[Integrations](https://spiral.ai/integrations) › [Muse](https://spiral.ai/integrations/muse) › [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/muse/kimi-k3-1-pro-batch)

# How to Use Kimi K3.1 Pro (batch) in Muse

Use Kimi K3.1 Pro for code changes, CAD scripts, and research across long documents. Built from Kimi K3, it improves coding, 3D creation, and financial research while keeping a million-token context window.

|  |  |
| --- | --- |
| Model | Kimi K3.1 Pro (batch) |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.021978 per run at the default inputs. $0.3575 per 1M input tokens, $5.3625 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 K3.1 Pro (batch) in Muse

- Use Kimi K3.1 Pro to compare the annual-report excerpts in this conversation. Explain changes in revenue definitions and reporting periods, quote the supporting passages, and flag comparisons that would be misleading.
- Use Kimi K3.1 Pro to explain the chart image in this conversation. Identify the axes, units, and main trend; distinguish exact readings from estimates and mark anything you cannot read.
- Use Kimi K3.1 Pro with maximum reasoning effort to review this proposed calculation. Check the units and assumptions, recompute each step, and give a concise explanation of any discrepancy.
- Use Kimi K3.1 Pro to write a Blender script for a bookshelf with adjustable shelf count, width, height, and depth. State the units and assumptions, and explain which dimensions I should change.
- Use Kimi K3.1 Pro to extract the claims from the research passages above. For each, return the claim, a supporting quotation, a limitation, and an unanswered question; use null when evidence is missing.

## How to set up Kimi K3.1 Pro (batch) 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 K3.1 Pro (batch)**: 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-k3.1-pro:batch",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse finds Kimi K3.1 Pro (batch) on Spiral, shows the price and runs it.

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

## Kimi K3.1 Pro (batch) tools and prices

- [MoonshotAI: Kimi K3.1 Pro (batch)](https://spiral.ai/tools/openrouter/moonshotai/kimi-k3.1-pro%3Abatch) (OpenRouter): Up to $0.029746 per run at the default inputs. $0.4836 per 1M input tokens, $7.2579 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| top_k | 0 to … | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 943718 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |

## What can you do with Kimi K3.1 Pro (batch) in Muse?

Compare long reports, explain visual evidence, and turn detailed briefs into code with Kimi K3.1 Pro. Ask for source passages, explicit assumptions, and a concrete answer format so the result is easier to review.

### Fix a bug across several modules

Give Kimi K3.1 Pro the failing behavior, relevant code, and acceptance criteria. Request a patch, a regression check, and an explanation of the root cause.

### Plan a codebase migration

Ask Kimi K3.1 Pro to trace dependencies and divide a migration into reviewable changes. Require a compatibility check and rollback condition for each stage.

### Compare long financial reports

Use Kimi K3.1 Pro to compare revenue definitions, reporting periods, and stated risks across reports. Request source passages beside each finding and keep calculations separate from interpretation.

### Answer questions across a document collection

Ask Kimi K3.1 Pro to answer a specific question using supplied reports and manuals. Require document titles, section references, and an explicit statement when the evidence is insufficient.

### Write a parametric CAD script

Give Kimi K3.1 Pro a part description, dimensions, and constraints. Request editable CAD code with named parameters and a checklist for inspecting the resulting geometry.

### Create a Blender scene script

Ask Kimi K3.1 Pro to turn a written scene brief into a Blender script. Specify object dimensions, materials, camera placement, and the edits you expect to make later.

### Interpret a chart image

Have Kimi K3.1 Pro explain a supplied chart, identify its units and time range, and distinguish visible values from estimates. Ask it to mark unreadable labels instead of guessing.

### Extract comparable research records

Give Kimi K3.1 Pro several research passages and an example record. Request consistent entries containing the main claim, supporting passage, limitations, and unanswered questions.

## Overview

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

## Kimi K3.1 Pro (batch) in other agents

- [Amp](https://spiral.ai/integrations/amp/kimi-k3-1-pro-batch)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/kimi-k3-1-pro-batch)
- [Claude](https://spiral.ai/integrations/claude-desktop/kimi-k3-1-pro-batch)
- [Claude Code](https://spiral.ai/integrations/claude-code/kimi-k3-1-pro-batch)
- [Cline](https://spiral.ai/integrations/cline/kimi-k3-1-pro-batch)
- [Codex](https://spiral.ai/integrations/codex/kimi-k3-1-pro-batch)
- [Cursor](https://spiral.ai/integrations/cursor/kimi-k3-1-pro-batch)
- [Devin](https://spiral.ai/integrations/devin/kimi-k3-1-pro-batch)
- [dots](https://spiral.ai/integrations/dots/kimi-k3-1-pro-batch)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kimi-k3-1-pro-batch)
- [Gemini](https://spiral.ai/integrations/gemini/kimi-k3-1-pro-batch)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kimi-k3-1-pro-batch)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kimi-k3-1-pro-batch)
- [goose](https://spiral.ai/integrations/goose/kimi-k3-1-pro-batch)
- [Grok](https://spiral.ai/integrations/grok/kimi-k3-1-pro-batch)
- [Grok Build](https://spiral.ai/integrations/grok-build/kimi-k3-1-pro-batch)
- [Hermes](https://spiral.ai/integrations/hermes/kimi-k3-1-pro-batch)
- [Instinct](https://spiral.ai/integrations/instinct/kimi-k3-1-pro-batch)
- [Manus](https://spiral.ai/integrations/manus/kimi-k3-1-pro-batch)
- [Muse Code](https://spiral.ai/integrations/muse-code/kimi-k3-1-pro-batch)
- [n8n](https://spiral.ai/integrations/n8n/kimi-k3-1-pro-batch)
- [Notion](https://spiral.ai/integrations/notion/kimi-k3-1-pro-batch)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kimi-k3-1-pro-batch)
- [opencode](https://spiral.ai/integrations/opencode/kimi-k3-1-pro-batch)
- [Perplexity](https://spiral.ai/integrations/perplexity/kimi-k3-1-pro-batch)
- [Raycast](https://spiral.ai/integrations/raycast/kimi-k3-1-pro-batch)
- [VS Code](https://spiral.ai/integrations/vscode/kimi-k3-1-pro-batch)
- [Windsurf](https://spiral.ai/integrations/windsurf/kimi-k3-1-pro-batch)
- [Zapier](https://spiral.ai/integrations/zapier/kimi-k3-1-pro-batch)

## More Muse guides

- [Kimi K3.1 Pro](https://spiral.ai/integrations/muse/kimi-k3-1-pro)
- [Kimi Latest](https://spiral.ai/integrations/muse/kimi-latest)
- [Kimi K3](https://spiral.ai/integrations/muse/kimi-k3)
- [LFM2.5-24B-A2B](https://spiral.ai/integrations/muse/lfm2-5-24b-a2b)
- [Kimi K2.7 Code](https://spiral.ai/integrations/muse/kimi-k2-7-code)
- [LFM3-1.7B](https://spiral.ai/integrations/muse/lfm3-1-7b)

## Questions about Kimi K3.1 Pro (batch) in Muse

**Can Muse use Kimi K3.1 Pro (batch)?**

Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Kimi K3.1 Pro (batch) like any built-in tool.

**How much does Kimi K3.1 Pro (batch) cost in Muse?**

Up to $0.021978 per run at the default inputs. $0.3575 per 1M input tokens, $5.3625 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 K3.1 Pro (batch) in Muse?**

You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs Kimi K3.1 Pro (batch) on its own OpenRouter account.

**How long does it take to set up Kimi K3.1 Pro (batch) in Muse?**

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

**Does Muse wait while Kimi K3.1 Pro (batch) runs?**

Kimi K3.1 Pro (batch) runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.

**What is Kimi K3.1 Pro good at?**

Its documented strengths include coding, 3D creation, and financial research. Useful tasks include debugging code, writing CAD scripts, and comparing evidence across long reports.

**How much can Kimi K3.1 Pro read and write?**

Its context window is 1,048,576 tokens. That figure is not a verified maximum answer length: NVIDIA's model documentation leaves the separate output limit undisclosed.

**How does Kimi K3.1 Pro help with 3D modeling?**

It can write Blender and CAD scripts that build assets and revise geometry. For a practical first task, request a parametric model with named dimensions and a short list of assumptions.

**Can Kimi K3.1 Pro still make factual mistakes?**

Yes. Moonshot reports improvements in factual accuracy but also tests cases where errors remain likely. For research, request source passages and independently check consequential claims.

**How should I prompt Kimi K3.1 Pro for structured answers?**

Give a concrete example of the answer you want and explain what each field means. For document extraction, also specify how to represent missing information and where to put supporting passages.

