[Integrations](https://spiral.ai/integrations) › [Amp](https://spiral.ai/integrations/amp) › [Kimi K2.6](https://spiral.ai/integrations/amp/kimi-k2-6)

# How to Use Kimi K2.6 in Amp

Kimi K2.6 suits extended coding jobs, interface building, and research that takes several tool calls. Moonshot reports stronger end-to-end coding results than Kimi K2.5, including work in Rust, Go, and Python.

|  |  |
| --- | --- |
| Model | Kimi K2.6 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.018189 per run at the default inputs. $0.845 per 1M input tokens, $4.433 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Kimi K2.6 in Amp

- Use Kimi K2.6 to investigate the failing tests in this repository. Trace the cause, make a focused fix, run the relevant tests, and report any remaining failures.
- Use Kimi K2.6 to profile this project's slowest request path. Record a baseline, change one bottleneck at a time, and report measured results.
- Use Kimi K2.6 to build a searchable, sortable table using this project's existing components. Include loading, empty, and error states, then check keyboard navigation.
- Use Kimi K2.6 to review the Go service's cancellation handling. Trace request contexts through downstream calls, fix leaks, and verify cancellation behavior.
- Use Kimi K2.6 to add session history to this application using its existing database patterns. Include creation, listing, and deletion, then verify the complete workflow.

## How to set up Kimi K2.6 in Amp

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

### Use Spiral's MCP server

1. **Add the server**: No header and no client ID or secret: Amp registers itself with Spiral.

```bash
amp mcp add spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `amp`. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.

3. **Check it**

```bash
amp mcp doctor
```

### Use the Spiral skill

1. **Send Amp 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 K2.6**: 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-k2.6",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Amp finds Kimi K2.6 on Spiral, shows the price and runs it.

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

## Kimi K2.6 tools and prices

- [MoonshotAI: Kimi K2.6](https://spiral.ai/tools/openrouter/moonshotai/kimi-k2.6) (OpenRouter): Up to $0.018189 per run at the default inputs. $0.845 per 1M input tokens, $4.433 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 K2.6 in Amp?

Kimi K2.6 can carry a coding task through investigation, implementation, and checks across a project. Use it for bugs spanning several modules, performance work, or interfaces with specific interactions.

### Fix a bug across several modules

Use Kimi K2.6 to trace a failing behavior through related code, implement a focused fix, and run the relevant checks.

### Investigate a performance bottleneck

Ask Kimi K2.6 to examine profiling evidence, propose a measurable change, and compare results before and after.

### Build an interactive interface

Give Kimi K2.6 a written brief covering layout, interactions, and acceptance criteria for a working frontend.

### Prototype a lightweight web application

Use Kimi K2.6 for a small workflow with user interactions and database operations, such as session tracking or transaction logging.

### Prepare a sourced research comparison

Have Kimi K2.6 combine retrieved evidence into a comparison that links each conclusion to its source.

### Triage recurring operational alerts

Use Kimi K2.6 to examine monitoring results, investigate related signals, and produce an incident brief with unresolved questions.

### Extract structured research notes

Ask Kimi K2.6 for a bounded JSON object containing findings, evidence, and missing information, with an example defining the format.

## Overview

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

## Kimi K2.6 in other agents

- [ChatGPT](https://spiral.ai/integrations/chatgpt/kimi-k2-6)
- [Claude](https://spiral.ai/integrations/claude-desktop/kimi-k2-6)
- [Claude Code](https://spiral.ai/integrations/claude-code/kimi-k2-6)
- [Cline](https://spiral.ai/integrations/cline/kimi-k2-6)
- [Codex](https://spiral.ai/integrations/codex/kimi-k2-6)
- [Cursor](https://spiral.ai/integrations/cursor/kimi-k2-6)
- [Devin](https://spiral.ai/integrations/devin/kimi-k2-6)
- [dots](https://spiral.ai/integrations/dots/kimi-k2-6)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kimi-k2-6)
- [Gemini](https://spiral.ai/integrations/gemini/kimi-k2-6)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kimi-k2-6)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kimi-k2-6)
- [goose](https://spiral.ai/integrations/goose/kimi-k2-6)
- [Grok](https://spiral.ai/integrations/grok/kimi-k2-6)
- [Grok Build](https://spiral.ai/integrations/grok-build/kimi-k2-6)
- [Hermes](https://spiral.ai/integrations/hermes/kimi-k2-6)
- [Instinct](https://spiral.ai/integrations/instinct/kimi-k2-6)
- [Manus](https://spiral.ai/integrations/manus/kimi-k2-6)
- [Muse](https://spiral.ai/integrations/muse/kimi-k2-6)
- [Muse Code](https://spiral.ai/integrations/muse-code/kimi-k2-6)
- [n8n](https://spiral.ai/integrations/n8n/kimi-k2-6)
- [Notion](https://spiral.ai/integrations/notion/kimi-k2-6)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kimi-k2-6)
- [opencode](https://spiral.ai/integrations/opencode/kimi-k2-6)
- [Perplexity](https://spiral.ai/integrations/perplexity/kimi-k2-6)
- [Raycast](https://spiral.ai/integrations/raycast/kimi-k2-6)
- [VS Code](https://spiral.ai/integrations/vscode/kimi-k2-6)
- [Windsurf](https://spiral.ai/integrations/windsurf/kimi-k2-6)
- [Zapier](https://spiral.ai/integrations/zapier/kimi-k2-6)

## More Amp guides

- [Kimi K2.5](https://spiral.ai/integrations/amp/kimi-k2-5)
- [Kimi K2.7 Code](https://spiral.ai/integrations/amp/kimi-k2-7-code)
- [Kimi K2 Thinking](https://spiral.ai/integrations/amp/kimi-k2-thinking)
- [Kimi K3](https://spiral.ai/integrations/amp/kimi-k3)
- [Kimi K2 0905](https://spiral.ai/integrations/amp/kimi-k2-0905)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/amp/kimi-k3-1-pro)

## Questions about Kimi K2.6 in Amp

**Can Amp use Kimi K2.6?**

Yes. Add Spiral to Amp as an MCP server, and Amp can find and run Kimi K2.6 like any built-in tool.

**How much does Kimi K2.6 cost in Amp?**

Up to $0.018189 per run at the default inputs. $0.845 per 1M input tokens, $4.433 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.

**Do I need an OpenRouter account to use Kimi K2.6 in Amp?**

No. Spiral runs Kimi K2.6 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 K2.6 in Amp?**

About two minutes: add the server, then sign in, then check it.

**Does Amp wait while Kimi K2.6 runs?**

Kimi K2.6 runs in the background. Amp starts the run, checks on it and gives you the text, json when it's ready.

**What is Kimi K2.6 good at?**

Extended coding tasks, frontend interfaces, and work that requires repeated reasoning and tool calls. Moonshot also demonstrates research and persistent monitoring workflows.

**How much context can Kimi K2.6 handle?**

Its documented context window is 262,144 tokens. Treat that as a context limit, rather than a promise about the length of a single answer.

**Which programming languages does Kimi K2.6 handle?**

Moonshot specifically highlights Rust, Go, and Python. Its examples span frontend development, DevOps, and performance optimization.

**Where does Kimi K2.6 need checking?**

Difficult reasoning still needs verification. Moonshot reports 36.4% accuracy without tools and 55.5% with tools on the text-only subset of Humanity's Last Exam, so ask for supporting evidence and check consequential conclusions.

**What sampling settings does Moonshot recommend?**

Moonshot recommends temperature 1.0 with Thinking mode and 0.6 with Instant mode, plus top-p 0.95. These are fixed values on Moonshot's own API.

