[Integrations](https://spiral.ai/integrations) › [Gemini](https://spiral.ai/integrations/gemini) › [Command A](https://spiral.ai/integrations/gemini/command-a)

# How to Use Command A in Gemini

Command A handles document-based questions, multilingual support, and SQL generation. Its 256,000-token context window suits long source material, while replies are capped at 8,000 tokens.

|  |  |
| --- | --- |
| Model | Command A |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.053363 per run at the default inputs. $3.25 per 1M input tokens, $13.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Command A in Gemini

- Use Command A to answer my next questions using only the policy passages I provide in this conversation. Reference the passage labels and say 'Not found in the supplied sources' when the answer is missing.
- Use Command A to summarize the quarterly report text above in 400 words. Separate reported results, management's explanations, and unresolved questions; preserve the reporting periods and units.
- Use Command A to draft a French customer reply from the product details and refund policy above. Keep it under 150 words, preserve product names, and avoid adding promises absent from the policy.
- Use Command A to compare the three proposals described above. Return a table covering scope, deadlines, dependencies, and unanswered questions, with a reference to the supplied text for each conclusion.
- Use Command A to extract action items from the meeting transcript above. Return only a JSON array containing the action, owner, due date, and supporting quote; use null when an owner or date is missing.

## How to set up Command A in Gemini

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

### Use the Gemini connector

1. **Open Connected Apps**: On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

2. **Add Spiral as a custom app**: Under Custom apps, click Add a custom app and paste this MCP server URL:

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

3. **Sign in to Spiral and approve**: Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Gemini 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 Command A**: 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": "cohere/command-a",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini finds Command A on Spiral, shows the price and runs it.

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

## Command A tools and prices

- [Cohere: Command A](https://spiral.ai/tools/openrouter/cohere/command-a) (OpenRouter): Up to $0.053363 per run at the default inputs. $3.25 per 1M input tokens, $13.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 8192 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Command A in Gemini?

Get answers from long passages, summaries of business material, and replies in a requested language. Command A works well with labeled sources and explicit instructions about answer length and format.

### Employee policy answers

Answer questions from supplied HR policies, separating rules by office location and referencing the relevant passage.

### Financial report briefs

Summarize long financial reports into a short brief with reported figures, reporting periods, and source references.

### SQL query drafting

Turn a reporting question and database schema into a draft SQL query, with assumptions about joins and date ranges stated explicitly.

### Code translation

Rewrite an existing function in another programming language, preserving its behavior and identifying differences that need review.

### Multilingual customer replies

Draft answers in French, Spanish, German, or Japanese using supplied product information and support policies.

### Knowledge base answers

Combine retrieved help articles into a direct answer with references to the passages that support it.

### Support request categorization

Sort incoming requests into defined categories using a few labeled examples, then return a concise result for each request.

### Structured text extraction

Extract dates, organizations, owners, and action items from business text into a requested JSON structure, marking missing values explicitly.

## Overview

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

## Command A in other agents

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

## More Gemini guides

- [Codestral 2508](https://spiral.ai/integrations/gemini/codestral-2508)
- [Command A Plus](https://spiral.ai/integrations/gemini/command-a-plus)
- [Claude Sonnet Latest](https://spiral.ai/integrations/gemini/claude-sonnet-latest)
- [Command R (08-2024)](https://spiral.ai/integrations/gemini/command-r-08-2024)
- [Claude Sonnet 5.5](https://spiral.ai/integrations/gemini/claude-sonnet-5-5)
- [Command R Plus (08-2024)](https://spiral.ai/integrations/gemini/command-r-plus-08-2024)

## Questions about Command A in Gemini

**Can Gemini use Command A?**

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

**How much does Command A cost in Gemini?**

Up to $0.053363 per run at the default inputs. $3.25 per 1M input tokens, $13.00 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 plan is separate.

**Do I need an OpenRouter account to use Command A in Gemini?**

No. Spiral runs Command A on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Command A in Gemini?**

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

**Does Gemini wait while Command A runs?**

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

**What is Command A good at?**

Command A is useful for answering questions from supplied documents, summarizing business information, multilingual text work, and SQL generation. Give it the relevant source material and specify the result you need.

**How much text can Command A handle?**

Cohere documents a 256,000-token context window and a maximum output of 8,000 tokens. Plan long writing tasks as separate sections rather than requesting a book-length response in one pass.

**Which languages does Command A support?**

Command A supports 23 languages, including English, French, Spanish, Italian, German, Portuguese, Japanese, and Korean. State the desired response language explicitly when working across languages.

**Is Command A useful for coding?**

SQL generation and code translation are documented uses. Cohere recommends a low temperature for code generation; include the database schema, target language, and expected behavior in your request.

**Why does Command A add introductions and code fences?**

Command A is conversational and verbose by default. Use a system instruction that asks for only the requested answer, with no introduction, follow-up question, or Markdown code fences.

