[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Kimi Latest](https://spiral.ai/integrations/gemini-cli/kimi-latest)

# How to Use Kimi Latest in Gemini CLI

Use Kimi Latest for large-codebase work, research synthesis, and tasks that need several tool calls. Unlike the fixed Kimi K3 name, it follows a changing model target, currently Kimi K3.

|  |  |
| --- | --- |
| Model | Kimi Latest |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.058611 per run at the default inputs. $0.23712 per 1M input tokens, $14.30715 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Kimi Latest in Gemini CLI

- Use Kimi Latest to trace the failing test through this repository, reproduce the failure, and make the smallest repair. Change only code needed for that failure and report the test result.
- Use Kimi Latest to map the authentication flow across this project's files. Produce a dependency map and identify three places where error handling needs investigation, with file and line references.
- Use Kimi Latest to plan a staged refactor of the data-access layer. Read the existing interfaces and tests, preserve public behavior, and give acceptance checks for each stage before editing.
- Use Kimi Latest to compare the implementation in this repository with the equations in its research notes. List mismatches, propose validation cases, and separate confirmed errors from uncertain interpretations.
- Use Kimi Latest to investigate this project's slowest benchmark. Profile before proposing changes, modify only the measured bottleneck, and report before-and-after results with correctness checks.

## How to set up Kimi Latest in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 Latest**: 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-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Kimi Latest on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Kimi Latest tools and prices

- [MoonshotAI: Kimi Latest](https://spiral.ai/tools/openrouter/~moonshotai/kimi-latest) (OpenRouter): Up to $0.058611 per run at the default inputs. $0.23465 per 1M input tokens, $14.30715 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 … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with Kimi Latest in Gemini CLI?

Kimi Latest can help carry an engineering task across a large repository, from tracing dependencies to checking a repair. Define the files and behavior in scope so its current Kimi K3 target has clear boundaries.

### Fix bugs across a large repository

Ask Kimi Latest to trace a failure through the relevant code, reproduce it, and propose a focused repair. Specify the permitted scope and require test evidence.

### Plan a cross-module refactor

Have Kimi Latest map dependencies and propose a staged refactor with acceptance checks. Define the behavior that each stage must preserve.

### Turn research methods into code

Give Kimi Latest a paper's methods and equations as text, then request an implementation plan, executable code, and checks against the reported results.

### Compare competing proposals

Supply proposal text and ask Kimi Latest to compare scope, assumptions, exclusions, and unanswered questions. Require supporting passages for each conclusion.

### Prepare a research brief

Have Kimi Latest synthesize retrieved sources into a concise brief with dated evidence, disagreements, and open questions. Define the audience and decision the brief must support.

### Explain Chinese and English material

Use Kimi Latest to explain supplied Chinese material in English, or English material in Chinese. Provide a terminology list and ask it to flag ambiguous passages.

### Review operational incidents

Give Kimi Latest incident timelines, log excerpts, and investigation notes as text. Ask for a causal hypothesis, conflicting evidence, and the next checks to run.

### Answer questions from reference material

Supply relevant policy or product documentation as text and ask Kimi Latest to answer with section references. Require it to identify questions the material does not resolve.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Kimi Latest in other agents

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

## More Gemini CLI guides

- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/gemini-cli/kimi-k3-1-pro-batch)
- [LFM2.5-24B-A2B](https://spiral.ai/integrations/gemini-cli/lfm2-5-24b-a2b)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/gemini-cli/kimi-k3-1-pro)
- [LFM3-1.7B](https://spiral.ai/integrations/gemini-cli/lfm3-1-7b)
- [Kimi K3](https://spiral.ai/integrations/gemini-cli/kimi-k3)
- [Ling 3.0 Flash](https://spiral.ai/integrations/gemini-cli/ling-3-0-flash)

## Questions about Kimi Latest in Gemini CLI

**Can Gemini CLI use Kimi Latest?**

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

**How much does Kimi Latest cost in Gemini CLI?**

Up to $0.058611 per run at the default inputs. $0.23712 per 1M input tokens, $14.30715 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 Latest in Gemini CLI?**

No. Spiral runs Kimi Latest 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 Latest in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Kimi Latest runs?**

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

**Does Kimi Latest always mean the same model?**

No. Its target can change, and the current listing points to Kimi K3. Treat saved prompts as something to recheck when the target changes.

**What is Kimi Latest best suited for?**

With its current Kimi K3 target, it suits sustained coding tasks, research synthesis, and knowledge work that takes several steps. Give it a concrete deliverable and a clear definition of done.

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

The alias can reach a 1,048,576-token context window, but the actual limit depends on its target. Use that capacity for relevant evidence, and ask for a bounded answer such as a comparison table or a short decision memo.

**Can Kimi Latest answer questions about today's events?**

Give it current source material or have the agent retrieve it first. Kimi's training knowledge alone cannot reliably answer time-sensitive questions.

**Which languages are a sensible starting point?**

Chinese and English are explicitly highlighted in Moonshot's example instructions. For bilingual work, specify the output language and supply a glossary for names and technical terms.

