How to Use Mi:dm K 3.0 Pro in Claude Code
Mi:dm K 3.0 Pro is KT’s text reasoning model for tasks such as comparing documents and extracting structured answers. Its 261,795-token context window makes it a candidate for reviewing substantial source material in one request.
Prompts to try with Mi:dm K 3.0 Pro in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Mi:dm K 3.0 Pro to compare this project’s implementation with its README requirements. Report suspected mismatches with file paths, line references, and a proposed verification step.
Use Mi:dm K 3.0 Pro to review the current diff against the existing tests. Identify changed behavior that lacks coverage and propose three focused test cases.
Use Mi:dm K 3.0 Pro to analyze the failing test output and relevant source files. Separate observed failures from possible causes, then recommend the smallest change to investigate first.
Use Mi:dm K 3.0 Pro to extract the project’s documented configuration rules into JSON. Define a schema for setting, requirement, default, and source reference; use null for undocumented defaults.
Use Mi:dm K 3.0 Pro to compare the old and new API specifications in this repository. Produce a table of changed request shapes, response shapes, and migration questions, citing the relevant sections.
How to set up Mi:dm K 3.0 Pro in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 Mi:dm K 3.0 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": "kt/midm-k-3.0-pro", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds Mi:dm K 3.0 Pro on Spiral, shows the price and runs it.
Mi:dm K 3.0 Pro providers and prices
Spiral runs Mi:dm K 3.0 Pro through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.00427 per run at the default inputs. $0.26 per 1M input tokens, $1.04 per 1M output tokens.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 235615 | 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). | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of KT: Mi:dm K 3.0 Pro is on its tool page: open its card above.
What can you do with Mi:dm K 3.0 Pro in Claude Code?
Use Mi:dm K 3.0 Pro to compare project code, specifications, and test output in one text review. Request code references and proposed checks so you can inspect each finding.
Compare policy revisions
Give the model two labeled policy texts and ask for changed obligations, conflicting clauses, and supporting passages.
Check requirements coverage
Compare a proposal with written requirements. Request a table of covered, missing, and ambiguous items with evidence.
Extract structured records
Turn supplied text into schema-constrained records for review. Define how missing values should be represented and validate the output.
Review code against specifications
Supply relevant source code and its specification, then request suspected mismatches, code references, and tests that could confirm them.
Prepare an incident brief
Provide text logs and incident notes. Ask for a timeline that separates recorded events, possible explanations, and unanswered questions.
Build a decision memo
Supply proposals and explicit decision criteria. Request a comparison grounded in the supplied evidence, with assumptions identified separately.
More on Mi:dm K 3.0 Pro and Claude Code
Overview
Mi:dm K 3.0 Pro in other agents
More Claude Code guides
Questions about Mi:dm K 3.0 Pro in Claude Code
Can Claude Code use Mi:dm K 3.0 Pro?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Mi:dm K 3.0 Pro like any built-in tool.
How much does Mi:dm K 3.0 Pro cost in Claude Code?
Up to $0.00427 per run at the default inputs. $0.26 per 1M input tokens, $1.04 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an OpenRouter account to use Mi:dm K 3.0 Pro in Claude Code?
No. Spiral runs Mi:dm K 3.0 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 Mi:dm K 3.0 Pro in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Mi:dm K 3.0 Pro runs?
Mi:dm K 3.0 Pro runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
What should I try Mi:dm K 3.0 Pro for?
Start with text tasks that require comparing evidence, such as reconciling two policies or checking a proposal against requirements. These are suggested applications of its reasoning capability, rather than claims of measured superiority.
How much context does Mi:dm K 3.0 Pro support?
KT lists 261,795 tokens. Account for instructions, earlier messages, and tool results when deciding how much source text to include.
Can Mi:dm K 3.0 Pro analyze screenshots or recordings?
Its listed input and output are text only. For a screenshot or recording, provide extracted text or a transcript for analysis.
Can Mi:dm K 3.0 Pro return structured JSON?
Yes, it supports output constrained by a JSON schema. Check that generation completed, then parse and validate the result before using it.
How should I prompt Mi:dm K 3.0 Pro for document analysis?
Give each source a label, state the question, and specify the answer format. Ask for supporting passages and an explicit unknown when the supplied text does not answer the question.
Start using Mi:dm K 3.0 Pro in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


