[Integrations](https://spiral.ai/integrations) › [Zapier](https://spiral.ai/integrations/zapier) › [Kimi K2.7 Code](https://spiral.ai/integrations/zapier/kimi-k2-7-code)

# How to Use Kimi K2.7 Code in Zapier

Kimi K2.7 Code is built for debugging, refactoring, and implementing changes across multiple files. Compared with Kimi K2.6, it targets longer coding tasks; Moonshot recommends Kimi K2.6 for general writing and conversation.

|  |  |
| --- | --- |
| Model | Kimi K2.7 Code |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.018665 per run at the default inputs. $0.78 per 1M input tokens, $4.55 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Kimi K2.7 Code in Zapier

- Every morning, use Kimi K2.7 Code to review the latest test-run summaries. Group recurring failures, compare them with yesterday's findings, and propose the next diagnostic step.
- Each weekday, use Kimi K2.7 Code to review newly reported software bugs. Extract reproduction details, identify missing evidence, and draft focused engineering tasks.
- After each release, use Kimi K2.7 Code to compare incident summaries with the release's acceptance criteria. Identify behavior that needs a regression test.
- Every week, use Kimi K2.7 Code to review dependency release notes supplied to this task. Identify changes that may affect our documented application behavior and propose migration checks.
- Each evening, use Kimi K2.7 Code to revisit unresolved debugging hypotheses using today's incident updates. Mark each hypothesis as supported, contradicted, or still untested, with evidence.

## How to set up Kimi K2.7 Code in Zapier

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

### Use the Spiral skill

1. **Send Zapier 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. **Add an MCP Client connection**: In Zapier open Apps, click Add connection and search for MCP Client. Fill in the form:

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Zapier never sees it, and you can remove it under Settings › Connected apps in the console.

3. **Run a Spiral tool in a Zap**: Add an MCP Client step to a Zap and choose the Run Tool action with your Spiral connection. Pick a tool: `discover` finds the right model for a task, `estimate_cost` prices it and `run` runs it. For example, `run` with:

```json
{
  "provider": "fal",
  "model": "fal-ai/flux/schnell",
  "input": { "prompt": "a lighthouse at dawn" },
  "wait": true
}
```

4. **Run Kimi K2.7 Code in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Kimi K2.7 Code, prices it and runs it each time the step fires.

### 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 K2.7 Code**: 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-k2.7-code",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Zapier finds Kimi K2.7 Code on Spiral, shows the price and runs it.

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

## Kimi K2.7 Code tools and prices

- [MoonshotAI: Kimi K2.7 Code](https://spiral.ai/tools/openrouter/moonshotai/kimi-k2.7-code) (OpenRouter): Up to $0.016002 per run at the default inputs. $0.78 per 1M input tokens, $3.90 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 K2.7 Code in Zapier?

Kimi K2.7 Code can support recurring engineering investigations that continue across several runs. Give each run the latest evidence and a record of unresolved questions so it can propose the next useful action.

### Fix a bug across multiple files

Ask Kimi K2.7 Code to trace a reported failure through the relevant code, propose a repair, and check it against the reproduction steps.

### Implement a complete feature

Give Kimi K2.7 Code acceptance criteria for a feature that touches several components. Request the implementation and a report of which criteria were verified.

### Refactor shared logic

Have Kimi K2.7 Code consolidate duplicated behavior while preserving existing interfaces and test expectations.

### Investigate failing tests

Give Kimi K2.7 Code the failure output and relevant implementation. Ask for the likely cause, a focused correction, and regression coverage.

### Plan a code migration

Ask Kimi K2.7 Code to identify affected components, order the changes, and define checks for each stage of a migration.

### Review a proposed change

Ask Kimi K2.7 Code to compare a patch with its requirements and identify concrete behavior changes that need testing.

### Investigate recurring failures

Use Kimi K2.7 Code to examine successive test or incident reports, track unresolved hypotheses, and propose the next diagnostic step.

## Overview

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

## Kimi K2.7 Code in other agents

- [Amp](https://spiral.ai/integrations/amp/kimi-k2-7-code)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/kimi-k2-7-code)
- [Claude](https://spiral.ai/integrations/claude-desktop/kimi-k2-7-code)
- [Claude Code](https://spiral.ai/integrations/claude-code/kimi-k2-7-code)
- [Cline](https://spiral.ai/integrations/cline/kimi-k2-7-code)
- [Codex](https://spiral.ai/integrations/codex/kimi-k2-7-code)
- [Cursor](https://spiral.ai/integrations/cursor/kimi-k2-7-code)
- [Devin](https://spiral.ai/integrations/devin/kimi-k2-7-code)
- [dots](https://spiral.ai/integrations/dots/kimi-k2-7-code)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kimi-k2-7-code)
- [Gemini](https://spiral.ai/integrations/gemini/kimi-k2-7-code)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kimi-k2-7-code)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kimi-k2-7-code)
- [goose](https://spiral.ai/integrations/goose/kimi-k2-7-code)
- [Grok](https://spiral.ai/integrations/grok/kimi-k2-7-code)
- [Grok Build](https://spiral.ai/integrations/grok-build/kimi-k2-7-code)
- [Hermes](https://spiral.ai/integrations/hermes/kimi-k2-7-code)
- [Instinct](https://spiral.ai/integrations/instinct/kimi-k2-7-code)
- [Manus](https://spiral.ai/integrations/manus/kimi-k2-7-code)
- [Muse](https://spiral.ai/integrations/muse/kimi-k2-7-code)
- [Muse Code](https://spiral.ai/integrations/muse-code/kimi-k2-7-code)
- [n8n](https://spiral.ai/integrations/n8n/kimi-k2-7-code)
- [Notion](https://spiral.ai/integrations/notion/kimi-k2-7-code)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kimi-k2-7-code)
- [opencode](https://spiral.ai/integrations/opencode/kimi-k2-7-code)
- [Perplexity](https://spiral.ai/integrations/perplexity/kimi-k2-7-code)
- [Raycast](https://spiral.ai/integrations/raycast/kimi-k2-7-code)
- [VS Code](https://spiral.ai/integrations/vscode/kimi-k2-7-code)
- [Windsurf](https://spiral.ai/integrations/windsurf/kimi-k2-7-code)

## More Zapier guides

- [Kimi K2.6](https://spiral.ai/integrations/zapier/kimi-k2-6)
- [Kimi K3](https://spiral.ai/integrations/zapier/kimi-k3)
- [Kimi K2.5](https://spiral.ai/integrations/zapier/kimi-k2-5)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/zapier/kimi-k3-1-pro)
- [Kimi K2 Thinking](https://spiral.ai/integrations/zapier/kimi-k2-thinking)
- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/zapier/kimi-k3-1-pro-batch)

## Questions about Kimi K2.7 Code in Zapier

**Can Zapier use Kimi K2.7 Code?**

Yes. Add Spiral to Zapier as an MCP server, and Zapier can find and run Kimi K2.7 Code like any built-in tool.

**How much does Kimi K2.7 Code cost in Zapier?**

Up to $0.018665 per run at the default inputs. $0.78 per 1M input tokens, $4.55 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Zapier plan is separate.

**Do I need an OpenRouter account to use Kimi K2.7 Code in Zapier?**

No. Spiral runs Kimi K2.7 Code on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Kimi K2.7 Code in Zapier?**

About two minutes: add an MCP Client connection, then sign in to Spiral and approve, then run a Spiral tool in a Zap.

**Does Zapier wait while Kimi K2.7 Code runs?**

Kimi K2.7 Code runs in the background. Zapier starts the run, checks on it and gives you the text, json when it's ready.

**What is Kimi K2.7 Code best suited for?**

Use it for coding tasks that require several connected changes, such as tracing a bug, refactoring a codebase, or implementing a feature across multiple files.

**How much context can Kimi K2.7 Code handle?**

It has a 256K-token context window. For code review, prioritize the relevant implementation, requirements, and test results so the task stays focused.

**Can Kimi K2.7 Code run without thinking?**

No. Kimi K2.7 Code always uses thinking mode.

**Which sampling settings does Moonshot recommend?**

Moonshot recommends temperature 1.0 and top_p 0.95. Use those as your starting point when evaluating coding results.

**Does Kimi K2.7 Code retain reasoning between turns?**

Yes. It preserves reasoning across turns, which supports coding tasks that continue through several rounds of investigation and changes.

