How to Use Kimi K2.7 Code in Gemini CLI
Kimi K2.7 Code is built for debugging, refactoring, and implementing changes across multiple files. Compared with Kimi K2.6, it targets longer coding tasks; Moonshot recommends Kimi K2.6 for general writing and conversation.
Prompts to try with Kimi K2.7 Code in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use Kimi K2.7 Code to investigate the failing tests in this project. Reproduce the failure, trace its cause, make a focused fix, and report the checks you ran.
Use Kimi K2.7 Code to add pagination to the existing search feature. Inspect the project's conventions, update the affected components, and test empty results and the final page.
Use Kimi K2.7 Code to consolidate duplicated validation logic in this repository. Preserve public interfaces and verify that existing error behavior stays consistent.
Use Kimi K2.7 Code to review the current diff against the issue's acceptance criteria. Identify concrete defects with file references and explain how to reproduce each one.
Use Kimi K2.7 Code to migrate this project's deprecated library calls. Inventory the affected files, make the changes in stages, and run the relevant checks after each stage.
How to set up Kimi K2.7 Code in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 K2.7 Code
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-k2.7-code", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Gemini CLI finds Kimi K2.7 Code on Spiral, shows the price and runs it.
Kimi K2.7 Code providers and prices
Spiral runs Kimi K2.7 Code through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.016002 per run at the default inputs. $0.78 per 1M input tokens, $3.90 per 1M output tokens.
Settings you can ask for
Ask Gemini CLI 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 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 235929 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 | ||
| Parallel tool calls | on or off |
Every API field of MoonshotAI: Kimi K2.7 Code is on its tool page: open its card above.
What can you do with Kimi K2.7 Code in Gemini CLI?
Kimi K2.7 Code can carry a bug fix or feature through changes across multiple project files. Give the agent a concrete result to achieve and ask it to verify the result with the project's checks.
Fix a bug across multiple files
Ask Kimi K2.7 Code to trace a reported failure through the relevant code, propose a repair, and check it against the reproduction steps.
Implement a complete feature
Give Kimi K2.7 Code acceptance criteria for a feature that touches several components. Request the implementation and a report of which criteria were verified.
Refactor shared logic
Have Kimi K2.7 Code consolidate duplicated behavior while preserving existing interfaces and test expectations.
Investigate failing tests
Give Kimi K2.7 Code the failure output and relevant implementation. Ask for the likely cause, a focused correction, and regression coverage.
Plan a code migration
Ask Kimi K2.7 Code to identify affected components, order the changes, and define checks for each stage of a migration.
Review a proposed change
Ask Kimi K2.7 Code to compare a patch with its requirements and identify concrete behavior changes that need testing.
Investigate recurring failures
Use Kimi K2.7 Code to examine successive test or incident reports, track unresolved hypotheses, and propose the next diagnostic step.
More on Kimi K2.7 Code and Gemini CLI
Overview
Kimi K2.7 Code in other agents
More Gemini CLI guides
Questions about Kimi K2.7 Code in Gemini CLI
Can Gemini CLI use Kimi K2.7 Code?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Kimi K2.7 Code like any built-in tool.
How much does Kimi K2.7 Code cost in Gemini CLI?
Up to $0.018665 per run at the default inputs. $0.78 per 1M input tokens, $4.55 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need an OpenRouter account to use Kimi K2.7 Code in Gemini CLI?
No. Spiral runs Kimi K2.7 Code 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 K2.7 Code in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Kimi K2.7 Code runs?
Kimi K2.7 Code runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.
What is Kimi K2.7 Code best suited for?
Use it for coding tasks that require several connected changes, such as tracing a bug, refactoring a codebase, or implementing a feature across multiple files.
How much context can Kimi K2.7 Code handle?
It has a 256K-token context window. For code review, prioritize the relevant implementation, requirements, and test results so the task stays focused.
Can Kimi K2.7 Code run without thinking?
No. Kimi K2.7 Code always uses thinking mode.
Which sampling settings does Moonshot recommend?
Moonshot recommends temperature 1.0 and top_p 0.95. Use those as your starting point when evaluating coding results.
Does Kimi K2.7 Code retain reasoning between turns?
Yes. It preserves reasoning across turns, which supports coding tasks that continue through several rounds of investigation and changes.
Start using Kimi K2.7 Code in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


