[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Llama 3.1 70B Instruct](https://spiral.ai/integrations/openclaw/llama-3-1-70b-instruct)

# How to Use Llama 3.1 70B Instruct in OpenClaw

Llama 3.1 70B Instruct handles document summaries, multilingual support, and coding tasks. Meta recommends it over Llama 3.1 8B Instruct when conversations also need tool calls.

|  |  |
| --- | --- |
| Model | Llama 3.1 70B Instruct |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.003868 per run at the default inputs. $0.936 per 1M input tokens, $0.936 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 70B Instruct in OpenClaw

- Every weekday, use Llama 3.1 70B Instruct to summarize the updates supplied for that run. Return decisions, blockers, and open questions in under 350 words. Cite the update supporting each item.
- Each morning, use Llama 3.1 70B Instruct to summarize the support conversations supplied for that run. Identify recurring questions and unanswered requests. Include one representative passage for each theme.
- Every Friday, use Llama 3.1 70B Instruct to draft release notes from the engineering updates supplied for that run. Separate user-visible changes from maintenance work and flag incomplete descriptions.
- Each week, use Llama 3.1 70B Instruct to draft Spanish and Portuguese versions of the supplied English product update. Preserve product names and technical identifiers. List phrases that need a translator's review.
- Each Monday, use Llama 3.1 70B Instruct to generate ten fictional support questions from the help excerpts supplied for that run. Include three cases where the excerpts lack an answer. Follow the approved example format supplied with the task.

## How to set up Llama 3.1 70B Instruct in OpenClaw

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

### Use the Spiral skill

1. **Send OpenClaw 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 Spiral's MCP server

1. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### 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 70B 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-3.1-70b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Llama 3.1 70B Instruct on Spiral, shows the price and runs it.

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

## Llama 3.1 70B Instruct tools and prices

- [Meta: Llama 3.1 70B Instruct](https://spiral.ai/tools/openrouter/meta-llama/llama-3.1-70b-instruct) (OpenRouter): Up to $0.003868 per run at the default inputs. $0.936 per 1M input tokens, $0.936 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| 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 Llama 3.1 70B Instruct in OpenClaw?

Produce recurring summaries of supplied updates, support conversations, and technical notes with Llama 3.1 70B Instruct. Define a fixed reporting format and require evidence for claims that need follow-up.

### Decision briefs from long documents

Turn a lengthy proposal or report into a short brief with decisions, supporting passages, and unresolved questions. Request section references so each conclusion can be checked.

### Multilingual customer support drafts

Draft replies in the eight supported languages using supplied product information. Preserve product names and separate documented answers from questions that need a support specialist.

### Code review and debugging assistance

Review relevant code and error output to propose a focused fix. Ask for the suspected cause, the proposed change, and a test that would confirm the fix.

### Meeting summaries with traceable actions

Convert a text transcript into decisions, action items, and open questions. Require transcript evidence for each assigned owner or deadline.

### Answers grounded in reference material

Answer questions using supplied help articles or policy excerpts. Request a supporting passage for every answer and an explicit statement when the material does not cover the question.

### Support conversation test data

Generate fictional support conversations for evaluation, including follow-up questions and cases with missing information. Review the examples before using them to assess another system.

### Release notes from technical changes

Turn commit descriptions and engineering notes into a readable release summary. Keep user-visible changes separate from internal maintenance and flag claims that need confirmation.

## Overview

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

## Llama 3.1 70B Instruct in other agents

- [Amp](https://spiral.ai/integrations/amp/llama-3-1-70b-instruct)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/llama-3-1-70b-instruct)
- [Claude](https://spiral.ai/integrations/claude-desktop/llama-3-1-70b-instruct)
- [Claude Code](https://spiral.ai/integrations/claude-code/llama-3-1-70b-instruct)
- [Cline](https://spiral.ai/integrations/cline/llama-3-1-70b-instruct)
- [Codex](https://spiral.ai/integrations/codex/llama-3-1-70b-instruct)
- [Cursor](https://spiral.ai/integrations/cursor/llama-3-1-70b-instruct)
- [Devin](https://spiral.ai/integrations/devin/llama-3-1-70b-instruct)
- [dots](https://spiral.ai/integrations/dots/llama-3-1-70b-instruct)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/llama-3-1-70b-instruct)
- [Gemini](https://spiral.ai/integrations/gemini/llama-3-1-70b-instruct)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/llama-3-1-70b-instruct)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/llama-3-1-70b-instruct)
- [goose](https://spiral.ai/integrations/goose/llama-3-1-70b-instruct)
- [Grok](https://spiral.ai/integrations/grok/llama-3-1-70b-instruct)
- [Grok Build](https://spiral.ai/integrations/grok-build/llama-3-1-70b-instruct)
- [Hermes](https://spiral.ai/integrations/hermes/llama-3-1-70b-instruct)
- [Instinct](https://spiral.ai/integrations/instinct/llama-3-1-70b-instruct)
- [Manus](https://spiral.ai/integrations/manus/llama-3-1-70b-instruct)
- [Muse](https://spiral.ai/integrations/muse/llama-3-1-70b-instruct)
- [Muse Code](https://spiral.ai/integrations/muse-code/llama-3-1-70b-instruct)
- [n8n](https://spiral.ai/integrations/n8n/llama-3-1-70b-instruct)
- [Notion](https://spiral.ai/integrations/notion/llama-3-1-70b-instruct)
- [opencode](https://spiral.ai/integrations/opencode/llama-3-1-70b-instruct)
- [Perplexity](https://spiral.ai/integrations/perplexity/llama-3-1-70b-instruct)
- [Raycast](https://spiral.ai/integrations/raycast/llama-3-1-70b-instruct)
- [VS Code](https://spiral.ai/integrations/vscode/llama-3-1-70b-instruct)
- [Windsurf](https://spiral.ai/integrations/windsurf/llama-3-1-70b-instruct)
- [Zapier](https://spiral.ai/integrations/zapier/llama-3-1-70b-instruct)

## More OpenClaw guides

- [Llama 3 8B Lunaris](https://spiral.ai/integrations/openclaw/llama-3-8b-lunaris)
- [Llama 3.1 8B Instruct](https://spiral.ai/integrations/openclaw/llama-3-1-8b-instruct)
- [Ling 3.1 Flash](https://spiral.ai/integrations/openclaw/ling-3-1-flash)
- [Llama 3.1 Euryale 70B v2.2](https://spiral.ai/integrations/openclaw/llama-3-1-euryale-70b-v2-2)
- [Ling 3.0 Tiny](https://spiral.ai/integrations/openclaw/ling-3-0-tiny)
- [Llama 3.3 70B Instruct](https://spiral.ai/integrations/openclaw/llama-3-3-70b-instruct)

## Questions about Llama 3.1 70B Instruct in OpenClaw

**Can OpenClaw use Llama 3.1 70B Instruct?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Llama 3.1 70B Instruct like any built-in tool.

**How much does Llama 3.1 70B Instruct cost in OpenClaw?**

Up to $0.003868 per run at the default inputs. $0.936 per 1M input tokens, $0.936 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

**Do I need an OpenRouter account to use Llama 3.1 70B Instruct in OpenClaw?**

No. Spiral runs Llama 3.1 70B 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 70B Instruct in OpenClaw?**

About two minutes: add the server, then sign in, then reload and check.

**Does OpenClaw wait while Llama 3.1 70B Instruct runs?**

Llama 3.1 70B Instruct runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Llama 3.1 70B Instruct useful for?**

Use it to summarize lengthy text, draft multilingual support replies, and assist with code. Give it the relevant source material and a concrete deliverable, such as a decision list or proposed patch.

**How much text can Llama 3.1 70B Instruct consider?**

Meta specifies a 128K-token context length. That figure describes context capacity, so do not treat it as a promise of a 128K-token response; set a separate response-length target.

**Which languages does Llama 3.1 70B Instruct support?**

Meta lists English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Specify the output language and any terminology that must stay unchanged.

**Can Llama 3.1 70B Instruct interpret images or generate video?**

It is a text model. For a task based on a screenshot or recording, provide a text description or transcript.

**What should I check in its answers?**

Check factual claims against the supplied sources, especially when an answer sounds certain. Ask it to quote supporting passages and mark missing information, then verify those passages yourself.

