[Integrations](https://spiral.ai/integrations) › [Devin](https://spiral.ai/integrations/devin) › [LFM3-1.7B](https://spiral.ai/integrations/devin/lfm3-1-7b)

# How to Use LFM3-1.7B in Devin

LFM3-1.7B suits focused text tasks, tool calling, and structured output with a 256K-token context window. Liquid AI advises against using it for agentic coding or complex multistep reasoning.

|  |  |
| --- | --- |
| Model | LFM3-1.7B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001069 per run at the default inputs. $0.104 per 1M input tokens, $0.26 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with LFM3-1.7B in Devin

- Use LFM3-1.7B to read the latest test log in this project and extract each failing test name, error message, and reported location as JSON. Preserve the original error text and do not infer causes.
- Use LFM3-1.7B to classify the issue descriptions in this project's issue export as bug, feature request, documentation, or uncertain. Return one label and one supporting quote per issue.
- Use LFM3-1.7B to extract configuration names, stated defaults, and descriptions from the project's README. Return JSON and use null wherever the README gives no value.
- Use LFM3-1.7B with temperature 0.1 and top-k 50 to label the supplied changelog entries as added, changed, fixed, removed, or uncertain. Preserve each entry's original wording.
- Use LFM3-1.7B to extract timestamps, error codes, and service names from the project's sample logs. Return one JSON record per log entry and leave unstated values null.

## How to set up LFM3-1.7B in Devin

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

### Use Spiral's MCP server

1. **Add a custom MCP**: Open Customize › MCPs. Click + and choose New MCP. Fill in:

2. **Sign in to Spiral and approve**: In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.

3. **Check it**: On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.

### Use the Spiral skill

1. **Send Devin 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 LFM3-1.7B**: 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-3-1.7b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Devin finds LFM3-1.7B on Spiral, shows the price and runs it.

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

## LFM3-1.7B tools and prices

- [LiquidAI: LFM3-1.7B](https://spiral.ai/tools/openrouter/liquid/lfm-3-1.7b) (OpenRouter): Up to $0.001069 per run at the default inputs. $0.104 per 1M input tokens, $0.26 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 LFM3-1.7B in Devin?

Turn project logs and issue descriptions into structured records with LFM3-1.7B. Keep each request focused on extraction or labeling, since Liquid AI advises against agentic coding.

### Support request triage

Ask LFM3-1.7B to label each request using your queue definitions and quote the words that justify the label.

### Structured record extraction

Turn order messages or intake notes into JSON with LFM3-1.7B. Specify the required fields and use null for missing information.

### Answers from supplied reference text

Give LFM3-1.7B relevant help-center excerpts and ask for a short answer with supporting passages and any information still missing.

### Tool selection for routine lookups

Ask LFM3-1.7B to select a lookup tool for an order or inventory question, then explain the returned result.

### Issue labeling

Have LFM3-1.7B classify issue descriptions against a fixed taxonomy, returning an uncertainty label when the text does not establish a category.

### Multilingual message routing

Use LFM3-1.7B to label intent in messages written in its supported languages, keeping the original wording beside each classification for review.

### Log detail extraction

Ask LFM3-1.7B to extract timestamps, error codes, and affected services from log text into records without inferring a root cause.

## Overview

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

## LFM3-1.7B in other agents

- [Amp](https://spiral.ai/integrations/amp/lfm3-1-7b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/lfm3-1-7b)
- [Claude](https://spiral.ai/integrations/claude-desktop/lfm3-1-7b)
- [Claude Code](https://spiral.ai/integrations/claude-code/lfm3-1-7b)
- [Cline](https://spiral.ai/integrations/cline/lfm3-1-7b)
- [Codex](https://spiral.ai/integrations/codex/lfm3-1-7b)
- [Cursor](https://spiral.ai/integrations/cursor/lfm3-1-7b)
- [dots](https://spiral.ai/integrations/dots/lfm3-1-7b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/lfm3-1-7b)
- [Gemini](https://spiral.ai/integrations/gemini/lfm3-1-7b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/lfm3-1-7b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/lfm3-1-7b)
- [goose](https://spiral.ai/integrations/goose/lfm3-1-7b)
- [Grok](https://spiral.ai/integrations/grok/lfm3-1-7b)
- [Grok Build](https://spiral.ai/integrations/grok-build/lfm3-1-7b)
- [Hermes](https://spiral.ai/integrations/hermes/lfm3-1-7b)
- [Instinct](https://spiral.ai/integrations/instinct/lfm3-1-7b)
- [Manus](https://spiral.ai/integrations/manus/lfm3-1-7b)
- [Muse](https://spiral.ai/integrations/muse/lfm3-1-7b)
- [Muse Code](https://spiral.ai/integrations/muse-code/lfm3-1-7b)
- [n8n](https://spiral.ai/integrations/n8n/lfm3-1-7b)
- [Notion](https://spiral.ai/integrations/notion/lfm3-1-7b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/lfm3-1-7b)
- [opencode](https://spiral.ai/integrations/opencode/lfm3-1-7b)
- [Perplexity](https://spiral.ai/integrations/perplexity/lfm3-1-7b)
- [Raycast](https://spiral.ai/integrations/raycast/lfm3-1-7b)
- [VS Code](https://spiral.ai/integrations/vscode/lfm3-1-7b)
- [Windsurf](https://spiral.ai/integrations/windsurf/lfm3-1-7b)
- [Zapier](https://spiral.ai/integrations/zapier/lfm3-1-7b)

## More Devin guides

- [LFM2.5-24B-A2B](https://spiral.ai/integrations/devin/lfm2-5-24b-a2b)
- [Ling 3.0 Flash](https://spiral.ai/integrations/devin/ling-3-0-flash)
- [Kimi Latest](https://spiral.ai/integrations/devin/kimi-latest)
- [Ling 3.0 Flash VL](https://spiral.ai/integrations/devin/ling-3-0-flash-vl)
- [Kimi K3.1 Pro (batch)](https://spiral.ai/integrations/devin/kimi-k3-1-pro-batch)
- [Ling 3.0 Tiny](https://spiral.ai/integrations/devin/ling-3-0-tiny)

## Questions about LFM3-1.7B in Devin

**Can Devin use LFM3-1.7B?**

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run LFM3-1.7B like any built-in tool.

**How much does LFM3-1.7B cost in Devin?**

Up to $0.001069 per run at the default inputs. $0.104 per 1M input tokens, $0.26 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Devin plan is separate.

**Do I need an OpenRouter account to use LFM3-1.7B in Devin?**

No. Spiral runs LFM3-1.7B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up LFM3-1.7B in Devin?**

About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.

**Does Devin wait while LFM3-1.7B runs?**

LFM3-1.7B runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.

**What is LFM3-1.7B best suited to?**

Use it for focused tasks such as extracting records, labeling requests, producing structured output, and selecting tools. Give it a clear task and a specific result to return.

**How much text can LFM3-1.7B handle?**

Its context window holds 256K tokens across input and output combined. Leave room for the response when supplying long text.

**Which languages does LFM3-1.7B support?**

Liquid AI lists English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish. Test your own terminology and examples before using it for a language-specific workflow.

**Is LFM3-1.7B suitable for autonomous coding?**

Liquid AI advises against agentic coding and complex multistep reasoning. In a coding assistant, keep requests bounded, such as extracting details from logs or classifying issues against supplied rules.

**Which sampling settings should I start with?**

Liquid AI's generation example uses temperature 0.1 and top-k 50. Start there for focused text tasks, then compare results against examples you have already checked.

