How to Use Kimi K3.1 Pro in Grok
Kimi K3.1 Pro handles coding, parametric 3D design, and financial research. Compared with Kimi K3, it improves these tasks while keeping a million-token context window.
Prompts to try with Kimi K3.1 Pro in Grok
Copy an example into Grok, or ask in your own words.
Use Kimi K3.1 Pro to compare the financial disclosures in this conversation. Reconcile revenue and operating income by period, cite the supporting passages, and flag incompatible units.
Use Kimi K3.1 Pro to explain the bug in the code pasted above. Give a minimal correction and three concrete inputs that would check it.
Use Kimi K3.1 Pro to draft parametric modeling code for a desk organizer measuring 200 by 100 by 80 mm. Make compartment count and wall thickness editable, and state all assumptions.
Use Kimi K3.1 Pro with maximum reasoning effort to examine the financial assumptions above. Show how the conclusion changes if revenue growth slows by five percentage points.
Use Kimi K3.1 Pro to answer my question using only the reference material in this conversation. Cite the relevant sections and identify anything the material does not establish.
How to set up Kimi K3.1 Pro in Grok
Pick the way that suits you. Each takes about two minutes.
Use the Grok connector
- Add a custom connector
In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.
- Check that it is connected
Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.
Use the Spiral skill
- Send Grok this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Kimi K3.1 Pro
One request; the result comes back by polling or a webhook.
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", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Grok finds Kimi K3.1 Pro on Spiral, shows the price and runs it.
Kimi K3.1 Pro providers and prices
Spiral runs Kimi K3.1 Pro through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.046871 per run at the default inputs. $0.3289 per 1M input tokens, $11.44 per 1M output tokens.
Settings you can ask for
Ask Grok for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 943718 | The most output tokens to generate. | |
| Top logprobs | 0 to 20 | ||
| Reasoning effort | none, low, high, or max | max | How much the model reasons. |
| Repetition penalty | 0 to 2 |
Every API field of MoonshotAI: Kimi K3.1 Pro is on its tool page: open its card above.
What can you do with Kimi K3.1 Pro in Grok?
Work through financial evidence, coding questions, and parametric design briefs with Kimi K3.1 Pro. State the desired result and ask for assumptions and evidence alongside the answer.
Repair a reproducible software bug
Give Kimi K3.1 Pro the failing behavior and relevant code. Request a focused patch and a regression check.
Build a game mechanic
Ask Kimi K3.1 Pro to implement a small Godot, Unity, or Unreal Engine mechanic with explicit controls and acceptance criteria.
Design an adjustable mechanical part
Give Kimi K3.1 Pro dimensions and constraints for a bracket or enclosure. Request parametric modeling code with named measurements.
Draft an architectural model
Ask Kimi K3.1 Pro for a parametric room or building model from a written brief, with units and dimensions stated explicitly.
Compare financial disclosures
Have Kimi K3.1 Pro reconcile figures across supplied disclosures, citing each source and flagging conflicting periods or units.
Review financial model assumptions
Ask Kimi K3.1 Pro to check the supplied formulas and assumptions, then explain which changes affect the conclusion.
Answer questions across lengthy reference material
Give Kimi K3.1 Pro a defined reference set and ask for an answer tied to named sections, with missing evidence identified.
Prepare a recurring research brief
Use Kimi K3.1 Pro to compare newly retrieved evidence with an earlier brief and report supported changes.
More on Kimi K3.1 Pro and Grok
Overview
Kimi K3.1 Pro in other agents
Questions about Kimi K3.1 Pro in Grok
Can Grok use Kimi K3.1 Pro?
Yes. Add Spiral to Grok as an MCP server, and Grok can find and run Kimi K3.1 Pro like any built-in tool.
How much does Kimi K3.1 Pro cost in Grok?
Up to $0.044753 per run at the default inputs. $0.31239 per 1M input tokens, $10.92299 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Grok plan is separate.
Do I need an OpenRouter account to use Kimi K3.1 Pro in Grok?
No. Spiral runs Kimi K3.1 Pro 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 K3.1 Pro in Grok?
About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.
Does Grok wait while Kimi K3.1 Pro runs?
Kimi K3.1 Pro runs in the background. Grok starts the run, checks on it and gives you the text, json when it's ready.
What is Kimi K3.1 Pro useful for?
Coding, parametric 3D design, and financial research are documented strengths. Give it a concrete deliverable, constraints, and a way to check the result.
How much context can Kimi K3.1 Pro handle?
Its context window is 1,048,576 tokens. That figure is not a promise of an equally long answer; NVIDIA's documentation leaves the separate output maximum undisclosed.
What kinds of 3D design suit Kimi K3.1 Pro?
Parametric mechanical parts and architectural models are documented strengths. Specify dimensions, units, and which measurements should remain editable.
Which reasoning effort should I choose?
Use low effort for straightforward work and try high or maximum effort for harder reasoning. Compare results on a representative task, since additional reasoning also affects response time and token usage.
Can I trust Kimi K3.1 Pro's financial research without checking it?
Verify material claims and calculations against the cited evidence. Moonshot still measured factual errors on its internal hard stress test, and explicitly says those results do not describe everyday error rates.
Start using Kimi K3.1 Pro in Grok
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Grok:
set up https://spiral.ai/SKILL.md


