[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [Codestral 2508](https://spiral.ai/integrations/antigravity/codestral-2508)

# How to Use Codestral 2508 in Google Antigravity

Codestral 2508 is built for code completion, filling gaps in existing code, and focused code generation. Mistral reports 50% fewer runaway generations than prior Codestral releases in its evaluation.

|  |  |
| --- | --- |
| Model | Codestral 2508 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.004807 per run at the default inputs. $0.39 per 1M input tokens, $1.17 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Codestral 2508 in Google Antigravity

- Use Codestral 2508 to complete the unfinished function in the current file. Read its callers and nearby tests first, preserve the signature, and change only the missing implementation.
- Use Codestral 2508 to propose the smallest fix for the failing test. Include the relevant function and failure output in the request, preserve existing behavior elsewhere, and show the diff.
- Use Codestral 2508 to write regression tests for the function I selected. Follow this project's test conventions and cover empty input, boundary values, and the reported failure.
- Use Codestral 2508 with temperature 0.2 to complete the selected validation block. Match the adjacent rules, reuse existing helpers, and return only the missing code.
- Use Codestral 2508 to implement one helper for the requirement in the current issue. Include the relevant types and dependency versions, preserve the public interface, and add examples of expected results.

## How to set up Codestral 2508 in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 Codestral 2508**: 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": "mistralai/codestral-2508",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds Codestral 2508 on Spiral, shows the price and runs it.

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

## Codestral 2508 tools and prices

- [Mistral: Codestral 2508](https://spiral.ai/tools/openrouter/mistralai/codestral-2508) (OpenRouter): Up to $0.004807 per run at the default inputs. $0.39 per 1M input tokens, $1.17 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 204800 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Codestral 2508 in Google Antigravity?

Codestral can help complete functions and draft focused edits from the code your coding agent supplies. Give it the relevant project context and define the exact scope of the requested change.

### Complete an unfinished function

Ask Codestral 2508 to fill a missing function body using the surrounding code, signature, and expected results.

### Implement a small helper

Give Codestral 2508 a focused specification for a parser, validator, or data transformation. Include examples of accepted and rejected inputs.

### Draft a targeted bug fix

Provide Codestral 2508 with the failing function, observed result, and expected result. Request the smallest proposed correction.

### Write regression tests

Ask Codestral 2508 for tests covering a reported failure, boundary inputs, and normal behavior in your chosen test framework.

### Generate a query from a schema

Supply Codestral 2508 with table definitions, the SQL dialect, and the desired result. Request one query with explicit handling of nulls and duplicates.

### Complete repetitive validation code

Show Codestral 2508 an existing validation rule and ask it to complete the remaining rules in the same style, with exact error messages.

### Create a runnable example

Ask Codestral 2508 to turn a narrow coding requirement into a complete example with imports, a function, and assertions for the expected results.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## Codestral 2508 in other agents

- [Amp](https://spiral.ai/integrations/amp/codestral-2508)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/codestral-2508)
- [Claude](https://spiral.ai/integrations/claude-desktop/codestral-2508)
- [Claude Code](https://spiral.ai/integrations/claude-code/codestral-2508)
- [Cline](https://spiral.ai/integrations/cline/codestral-2508)
- [Codex](https://spiral.ai/integrations/codex/codestral-2508)
- [Cursor](https://spiral.ai/integrations/cursor/codestral-2508)
- [Devin](https://spiral.ai/integrations/devin/codestral-2508)
- [dots](https://spiral.ai/integrations/dots/codestral-2508)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/codestral-2508)
- [Gemini](https://spiral.ai/integrations/gemini/codestral-2508)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/codestral-2508)
- [goose](https://spiral.ai/integrations/goose/codestral-2508)
- [Grok](https://spiral.ai/integrations/grok/codestral-2508)
- [Grok Build](https://spiral.ai/integrations/grok-build/codestral-2508)
- [Hermes](https://spiral.ai/integrations/hermes/codestral-2508)
- [Instinct](https://spiral.ai/integrations/instinct/codestral-2508)
- [Manus](https://spiral.ai/integrations/manus/codestral-2508)
- [Muse](https://spiral.ai/integrations/muse/codestral-2508)
- [Muse Code](https://spiral.ai/integrations/muse-code/codestral-2508)
- [n8n](https://spiral.ai/integrations/n8n/codestral-2508)
- [Notion](https://spiral.ai/integrations/notion/codestral-2508)
- [OpenClaw](https://spiral.ai/integrations/openclaw/codestral-2508)
- [opencode](https://spiral.ai/integrations/opencode/codestral-2508)
- [Perplexity](https://spiral.ai/integrations/perplexity/codestral-2508)
- [Raycast](https://spiral.ai/integrations/raycast/codestral-2508)
- [VS Code](https://spiral.ai/integrations/vscode/codestral-2508)
- [Windsurf](https://spiral.ai/integrations/windsurf/codestral-2508)
- [Zapier](https://spiral.ai/integrations/zapier/codestral-2508)

## More Google Antigravity guides

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

## Questions about Codestral 2508 in Google Antigravity

**Can Google Antigravity use Codestral 2508?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Codestral 2508 like any built-in tool.

**How much does Codestral 2508 cost in Google Antigravity?**

Up to $0.004807 per run at the default inputs. $0.39 per 1M input tokens, $1.17 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenRouter account to use Codestral 2508 in Google Antigravity?**

No. Spiral runs Codestral 2508 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Codestral 2508 in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while Codestral 2508 runs?**

Codestral 2508 runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is Codestral best suited to?**

Codestral is designed for frequent code completions, filling gaps in existing code, and generating code from instructions. Start with a bounded task, such as completing one function or implementing one helper.

**Can Codestral complete code between two existing sections?**

Yes. Filling gaps in partial code is a core Codestral task. Include the surrounding code and clearly identify the section you want completed.

**Does Codestral support multiple programming languages?**

Yes. Mistral describes Codestral 2508 as supporting a wide range of languages and tasks. Name the target language, runtime, and dependencies in your request.

**Which settings matter for focused code generation?**

Start with a low temperature, around 0.2, for focused completions. Mistral recommends adjusting temperature or top-p, rather than changing both together.

**How much code should I include in a request?**

Include the relevant function, its dependencies, and the expected behavior. Leave room for the answer: context accounting includes both your input and the generated output.

