for a difficult debugging or analysis task, and compare Instant on routine extraction or rewriting using the same examples.

**Which temperature should I use?**

Moonshot recommends 1.0 for Thinking and 0.6 for Instant. Start with those values and judge changes against representative tasks.

**Where does Kimi K2.5 need extra checking?**

Factual recall deserves scrutiny: Moonshot reports 36.9% on SimpleQA Verified. Ask for evidence, check citations, and require an explicit uncertainty statement when the supplied material does not support an answer.

