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

# How to Use Mixtral 8x22B Instruct in ChatGPT

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 ChatGPT

- Use Mixtral 8x22B Instruct to explain compound interest on a starting balance of 1,000 at 4% annually for three years. Show the formula, each year's balance, and the final result rounded to two decimals.
- Use Mixtral 8x22B Instruct to translate this support reply into French, German, Italian, and Spanish: 'Your export is ready. Open Reports, choose Exports, and select Download.' Keep the interface labels in English.
- Use Mixtral 8x22B Instruct to summarize our conversation in five bullets. Separate decisions, unresolved questions, and next actions, and do not add details we have not discussed.
- Use Mixtral 8x22B Instruct to explain why a Python function with a default empty list can retain values between calls. Give a short failing example, a corrected version, and the expected outputs.
- Use Mixtral 8x22B Instruct to classify these messages as access, billing, or product: 'I cannot sign in'; 'My invoice has the wrong address'; 'Can I export a report?' Return one category per message and use low randomness.

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

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

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

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 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: ChatGPT finds Mixtral 8x22B Instruct on Spiral, shows the price and runs it.

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

## 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 ChatGPT?

Work through calculations, translate text, and ask focused questions about supplied documents with Mixtral 8x22B Instruct. State the answer language and format, and include an example when consistency matters.

### 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 ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Mixtral 8x22B Instruct in other agents

- [Amp](https://spiral.ai/integrations/amp/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)
- [Notion](https://spiral.ai/integrations/notion/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 ChatGPT guides

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

## Questions about Mixtral 8x22B Instruct in ChatGPT

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

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

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

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 ChatGPT plan is separate.

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

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 ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

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

Mixtral 8x22B Instruct runs in the background. ChatGPT 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.

