[Integrations](https://spiral.ai/integrations) › [dots](https://spiral.ai/integrations/dots) › [Mistral Large 3](https://spiral.ai/integrations/dots/mistral-large-3)

# How to Use Mistral Large 3 in dots

Use Mistral Large 3 for longer document analysis, coding assistance, and multilingual conversations. Its 256k context window doubles the 128k documented for Mistral Large 2407, though dedicated reasoning models can outperform it on strict reasoning tasks.

|  |  |
| --- | --- |
| Model | Mistral Large 3 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.008011 per run at the default inputs. $0.65 per 1M input tokens, $1.95 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 Large 3 in dots

- Every Friday, use Mistral Large 3 to compare this week's supplied release announcements with last week's. Report added features, changed behavior, and unresolved migration questions with source links.
- Every Monday, use Mistral Large 3 to review the supplied product FAQ updates. Identify conflicting answers and missing evidence, then produce a review queue without inventing resolutions.
- Every Monday at 9am: ask Mistral Large 3 through Spiral to review the diff on this branch and list the three riskiest changes.
- Get a second opinion from Mistral Large 3 on this function, then tell me what the call cost.
- Summarize these release notes with Mistral Large 3 in five bullet points.

## How to set up Mistral Large 3 in dots

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

### Use the Spiral skill

1. **Send dots 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 your dot. Copy it.

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

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

3. **Give your dot the key**: When your dot asks for the key, add it where your dot 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 Large 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-large-2512",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## Mistral Large 3 tools and prices

- [Mistral: Mistral Large 3 2512](https://spiral.ai/tools/openrouter/mistralai/mistral-large-2512) (OpenRouter): Up to $0.008011 per run at the default inputs. $0.65 per 1M input tokens, $1.95 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 209715 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Mistral Large 3 in dots?

Convert recurring batches of operational text into briefs, labels, and review queues with Mistral Large. Define the reporting period and evidence rules so each run produces a comparable result.

### Compare policy documents

Give Mistral Large two policy texts and ask for changed obligations, exceptions, and deadlines. Require a section reference for every difference.

### Extract records from business text

Use Mistral Large to turn order emails or service requests into records with names, dates, requested actions, and supporting excerpts. Mark missing values explicitly.

### Triage multilingual support messages

Ask Mistral Large to label French, Spanish, and English inquiries by intent, summarize the issue in English, and draft a response in the customer's language.

### Review code changes

Have Mistral Large inspect a proposed change alongside its surrounding code. Request concrete failure cases and a small patch with tests that exercise the affected behavior.

### Answer questions from supplied documentation

Give Mistral Large selected documentation passages and ask a specific product question. Require citations to those passages and an explicit answer when the evidence is insufficient.

### Prepare a daily operations brief

Use Mistral Large to summarize supplied incident updates, group repeated issues, and separate confirmed resolutions from open questions. Include the source link for each incident.

### Check translated product copy

Ask Mistral Large to compare English product copy with French or Spanish translations. Flag changed quantities, omitted conditions, and inconsistent terminology before human review.

## Overview

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

## Mistral Large 3 in other agents

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

## More dots guides

- [Mistral Large 2407](https://spiral.ai/integrations/dots/mistral-large-2407)
- [Mistral Large 4](https://spiral.ai/integrations/dots/mistral-large-4)
- [Mistral Large](https://spiral.ai/integrations/dots/mistral-large)
- [Mistral Medium 3](https://spiral.ai/integrations/dots/mistral-medium-3)
- [Ministral 3 8B](https://spiral.ai/integrations/dots/ministral-3-8b)
- [Mistral Medium 3.1](https://spiral.ai/integrations/dots/mistral-medium-3-1)

## Questions about Mistral Large 3 in dots

**Can dots use Mistral Large 3?**

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

**How much does Mistral Large 3 cost in dots?**

Up to $0.008011 per run at the default inputs. $0.65 per 1M input tokens, $1.95 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your dots plan is separate.

**Do I need an OpenRouter account to use Mistral Large 3 in dots?**

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

**How long does it take to set up Mistral Large 3 in dots?**

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

**Does dots wait while Mistral Large 3 runs?**

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

**Are Mistral Large and Mistral Large 2407 different models?**

Both listings describe Mistral Large 2, version 2407. Mistral Large 3 is a later model with a 256k context window, compared with the 128k documented for 2407.

**What should I use Mistral Large for?**

Useful starting points include multilingual document analysis, coding assistance, and extracting structured information from text. Give it a concrete task, the relevant source material, and an example of the answer you want.

**Can Mistral Large work with languages other than English?**

Yes. Both 2407 and Large 3 support dozens of languages, including French and Spanish. State the desired output language and identify any names or technical terms that must stay unchanged.

**How should I prompt Mistral Large?**

Separate the task, source material, constraints, and expected answer format into clear sections. Include a completed example when formatting matters, and specify what it should return when the source lacks an answer.

**How should I use Mistral Large for long documents?**

Ask a focused question and require section references or short supporting excerpts. For large extraction jobs, request only the records you need and check a sample against the original text.

