[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [LFM2.5-24B-A2B](https://spiral.ai/integrations/antigravity/lfm2-5-24b-a2b)

# How to Use LFM2.5-24B-A2B in Google Antigravity

Use LFM2.5-24B-A2B for text-based agents that follow detailed instructions and call tools across multiple steps. Its 131,072-token context supports long conversations and documents, while built-in reasoning stays on for every answer.

|  |  |
| --- | --- |
| Model | LFM2.5-24B-A2B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.00373 per run at the default inputs. $0.065 per 1M input tokens, $0.91 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with LFM2.5-24B-A2B in Google Antigravity

- Use LFM2.5-24B-A2B to investigate the first failing test in this project. Trace the relevant code, make the smallest justified fix, and rerun the affected tests; report the commands and results.
- Use LFM2.5-24B-A2B to compare the README's configuration instructions with the implementation. List mismatches with file and line references, then propose corrections grounded in the code.
- Use LFM2.5-24B-A2B to review the current diff for missing error handling. Follow each changed call to its implementation and report only findings supported by a concrete failure path.
- Use LFM2.5-24B-A2B to turn the requirements in this project's issue notes into an implementation plan. Identify dependencies, affected files, and a verification step for each requirement.
- Use LFM2.5-24B-A2B with temperature 0.1 and top-k 50 to check this project's Spanish and French interface text against the English strings. Preserve interpolation tokens and report meaning changes with file references.

## How to set up LFM2.5-24B-A2B 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 LFM2.5-24B-A2B**: 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": "liquid/lfm-2.5-24b-a2b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds LFM2.5-24B-A2B on Spiral, shows the price and runs it.

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

## LFM2.5-24B-A2B tools and prices

- [LiquidAI: LFM2.5-24B-A2B](https://spiral.ai/tools/openrouter/liquid/lfm-2.5-24b-a2b) (OpenRouter): Up to $0.00373 per run at the default inputs. $0.065 per 1M input tokens, $0.91 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 LFM2.5-24B-A2B in Google Antigravity?

Use LFM2.5-24B-A2B to trace project code, work through a focused fix, and check the result with tools. Give it a bounded task and explicit acceptance criteria, then require test evidence.

### Research briefs with sources

Use LFM2.5-24B-A2B to search for evidence, compare findings, and write a brief with links attached to factual claims. Ask it to flag unanswered questions.

### Support answers grounded in policy

Have LFM2.5-24B-A2B retrieve the relevant policy passages, reconcile them with the customer's request, and draft a response that identifies missing information.

### Long document comparisons

Give LFM2.5-24B-A2B the text of two specifications or proposals. Request a comparison of requirements, contradictions, and open decisions with passage references.

### Small code fixes with verification

Ask LFM2.5-24B-A2B to inspect a failing test, trace the relevant code, and propose a focused patch. Require test results before accepting the fix.

### Multilingual request triage

Use LFM2.5-24B-A2B to summarize incoming text in supported languages and assign categories from a written rubric. Review ambiguous classifications.

### Daily operational digests

Have LFM2.5-24B-A2B compare current tool results with the previous report, identify changes, and produce a short digest with evidence for each exception.

### Plans with dependencies

Give LFM2.5-24B-A2B a goal, constraints, and available resources. Request an ordered plan that makes dependencies and unresolved assumptions explicit.

### Multistep calculation checks

Ask LFM2.5-24B-A2B to compare quantities, schedules, or capacity assumptions from supplied text. Require stated units and an independent calculation check.

## Overview

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

## LFM2.5-24B-A2B in other agents

- [Amp](https://spiral.ai/integrations/amp/lfm2-5-24b-a2b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/lfm2-5-24b-a2b)
- [Claude](https://spiral.ai/integrations/claude-desktop/lfm2-5-24b-a2b)
- [Claude Code](https://spiral.ai/integrations/claude-code/lfm2-5-24b-a2b)
- [Cline](https://spiral.ai/integrations/cline/lfm2-5-24b-a2b)
- [Codex](https://spiral.ai/integrations/codex/lfm2-5-24b-a2b)
- [Cursor](https://spiral.ai/integrations/cursor/lfm2-5-24b-a2b)
- [Devin](https://spiral.ai/integrations/devin/lfm2-5-24b-a2b)
- [dots](https://spiral.ai/integrations/dots/lfm2-5-24b-a2b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/lfm2-5-24b-a2b)
- [Gemini](https://spiral.ai/integrations/gemini/lfm2-5-24b-a2b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/lfm2-5-24b-a2b)
- [goose](https://spiral.ai/integrations/goose/lfm2-5-24b-a2b)
- [Grok](https://spiral.ai/integrations/grok/lfm2-5-24b-a2b)
- [Grok Build](https://spiral.ai/integrations/grok-build/lfm2-5-24b-a2b)
- [Hermes](https://spiral.ai/integrations/hermes/lfm2-5-24b-a2b)
- [Instinct](https://spiral.ai/integrations/instinct/lfm2-5-24b-a2b)
- [Manus](https://spiral.ai/integrations/manus/lfm2-5-24b-a2b)
- [Muse](https://spiral.ai/integrations/muse/lfm2-5-24b-a2b)
- [Muse Code](https://spiral.ai/integrations/muse-code/lfm2-5-24b-a2b)
- [n8n](https://spiral.ai/integrations/n8n/lfm2-5-24b-a2b)
- [Notion](https://spiral.ai/integrations/notion/lfm2-5-24b-a2b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/lfm2-5-24b-a2b)
- [opencode](https://spiral.ai/integrations/opencode/lfm2-5-24b-a2b)
- [Perplexity](https://spiral.ai/integrations/perplexity/lfm2-5-24b-a2b)
- [Raycast](https://spiral.ai/integrations/raycast/lfm2-5-24b-a2b)
- [VS Code](https://spiral.ai/integrations/vscode/lfm2-5-24b-a2b)
- [Windsurf](https://spiral.ai/integrations/windsurf/lfm2-5-24b-a2b)
- [Zapier](https://spiral.ai/integrations/zapier/lfm2-5-24b-a2b)

## More Google Antigravity guides

- [Kimi Latest](https://spiral.ai/integrations/antigravity/kimi-latest)
- [LFM3-1.7B](https://spiral.ai/integrations/antigravity/lfm3-1-7b)
- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/antigravity/kimi-k3-1-pro-batch)
- [Ling 3.0 Flash](https://spiral.ai/integrations/antigravity/ling-3-0-flash)
- [Kimi K3.1 Pro](https://spiral.ai/integrations/antigravity/kimi-k3-1-pro)
- [Ling 3.0 Flash VL](https://spiral.ai/integrations/antigravity/ling-3-0-flash-vl)

## Questions about LFM2.5-24B-A2B in Google Antigravity

**Can Google Antigravity use LFM2.5-24B-A2B?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run LFM2.5-24B-A2B like any built-in tool.

**How much does LFM2.5-24B-A2B cost in Google Antigravity?**

Up to $0.00373 per run at the default inputs. $0.065 per 1M input tokens, $0.91 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 LFM2.5-24B-A2B in Google Antigravity?**

No. Spiral runs LFM2.5-24B-A2B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up LFM2.5-24B-A2B in Google Antigravity?**

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

**Does Google Antigravity wait while LFM2.5-24B-A2B runs?**

LFM2.5-24B-A2B runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is LFM2.5-24B-A2B good at?**

Tool use and following detailed instructions are its clearest strengths. Consider it for tasks that combine several lookups, decisions, or checks before producing an answer.

**Where does LFM2.5-24B-A2B fall short?**

Liquid AI reports that larger comparison models retain an edge on knowledge-heavy and coding benchmarks. For factual research, pair it with retrieved sources or web search; for code changes, check the result with tests.

**How much context can LFM2.5-24B-A2B handle?**

The documented context length is 131,072 tokens. It is a text-only model, so use document text or transcripts for document analysis.

**Which languages does LFM2.5-24B-A2B support?**

Liquid AI lists 16 languages: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish. The list does not establish equal accuracy across languages, so check examples from your actual task.

**Can I turn off reasoning in LFM2.5-24B-A2B?**

No supported thinking-off switch is documented. Reasoning and the final answer share the generation token limit, so leave room for both.

