Airtop and Mistral AI Integration

Demonstration of how apps are integrated in WEXTL workflow builder[4]

Keep Airtop and Mistral AI matched by integrating their events and actions. When ai events happen in Airtop, update the Mistral AI automatically - without any line of code in visual workflow builder.

  • 3-day trial
  • Cancel anytime
  • Up to 10 minutes quick set up
  • GDPR
  • Data Encryption
  • 2FA
  • Local Data Region

Learn about Airtop and Mistral AI

Detailed info you need to know about Airtop and Mistral AI integrations in WEXTL. Explore which modules apps support and how you connect them.

  • Airtop

    • AI
    • 5 searches
    • 14 actions

    Run cloud browser sessions and extract or interact with web pages using Airtop.[5]

  • Mistral AI

    • AI
    • 4 triggers
    • 29 searches
    • 43 actions

    Mistral AI platform with chat, embeddings, FIM, OCR, audio, files, batches, fine-tuned models and agents.[6]

How to connect Airtop to Mistral AI

Set up your Airtop and Mistral AI integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.

How does the integration between Airtop and Mistral AI work in WEXTL?

WEXTL exposes actions and triggers for Airtop and Mistral AI that help you connect apps and automate repetitive tasks[1]. A trigger is an event that happens, and an action is a step that performs when the event has occurred.

Mistral AI triggersAirtop actions

Mistral AI modules

  • Append to a Conversation Continues an existing conversation by sending new Inputs, either as a plain prompt or an array of entries. Use Handoff Execution to pick client or server. The output has the Outputs, Usage and Guardrails.
  • Archive a Fine Tuned Model Archives a fine-tuned model. Afterwards the output reports the Archived flag next to the ID and Object.
  • Cancel a Batch Job Cancels a batch job before it finishes. The output reports its Status together with Total Requests and Completed Requests.
  • Create a Batch Job Queues many requests as one job against an Endpoint such as chat completions or embeddings. Supply Input Files or inline Requests, with Timeout Hours as an upper bound on the run.
  • Create a Chat Completion Sends Messages to a Model and receives its reply as Choices. Tune the reply with Temperature, Top P, Max Tokens or Random Seed, set a Response Format, or let the model call Tools.
  • Create a Conversation Starts a conversation from Inputs, as a plain prompt or entries. Base it on an Agent ID or a Model, or supply Instructions and Tools of your own. The output has the Conversation ID and Outputs.
  • Create a FIM Completion Generates the text that fits between a Prompt and an optional Suffix with a Model. Use Temperature, Max Tokens, Min Tokens or Stop to adjust the result.
  • Create a Library Sets up a library from its Name, with an optional Description, Chunk Size and Owner Type of User or Workspace. The output shows its ID, Total Size and Nb Documents.
  • Create a Transcription Transcribes audio with a Model, from a File, a File URL or a File ID. Set Language or turn on Diarize, and add Context Bias or Timestamp Granularities to refine it. The output has Text and Segments.
  • Create a Voice Saves a custom voice from a Name and Sample Audio. Describe it with Languages, Gender, Age, Tags, Color or Description, and set its Slug. The output includes Trimmed Seconds.
  • Create an Agent Sets up an agent from a Model and a Name. Add Instructions, Tools, Handoffs to other agents and Guardrails, and note what changed with Version Message. The output includes the ID, Version and Versions.
  • Create an Agent Alias Creates or updates an Alias that points at a Version of an agent. An Alias that does not exist yet is created.
  • Create an Agents Completion Sends Messages to an agent and gets its reply as Choices. Add Max Tokens, Stop or Random Seed to shape the answer, and Tools with Tool Choice to let it call functions.
  • Create Chat Classifications Classifies a conversation with a chosen Model. Send Input as Messages that each carry a Role and Content, and read the Results from the output.
  • Create Chat Moderations Runs moderation on chat Input, where each message can hold a Role, Content and Tool Calls. Pick a Model to use a specific one, and read the Results from the output.
  • Create Classifications Classifies the text of Input with a Model and returns the Results. Add Metadata as a free-form object if you need it.
  • Create Embeddings Converts Input into vectors with a Model. Use Output Dimension, Output Dtype or Encoding Format to shape the vectors, which the output returns as Data.
  • Create Moderations Checks the text of Input against a moderation Model and returns the Results.
  • Create Speech Turns Input text into audio. Use Voice ID to speak with a saved voice, Ref Audio to supply a reference, and Response Format to get pcm, wav, mp3, flac or opus. The audio arrives as Audio Data.
  • Delete a Batch Job Removes a batch job and shows its ID, Object and a Deleted flag.
  • Delete a Conversation Deletes a conversation from Mistral AI.
  • Delete a File Removes a file from Mistral AI, confirming it with a Deleted flag.
  • Delete a Library Deletes one library. The output shows its Name and ID.
  • Delete a Library Document Removes a single document from a library in Mistral AI.
  • Delete a Model Deletes a model and reports the result as a Deleted flag.
  • Delete a Voice Deletes one voice from your Mistral AI account, with the Name and ID in the output.
  • Delete an Agent Removes an agent from Mistral AI.
  • Delete an Agent Alias Deletes one Alias that was created for an agent in Mistral AI.
  • Delete Library Access Removes the access that a user, workspace or org has to a library, matched on Share With Type, Share With UUID and Level.
  • Download a File Downloads a stored file and hands it on as File, with its Filename, Content Type and Size.
  • Extract Document Text Reads a Document with a Model and extracts its text as Pages. Use Pages to limit which pages are read, Table Format to choose markdown or html, and Extract Header or Extract Footer to include them.
  • Get a Batch Job Checks how a batch job is going through its Status, Total Requests, Completed Requests and Failed Requests.
  • Get a Conversation Reads how a conversation was set up, including its Model, Agent ID, Instructions, Tools and Name.
  • Get a File Reads the details of an uploaded file, such as Filename, Bytes, Purpose, Mimetype and Expires At.
  • Get a File Signed URL Issues a signed URL for a stored file. Use Expiry to set when the link ends.
  • Get a Library Fetches one library: Name, Owner Type, Total Size, Nb Documents and Chunk Size.
  • Get a Library Document Reads a single library document, including Name, Mime Type, Size, Process Status and Summary.
  • Get a Library Document Extracted Text URL Fetches a signed link that points to the text extracted from a library document. The link is the Value in the output.
  • Get a Library Document Signed URL Returns a signed URL for downloading a library document. The output holds one URL.
  • Get a Library Document Status Checks how far a library document has got in processing, with its Process Status and Processing Status.
  • Get a Library Document Text Reads the Text of a library document. Use Page Start to begin at a later page and Page End to stop earlier.
  • Get a Model Looks up a model and reports its Capabilities, Max Context Length, Aliases, Deprecation and Default Model Temperature.
  • Get a Voice Loads a single voice and its Name, Slug, Languages, Gender, Age and Tags.
  • Get a Voice Sample Downloads the sample audio of a voice as File, with its Filename, Content Type and Size.
  • Get an Agent Loads an agent with its Model, Instructions, Tools and Guardrails. Add an Agent Version to read an earlier version instead of the latest.
  • Get an Agent Version Reads a saved version of an agent, giving its Instructions, Tools and Completion Args at that point.
  • Get Conversation History Gets the Entries of a conversation. Use Limit to cap the results, though whole pages are fetched so a run can return up to one page more.
  • Get Conversation Messages Collects the Messages recorded for a conversation, up to a Limit. Whole pages are fetched, so a run can return up to one page more than that number.
  • List Agent Aliases Lists the aliases set on an agent, with each Version, Created At and Updated At. Pass a Limit if you want fewer.
  • List Agent Versions Lists the saved versions of an agent with each Version, Model, Name and Instructions. Set Limit to collect fewer.

Airtop modules

  • Click an Element Clicks an element on the page in a browser window, finding it from the plain-language text of Element description. Returns the Model response.
  • Create a File Registers a file with Airtop under a File name before upload. Set File type to PDF, CSV or Other, and list Session IDs to attach it to sessions at once.
  • Create a Session Starts a cloud browser session. Use Configuration to set a Profile name or a Timeout minutes limit. The CDP URL in the result lets a browser tool connect to it.
  • Create a Window Opens another browser window inside a running session. Add an Initial URL to load a page as soon as it opens.
  • Delete a Session Ends a cloud browser session and shuts down the windows in it.
  • Get a File Looks up one uploaded file and reads its File name. Includes a Download URL for fetching the content.
  • Get a Session Reads a single cloud browser session by choosing it from your sessions. The CDP URL on the result is what a browser driver attaches to.
  • Get a Window Reads one browser window within a session. Includes the URL of the page that window currently has loaded.
  • Hover Over an Element Moves the mouse over an element of the page, located from the text you write for Element description. Returns the Model response.
  • List Files Shows files uploaded to Airtop, with the File ID and File name of each. Use Limit to restrict how many files are read.
  • List Sessions Reads your cloud browser sessions, showing each Session ID and Status. Set Status to Initializing, Running or Ended to filter, and add a Limit to end the read early.
  • Load a URL Sends a window of your session to the web address given as URL. Returns Success.
  • Make an API Call Calls the Airtop REST API directly with a free-form request under your saved credential.
  • Push a File to a Session Gives a running browser session access to a file you uploaded earlier, such as for an upload form on a page.
  • Scrape Content Extracts the content of the page loaded in a window. The result is the Scraped content as text.
  • Scroll a Page Scrolls a window up or down. Use Direction to pick the way and Scrolling mode to control how it moves. Returns the Model response.
  • Take a Screenshot Captures what a browser window shows. Adjust the capture with Configuration. You receive the Screenshots along with a Description of the page and the Status.
  • Type Text Enters Text into a page element that you identify through Element description. Returns the Model response.
  • Update an Automation Description Replaces the Description on an automation in your account. Returns the Automation ID.

Explore alternative integrations

There are other apps[9] supported by WEXTL that can be paired with Airtop and Mistral AI integrations. Pick any from the list below if the current combination isn't the one you need.

Automate Airtop and Mistral AI on WEXTL®

Claim your 3-day trial to build Airtop with Mistral AI integration and access every WEXTL® feature.

Cancel anytime.

Frequently asked questions

Common questions about connecting Airtop and Mistral AI.

How do I connect Airtop and Mistral AI?

Connect your Airtop and Mistral AI accounts once, pick a trigger in one app and an action in the other, then map the fields so data flows automatically between them.[3]

What can I automate between Airtop and Mistral AI?

Example: when the "Watch Agents" trigger in Mistral AI fires, WEXTL can "Click an Element" in Airtop. Airtop has 19 actions (including Click an Element, Create a File, and Create a Session). Mistral AI has 72 actions (including Append to a Conversation, Archive a Fine Tuned Model, and Cancel a Batch Job). Add filters and transforms between steps when you need them.[1]

Can Airtop trigger actions in Mistral AI, and Mistral AI in Airtop?

Yes. The integration works in both directions. Use the triggers of each app to start a workflow and the actions of the other app to update it.[2]

Do I need to write code to integrate Airtop and Mistral AI?

No. Airtop-to-Mistral AI automations are built visually on the canvas. You can optionally add custom JavaScript with Functions when you need advanced logic.[4]

Does Airtop integrate with Mistral AI in real time?

Yes. Trigger-based automations start the moment Airtop (or Mistral AI) fires a new event. Webhook-backed apps run within seconds, and polling-only apps re-check on a schedule you control.[7]

How long does it take to set up a Airtop + Mistral AI integration?

A first automation typically takes 5–10 minutes: connect the credential of each app once, drop a trigger + action onto the canvas, map the fields, and turn the workflow on.

Do I need a paid plan to connect Airtop with Mistral AI?

You can build your Airtop + Mistral AI automation on a 3-day trial with every feature unlocked. Cancel anytime.[8]

References

List of sources used to gather information about the Airtop and Mistral AI integration.

  1. Airtop and Mistral AI integration source code, module specs and credentials implementation.
  2. Our Airtop and Mistral AI integration documentation, structured input and output parameters, scopes, and authentication methods.
  3. Official vendor API documentation for Airtop and Mistral AI, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
  4. WEXTL® visual workflow builder, anonymized data from our technical support team.
  5. Airtop integration information
  6. Mistral AI integration information
  7. WEXTL® Scheduling
  8. WEXTL® Pricing and Trial
  9. WEXTL® Apps Library

How we write our apps documentation

Explore how WEXTL® crafted Airtop and Mistral AI integration page documentation. Used sources, the role of AI, and how the team validates the result.

Explore Airtop and Mistral AI, or get started