[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Mistral Medium 3](https://spiral.ai/integrations/instinct/mistral-medium-3)

# How to Use Mistral Medium 3 in Instinct

Mistral Medium 3 suits code review, STEM explanations, and questions over supplied text. It is the May 2025 model with a 128k context window, so leave room for the answer when providing long material.

|  |  |
| --- | --- |
| Model | Mistral Medium 3 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.010668 per run at the default inputs. $0.52 per 1M input tokens, $2.60 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Mistral Medium 3 in Instinct

- Each morning, use Mistral Medium 3 to summarize the support messages supplied to this run. Group recurring issues, include message IDs, and separate explicit requests from inferred concerns.
- Each weekday, use Mistral Medium 3 to extract action items from the meeting text supplied to this run. Return JSON with an action, owner, and due date; use null for missing details and keep randomness low.
- Each week, use Mistral Medium 3 to compare the old and new policy text supplied to this run. List changed obligations with supporting excerpts from both versions.
- Each morning, use Mistral Medium 3 to review the code snippets and failure messages supplied to this run. Rank plausible causes, cite the supporting evidence, and propose a test for each cause.
- Each Friday, use Mistral Medium 3 to draft Spanish replies for the customer messages supplied to this run. Follow the supplied policy, preserve product names, and flag questions the policy cannot answer.

## How to set up Mistral Medium 3 in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Mistral Medium 3**: 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/mistral-medium-3",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Mistral Medium 3 on Spiral, shows the price and runs it.

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

## Mistral Medium 3 tools and prices

- [Mistral: Mistral Medium 3](https://spiral.ai/tools/openrouter/mistralai/mistral-medium-3) (OpenRouter): Up to $0.011736 per run at the default inputs. $0.572 per 1M input tokens, $2.86 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 104857 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Mistral Medium 3 in Instinct?

Turn recurring text inputs into reviewable summaries and extracted records with Mistral Medium 3. Give each run a fixed output structure and require evidence for findings drawn from source material.

### Review a proposed code change

Ask Mistral Medium 3 to inspect a diff for logic errors and missing edge cases. Request a concrete failure example for each finding.

### Draft tests from requirements

Give Mistral Medium 3 a function contract and ask for normal, boundary, and invalid-input tests with expected results.

### Explain a technical calculation

Provide the formula, quantities, and units. Ask Mistral Medium 3 to explain the calculation and identify assumptions that need checking.

### Answer questions from supplied documentation

Give Mistral Medium 3 relevant text and ask it to support each answer with a short source excerpt. Require it to identify unanswered questions.

### Extract records from business text

Ask Mistral Medium 3 to turn support messages or meeting notes into JSON records. Define missing values and include a completed example.

### Prepare multilingual support drafts

Ask Mistral Medium 3 to draft French, German, or Spanish replies from supplied policy text. Provide approved terminology and review the translation before sending.

### Explain results returned by a tool

Pass a completed lookup result to Mistral Medium 3 and ask for a plain-English explanation that preserves the returned values and identifies missing information.

## Overview

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

## Mistral Medium 3 in other agents

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

## More Instinct guides

- [Mistral Large 4](https://spiral.ai/integrations/instinct/mistral-large-4)
- [Mistral Medium 3.1](https://spiral.ai/integrations/instinct/mistral-medium-3-1)
- [Mistral Large 3](https://spiral.ai/integrations/instinct/mistral-large-3)
- [Mistral Medium 3.5](https://spiral.ai/integrations/instinct/mistral-medium-3-5)
- [Mistral Large 2407](https://spiral.ai/integrations/instinct/mistral-large-2407)
- [Mistral NeMo](https://spiral.ai/integrations/instinct/mistral-nemo)

## Questions about Mistral Medium 3 in Instinct

**Can Instinct use Mistral Medium 3?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Mistral Medium 3 like any built-in tool.

**How much does Mistral Medium 3 cost in Instinct?**

Up to $0.010668 per run at the default inputs. $0.52 per 1M input tokens, $2.60 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an OpenRouter account to use Mistral Medium 3 in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Mistral Medium 3 on its own OpenRouter account.

**How long does it take to set up Mistral Medium 3 in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Mistral Medium 3 runs?**

Mistral Medium 3 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is Mistral Medium 3 good at?**

Mistral identifies coding and STEM as particular strengths. Try it for reviewing a function, explaining a technical calculation, or drafting tests from a specification.

**How much text can Mistral Medium 3 handle?**

Its context window is 128k tokens. Input and output share that budget, so reserve space for the answer instead of filling the window with source material.

**Can I trust an answer because it is valid JSON?**

Check the contents against the source material. Mistral's guidance recommends evaluating generated answers for faithfulness to documents, even when the output has the requested structure.

**How should I prompt Mistral Medium 3 for extraction?**

State what to extract, define how to represent missing information, and include a completed example. For JSON output, explicitly request JSON and describe the required structure.

**Which setting matters most for focused answers?**

Start with a low temperature, such as 0.2, for extraction or code review. Higher values, such as 0.7, make output more random and can suit drafting alternatives.

