[Integrations](https://spiral.ai/integrations) › [Notion](https://spiral.ai/integrations/notion) › [Mixtral 8x22B Instruct](https://spiral.ai/integrations/notion/mixtral-8x22b-instruct)

# How to Use Mixtral 8x22B Instruct in Notion

Mixtral 8x22B Instruct suits coding, math, and document questions across five supported languages. Unlike Mixtral 8x22B Base, it is fine-tuned to follow instructions.

|  |  |
| --- | --- |
| Model | Mixtral 8x22B Instruct |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Mixtral 8x22B Instruct in Notion

- Every morning, use Mixtral 8x22B Instruct to summarize the support messages supplied to this run. Group them by issue, quote one example per issue, and keep the digest under 500 words.
- For each hourly batch, use Mixtral 8x22B Instruct to classify incoming messages as billing, access, product, or other. Use low randomness and return a category, message identifier, and supporting excerpt.
- Each weekday, use Mixtral 8x22B Instruct to draft replies to the French, German, Italian, and Spanish messages supplied to this run. Answer in the customer's language and use only the supplied product policy.
- Each evening, use Mixtral 8x22B Instruct to compare today's supplied release notes with yesterday's. List additions, removals, and changed behavior, quoting the text behind each finding.
- Every Friday, use Mixtral 8x22B Instruct to review the weekly counts supplied to this run. Calculate percentage changes, show the arithmetic, and mark a percentage change as undefined when the previous count is zero.

## How to set up Mixtral 8x22B Instruct in Notion

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

### Use the Spiral skill

1. **Send Notion 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. **Allow custom MCP servers**: A workspace owner opens Settings › Connections, then the Manage tab, and turns on Enable custom MCP servers. Where members may install only approved connections, also add Spiral under Approved connections › Add approved connection › Custom MCP server with the URL below.

2. **Add Spiral to a custom agent**: Open the custom agent (or create one), then Settings › Tools & Access › Add connection › Custom MCP server. Paste this URL, name it Spiral, keep OAuth and click Connect.

```text
https://api.spiral.ai/mcp
```

3. **Sign in to Spiral and approve**: Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Notion never sees it, and you can remove it under Settings › Connected apps in the console.

4. **Run Mixtral 8x22B Instruct in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Mixtral 8x22B Instruct, prices it and runs it each time the step fires.

### 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 Mixtral 8x22B 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": "mistralai/mixtral-8x22b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Notion finds Mixtral 8x22B Instruct on Spiral, shows the price and runs it.

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

## Mixtral 8x22B Instruct tools and prices

- [Mistral: Mixtral 8x22B Instruct](https://spiral.ai/tools/openrouter/mistralai/mixtral-8x22b-instruct) (OpenRouter): Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 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 52428 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Mixtral 8x22B Instruct in Notion?

Turn recurring batches of text into summaries, labels, and multilingual reply drafts with Mixtral 8x22B Instruct. Keep each run focused on supplied material and use a consistent answer format so results are easy to compare.

### Explain unfamiliar code

Ask for a walkthrough of a function, its assumptions, and likely failure cases. Supply the surrounding code so the explanation has enough context.

### Draft regression tests

Provide a bug report and the affected function, then request tests for the reported failure and nearby edge cases.

### Answer questions about long documents

Supply policy or product documentation and ask for answers with supporting passages. Keep the text and requested answer within the 64K-token context budget.

### Draft multilingual support replies

Use supplied product policies to draft replies in English, French, Italian, German, or Spanish. Specify the response language and preserve product names.

### Extract records from text

Turn meeting notes or support messages into consistent records. Provide an example record and instructions for missing values.

### Work through calculations

Ask for formulas, substitutions, units, and intermediate results when checking percentage changes or operational calculations.

### Classify incoming requests

Define categories such as billing, access, and product questions, then supply labeled examples. Request a category and supporting excerpt for each message.

## Overview

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

## Mixtral 8x22B Instruct in other agents

- [Amp](https://spiral.ai/integrations/amp/mixtral-8x22b-instruct)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mixtral-8x22b-instruct)
- [Claude](https://spiral.ai/integrations/claude-desktop/mixtral-8x22b-instruct)
- [Claude Code](https://spiral.ai/integrations/claude-code/mixtral-8x22b-instruct)
- [Cline](https://spiral.ai/integrations/cline/mixtral-8x22b-instruct)
- [Codex](https://spiral.ai/integrations/codex/mixtral-8x22b-instruct)
- [Cursor](https://spiral.ai/integrations/cursor/mixtral-8x22b-instruct)
- [Devin](https://spiral.ai/integrations/devin/mixtral-8x22b-instruct)
- [dots](https://spiral.ai/integrations/dots/mixtral-8x22b-instruct)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mixtral-8x22b-instruct)
- [Gemini](https://spiral.ai/integrations/gemini/mixtral-8x22b-instruct)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mixtral-8x22b-instruct)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mixtral-8x22b-instruct)
- [goose](https://spiral.ai/integrations/goose/mixtral-8x22b-instruct)
- [Grok](https://spiral.ai/integrations/grok/mixtral-8x22b-instruct)
- [Grok Build](https://spiral.ai/integrations/grok-build/mixtral-8x22b-instruct)
- [Hermes](https://spiral.ai/integrations/hermes/mixtral-8x22b-instruct)
- [Instinct](https://spiral.ai/integrations/instinct/mixtral-8x22b-instruct)
- [Manus](https://spiral.ai/integrations/manus/mixtral-8x22b-instruct)
- [Muse](https://spiral.ai/integrations/muse/mixtral-8x22b-instruct)
- [Muse Code](https://spiral.ai/integrations/muse-code/mixtral-8x22b-instruct)
- [n8n](https://spiral.ai/integrations/n8n/mixtral-8x22b-instruct)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mixtral-8x22b-instruct)
- [opencode](https://spiral.ai/integrations/opencode/mixtral-8x22b-instruct)
- [Perplexity](https://spiral.ai/integrations/perplexity/mixtral-8x22b-instruct)
- [Raycast](https://spiral.ai/integrations/raycast/mixtral-8x22b-instruct)
- [VS Code](https://spiral.ai/integrations/vscode/mixtral-8x22b-instruct)
- [Windsurf](https://spiral.ai/integrations/windsurf/mixtral-8x22b-instruct)
- [Zapier](https://spiral.ai/integrations/zapier/mixtral-8x22b-instruct)

## More Notion guides

- [Mistral Small 4](https://spiral.ai/integrations/notion/mistral-small-4)
- [Moondream 3 Preview](https://spiral.ai/integrations/notion/moondream-3-preview)
- [Mistral Small 3.2 24B](https://spiral.ai/integrations/notion/mistral-small-3-2-24b)
- [Moondream 3.1](https://spiral.ai/integrations/notion/moondream-3-1)
- [Mistral Small 3.1 24B Instruct](https://spiral.ai/integrations/notion/mistral-small-3-1-24b-instruct)
- [Morph V3 Fast](https://spiral.ai/integrations/notion/morph-v3-fast)

## Questions about Mixtral 8x22B Instruct in Notion

**Can Notion use Mixtral 8x22B Instruct?**

Yes. Add Spiral to Notion as an MCP server, and Notion can find and run Mixtral 8x22B Instruct like any built-in tool.

**How much does Mixtral 8x22B Instruct cost in Notion?**

Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Notion plan is separate.

**Do I need an OpenRouter account to use Mixtral 8x22B Instruct in Notion?**

No. Spiral runs Mixtral 8x22B 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 Mixtral 8x22B Instruct in Notion?**

About two minutes: allow custom MCP servers, then add Spiral to a custom agent, then sign in to Spiral and approve.

**Does Notion wait while Mixtral 8x22B Instruct runs?**

Mixtral 8x22B Instruct runs in the background. Notion starts the run, checks on it and gives you the text, json when it's ready.

**What is Mixtral 8x22B good at?**

Coding, mathematics, multilingual text, and questions about long documents are documented strengths. Try it for code explanations, calculation walkthroughs, or extracting answers from supplied text.

**Which languages does Mixtral 8x22B support?**

Mistral names English, French, Italian, German, and Spanish. Specify the language you want in the answer, especially when your source text mixes languages.

**How much text can Mixtral 8x22B handle?**

Its context window is 64K tokens. Budget for the source text, conversation, and generated answer together; that window is not a promise of a 64K-token answer.

**How does Mixtral 8x22B Instruct differ from Mixtral 8x22B Base?**

Mixtral 8x22B Instruct is fine-tuned to follow instructions. Choose it for requests that specify a task, audience, or answer format.

**How should I prompt Mixtral 8x22B?**

State the task, supply the relevant text, and define the answer format. Include a worked example when you need consistent labels, extracted records, or a particular writing style.

