> For the complete documentation index, see [llms.txt](https://docs.diaflow.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.diaflow.io/workflow-builder/nodes/private-ai-llm-models/mistralai.md).

# MistralAI

### 1. The "Ready-to-Use" AI (Overview)

Zero setup, zero API keys. Just drag, drop, and start prompting using Diaflow's built-in AI credits.

Mistral’s standout strength is flexible multimodal reasoning. With **Pixtral Large**, it can understand both text and images in one step, which makes it a strong fit for visual review, document understanding, and detailed business analysis.

### 2. How to Add the Node

On your canvas, open the node picker, search for **MistralAI**, and click it to add the node to your workflow.

<figure><img src="/files/eCeShAylJJC5CZ3dKTKb" alt=""><figcaption></figcaption></figure>

### 3. What can you automate? (The "Wow" Use Cases)

#### 1. **The Visual Approval Assistant**

Pass product images, creative drafts, or visual mockups into **Pixtral Large** and get fast review notes, issue spotting, and business-ready feedback.

#### 2. **The Contract and Policy Briefing Desk**

Send long files such as contracts, PDFs, spreadsheets, or reports and let Mistral turn them into concise summaries, key risks, and action points.

#### 3. **The Executive Answer Engine**

Feed in meeting notes, research, or internal documents and let Mistral generate polished answers, summaries, and decision support for leaders and client teams.

### 4. Step-by-Step: Configuration & Smart Data Injection

#### 1. **Choose your Brain (Model):**

Select your preferred model from the dropdown.

Use **Mistral Small** or **Mistral 7B** for faster, lighter tasks. Use **Mistral Large** or **Pixtral Large** for deeper reasoning and more demanding work.

#### 2. **Write the Prompt & Inject Data:**

The easiest way to add live workflow data is to type `@` on your keyboard. Diaflow opens a visual dropdown so you can pick dynamic values from earlier steps.

Typing `{{` also works perfectly if you prefer the classic bracket syntax.

Put your task, rules, tone, and desired format directly into the main Prompt box.

#### 3. **Attach Media (Images and documents):**

If you want Mistral to look at images, pass image links from earlier steps into the image field.

If you want Mistral to work from files, insert the document link into the Prompt with `@`.

For image understanding, **Pixtral Large** is the best choice.

You can pass more than one image when your workflow needs side-by-side review.

If your workflow starts from a chat or form attachment, Diaflow can also pick up that attachment automatically.

<figure><img src="/files/pKlj90w2eqP5UyAhdpcQ" alt=""><figcaption></figcaption></figure>

### 5. The Output: Seeing Your Results

This node returns generated text that you can send straight into the next step.

Use `{{node_name.data}}` in your next step, like Gmail or Google Sheets, to pass the generated text or media forward.

You may also see the model used and the final prompt that ran. This helps you review what the node actually used.

You will also see `input_token` and `output_token`. Since Diaflow handles the billing, these tokens simply act as a meter so you can track how many credits your workflow is consuming.

<figure><img src="/files/kGPDsWOj8XAP4Ck4fyvl" alt=""><figcaption></figcaption></figure>

### 6. Golden Rules & Guardrails (CRITICAL PRO-TIPS)

#### **File/Image Limits:**

This node supports image input and document-aware prompting.

Supported image formats include `jpg`, `jpeg`, `png`, and `webp`.

Supported document types include `docx`, `pdf`, `txt`, `csv`, `xlsx`, and `xls`.

Multiple images are supported. If you need the strongest image understanding, choose **Pixtral Large**.

#### **The System Prompt Trap:**

Separate system instructions are not applied in this node.

For guaranteed results with advanced models, put your Persona/System instructions directly into the main Prompt box.

#### **Auto-Streaming:**

The AI will think quietly and return the full complete answer at once.

#### **Output length limits:**

Diaflow starts with a generous answer length.

If you increase it too far, some models may reject the run instead of trimming it automatically.

If that happens, lower the requested answer length and try again.

#### **Text-only output:**

Even when you send images or files, this node returns text.

Use the text result in your next step for email, spreadsheets, approvals, or follow-up actions.

#### **Built-in memory and caching:**

Turn on **Memory** when you want the node to remember earlier turns in the same flow.

Turn on **Caching** when you expect the same request to repeat and want faster repeat runs.

#### **If a run fails:**

If you see `Prompt invalid`, review the dynamic values you inserted and make sure the earlier step exists.

If you see `Invalid Model`, reselect the model and test again.

If the run still fails, reduce the request size or answer length, then retry once.

### 7. Need Help?

* [**Understanding Diaflow Variables (`@` vs `{{ }}`)**](/agent-builder/agent-builder/cross-features-control/mention-tool.md)
* [**Contact Diaflow Support**](mailto:support@diaflow.io)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.diaflow.io/workflow-builder/nodes/private-ai-llm-models/mistralai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.