[Integrations](https://spiral.ai/integrations) › [Devin](https://spiral.ai/integrations/devin) › [Llama 3.1 8B Instruct](https://spiral.ai/integrations/devin/llama-3-1-8b-instruct)

# How to Use Llama 3.1 8B Instruct in Devin

Use Llama 3.1 8B Instruct for document summaries, multilingual conversations, and focused coding help. Compared with Llama 3 8B Instruct, it expands context from 8K to 128K tokens and supports eight languages.

|  |  |
| --- | --- |
| Model | Llama 3.1 8B Instruct |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.000215 per run at the default inputs. $0.026 per 1M input tokens, $0.052 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Llama 3.1 8B Instruct in Devin

- Use Llama 3.1 8B Instruct to read the README and explain the project's purpose, main components, and documented commands in under 250 words. Mark anything the README leaves unclear.
- Use Llama 3.1 8B Instruct to explain the function I have selected. Describe its inputs, return value, error paths, and five edge cases worth checking; tie each point to the code.
- Use Llama 3.1 8B Instruct to turn the current Git diff into release notes under 200 words. Separate additions, fixes, and compatibility concerns, and include only changes visible in the diff.
- Use Llama 3.1 8B Instruct to draft unit tests for the selected parser using the project's existing test style. Cover empty input, malformed input, and one valid example, then run the relevant tests.
- Use Llama 3.1 8B Instruct to extract the environment variables documented in this repository into JSON. Include each name, purpose, and documented default; use null when no default is stated. Set temperature to 0.1.

## How to set up Llama 3.1 8B Instruct 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 Llama 3.1 8B Instruct**: 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": "meta-llama/llama-3.1-8b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Devin finds Llama 3.1 8B Instruct on Spiral, shows the price and runs it.

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

## Llama 3.1 8B Instruct tools and prices

- [Meta: Llama 3.1 8B Instruct](https://spiral.ai/tools/openrouter/meta-llama/llama-3.1-8b-instruct) (OpenRouter): Up to $0.000215 per run at the default inputs. $0.026 per 1M input tokens, $0.052 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 Llama 3.1 8B Instruct in Devin?

Turn project code and documentation into explanations, release notes, and focused change proposals with Llama 3.1 8B Instruct. Give each request a defined scope, the relevant files, and a concrete deliverable.

### Document briefs

Use Llama 3.1 8B Instruct to turn a long report into a short brief with findings, supporting passages, and unanswered questions.

### Multilingual support drafts

Draft replies in English, German, French, Italian, Portuguese, Hindi, Spanish, or Thai using supplied policy text and the customer's message.

### Ticket classification

Assign incoming text to a defined set of support categories. Provide labeled examples and an uncertain category for cases that need review.

### Structured extraction

Request dates, organizations, and action items from supplied text in a consistent JSON format, with null for missing information.

### Code explanations

Ask Llama 3.1 8B Instruct to explain a function, trace its inputs and outputs, and suggest edge cases to check.

### Release note drafts

Turn supplied change descriptions into release notes organized by user impact. Ask for separate sections for fixes, additions, and compatibility concerns.

### Recurring text digests

Summarize newly collected announcements or support messages into a brief that preserves source dates and separates reported facts from open questions.

## Overview

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

## Llama 3.1 8B Instruct in other agents

- [Amp](https://spiral.ai/integrations/amp/llama-3-1-8b-instruct)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/llama-3-1-8b-instruct)
- [Claude](https://spiral.ai/integrations/claude-desktop/llama-3-1-8b-instruct)
- [Claude Code](https://spiral.ai/integrations/claude-code/llama-3-1-8b-instruct)
- [Cline](https://spiral.ai/integrations/cline/llama-3-1-8b-instruct)
- [Codex](https://spiral.ai/integrations/codex/llama-3-1-8b-instruct)
- [Cursor](https://spiral.ai/integrations/cursor/llama-3-1-8b-instruct)
- [dots](https://spiral.ai/integrations/dots/llama-3-1-8b-instruct)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/llama-3-1-8b-instruct)
- [Gemini](https://spiral.ai/integrations/gemini/llama-3-1-8b-instruct)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/llama-3-1-8b-instruct)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/llama-3-1-8b-instruct)
- [goose](https://spiral.ai/integrations/goose/llama-3-1-8b-instruct)
- [Grok](https://spiral.ai/integrations/grok/llama-3-1-8b-instruct)
- [Grok Build](https://spiral.ai/integrations/grok-build/llama-3-1-8b-instruct)
- [Hermes](https://spiral.ai/integrations/hermes/llama-3-1-8b-instruct)
- [Instinct](https://spiral.ai/integrations/instinct/llama-3-1-8b-instruct)
- [Manus](https://spiral.ai/integrations/manus/llama-3-1-8b-instruct)
- [Muse](https://spiral.ai/integrations/muse/llama-3-1-8b-instruct)
- [Muse Code](https://spiral.ai/integrations/muse-code/llama-3-1-8b-instruct)
- [n8n](https://spiral.ai/integrations/n8n/llama-3-1-8b-instruct)
- [Notion](https://spiral.ai/integrations/notion/llama-3-1-8b-instruct)
- [OpenClaw](https://spiral.ai/integrations/openclaw/llama-3-1-8b-instruct)
- [opencode](https://spiral.ai/integrations/opencode/llama-3-1-8b-instruct)
- [Perplexity](https://spiral.ai/integrations/perplexity/llama-3-1-8b-instruct)
- [Raycast](https://spiral.ai/integrations/raycast/llama-3-1-8b-instruct)
- [VS Code](https://spiral.ai/integrations/vscode/llama-3-1-8b-instruct)
- [Windsurf](https://spiral.ai/integrations/windsurf/llama-3-1-8b-instruct)
- [Zapier](https://spiral.ai/integrations/zapier/llama-3-1-8b-instruct)

## More Devin guides

- [Llama 3.1 70B Instruct](https://spiral.ai/integrations/devin/llama-3-1-70b-instruct)
- [Llama 3.1 Euryale 70B v2.2](https://spiral.ai/integrations/devin/llama-3-1-euryale-70b-v2-2)
- [Llama 3 8B Lunaris](https://spiral.ai/integrations/devin/llama-3-8b-lunaris)
- [Llama 3.3 70B Instruct](https://spiral.ai/integrations/devin/llama-3-3-70b-instruct)
- [Ling 3.1 Flash](https://spiral.ai/integrations/devin/ling-3-1-flash)
- [Llama 4 Maverick](https://spiral.ai/integrations/devin/llama-4-maverick)

## Questions about Llama 3.1 8B Instruct in Devin

**Can Devin use Llama 3.1 8B Instruct?**

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Llama 3.1 8B Instruct like any built-in tool.

**How much does Llama 3.1 8B Instruct cost in Devin?**

Up to $0.000215 per run at the default inputs. $0.026 per 1M input tokens, $0.052 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 Llama 3.1 8B Instruct in Devin?**

No. Spiral runs Llama 3.1 8B Instruct on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Llama 3.1 8B Instruct in Devin?**

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

**Does Devin wait while Llama 3.1 8B Instruct runs?**

Llama 3.1 8B Instruct runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.

**What is Llama 3.1 8B Instruct useful for?**

Use it to summarize long passages, draft multilingual conversations, and help with focused coding tasks. Meta names these uses for its upgraded 8B and 70B models.

**How much text can Llama 3.1 8B Instruct handle?**

Its context window is 128K tokens, compared with 8K for Llama 3. That context figure is not a promise of a 128K-token response; give each task a specific output length.

**Which languages does Llama 3.1 8B Instruct support?**

English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Name the target language in your request and supply examples when terminology or tone matters.

**Can Llama 3.1 8B Instruct understand images or audio?**

It is a text-only model. For a task involving a recording or screenshot, provide a transcript or text description for it to work from.

**Does Llama 3.1 8B Instruct know current events?**

Its pretraining knowledge cutoff is December 2023. For newer information, supply dated source text and ask it to base the answer on that material.

