[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Kimi K3](https://spiral.ai/integrations/chatgpt/kimi-k3)

# How to Use Kimi K3 in ChatGPT

Kimi K3 suits long coding tasks and research that turns into working reports or dashboards. Its million-token context supports large projects, but explicit boundaries help prevent unrequested changes.

|  |  |
| --- | --- |
| Model | Kimi K3 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.085206 per run at the default inputs. $0.2496 per 1M input tokens, $20.80 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Kimi K3 in ChatGPT

- Use Kimi K3 to compare the research excerpts below. Create an evidence table, identify disagreements, and write a 600-word synthesis. Cite the supplied source labels and mark unanswered questions.
- Use Kimi K3 to turn the brief below into a 10-slide presentation outline. Give each slide one main claim, the evidence it needs, a chart suggestion, and speaker notes. Flag unsupported claims.
- Use Kimi K3 to design an interactive research report from the evidence below. Propose the narrative, charts, filters, and source notes. Explain what each interaction helps the reader investigate.
- Use Kimi K3 with high reasoning effort to review the computational method below. Check the assumptions, units, and validation approach, then propose a Python implementation plan.
- Use Kimi K3 with low reasoning effort to condense the brief below into a 300-word decision memo. Include the decision, supporting evidence, unresolved questions, and the next check to perform.

## How to set up Kimi K3 in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

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

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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**: 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",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Kimi K3 on Spiral, shows the price and runs it.

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

## Kimi K3 tools and prices

- [MoonshotAI: Kimi K3](https://spiral.ai/tools/openrouter/moonshotai/kimi-k3) (OpenRouter): Up to $0.085206 per run at the default inputs. $0.2496 per 1M input tokens, $20.80 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 … | — |  |
| logprobs |  | — |  |

## What can you do with Kimi K3 in ChatGPT?

Turn a dense brief into a research synthesis, presentation draft, or dashboard plan with Kimi K3. Specify the audience, evidence requirements, and desired length to give the work a clear finish.

### Fix bugs across a large codebase

Use Kimi K3 to trace a failing behavior through several modules, propose a focused fix, and check it against a reproducible test.

### Implement a feature from a specification

Give Kimi K3 the requirements, permitted changes, and acceptance checks. Ask it to carry the implementation through testing and report any unfinished requirements.

### Optimize a GPU kernel

Ask Kimi K3 to profile a kernel, investigate the bottleneck, and compare revisions against the same correctness tolerance and benchmark.

### Reproduce a computational research method

Use Kimi K3 to connect a paper's equations to executable code, document assumptions, and compare computed results with the published method.

### Build an interactive research report

Ask Kimi K3 to organize supplied evidence into a report with charts and drill-down views. Require a source for each quantitative claim.

### Draft a research presentation

Turn a research brief into a slide narrative with chart specifications, supporting evidence, and speaker notes using Kimi K3.

### Create a recurring analysis dashboard

Use Kimi K3 to turn fresh data into dashboard updates, explanations of changes, and a list of gaps that need investigation.

## Overview

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

## Kimi K3 in other agents

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

## More ChatGPT guides

- [Kimi K2.7 Code](https://spiral.ai/integrations/chatgpt/kimi-k2-7-code)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/chatgpt/kimi-k3-1-pro)
- [Kimi K2.6](https://spiral.ai/integrations/chatgpt/kimi-k2-6)
- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/chatgpt/kimi-k3-1-pro-batch)
- [Kimi K2.5](https://spiral.ai/integrations/chatgpt/kimi-k2-5)
- [Kimi Latest](https://spiral.ai/integrations/chatgpt/kimi-latest)

## Questions about Kimi K3 in ChatGPT

**Can ChatGPT use Kimi K3?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Kimi K3 like any built-in tool.

**How much does Kimi K3 cost in ChatGPT?**

Up to $0.085206 per run at the default inputs. $0.2496 per 1M input tokens, $20.80 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need an OpenRouter account to use Kimi K3 in ChatGPT?**

No. Spiral runs Kimi K3 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 K3 in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Kimi K3 runs?**

Kimi K3 runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

**What is Kimi K3 good at?**

Kimi K3 is suited to coding tasks that span many steps, large codebases, and research that becomes a report, presentation, or dashboard. Give it a concrete deliverable and a way to check the result.

**How much context can Kimi K3 handle?**

Moonshot documents a context window of one million tokens. Treat that as room for relevant evidence and conversation history, rather than a target to fill with unrelated material.

**Which reasoning setting should I choose?**

Moonshot documents low, high, and maximum effort, with maximum as the default. Start with low for bounded tasks and compare higher effort on work that requires several dependent decisions.

**What should I watch for with Kimi K3?**

Moonshot warns that ambiguous instructions can lead to unexpected decisions. State which changes are allowed, what needs review, and when the task is finished.

**Why does conversation history matter for Kimi K3?**

Kimi K3 expects complete assistant messages to be retained across conversation turns and tool calls, including reasoning and tool-call information. Keeping only the visible answer discards information Moonshot says the model requires.

