> ## Documentation Index > Fetch the complete documentation index at: https://docs.abbyy.com/llms.txt > Use this file to discover all available pages before exploring further. # LLMs in ABBYY Vantage > How ABBYY Vantage uses large language models (LLMs) for AI-powered document processing, including ABBYY Phoenix Plus, LLM connections, prompt-based extraction, supported providers, data handling, and cost. ABBYY Vantage uses **large language models (LLMs)** to extract, classify, and understand document data from natural-language instructions. There are two ways to reach a model: * **ABBYY Phoenix Plus**: an LLM endpoint that ABBYY supplies and operates for you. Nothing to obtain, configure, or rotate. * **Your own LLM connection**: credentials for your own account with an external provider such as **Anthropic**, **Google AI Studio (Gemini)**, **Microsoft Foundry**, **Mistral AI**, or **OpenAI**. **Custom (OpenAI-Compatible)** covers an OpenAI-compatible endpoint you host or control yourself. Both are tenant connections of the same kind. Both appear under **ADMIN → Configuration → Connections**, and both can be selected by a **prompt-based activity** in a Document Skill. A tenant can use both at the same time. ## Choosing a source | | ABBYY Phoenix Plus | Your own LLM connection | | :- | :- | :- | | What you configure | Nothing. ABBYY provisions the connection | Provider credentials, endpoint, and model name | | Who chooses the model | ABBYY selects and maintains it | You do | | Availability | ABBYY Vantage Cloud, with a contracted entitlement | Cloud and self-hosted | | Billing | Contracted entitlement with ABBYY | Billed by your provider | Prompt-based extraction is currently available in Document Skills through ABBYY Advanced Designer only. LLM connections are managed at the tenant level, under **ADMIN → Configuration → Connections**. ## ABBYY Phoenix Plus **ABBYY Phoenix Plus** gives a tenant LLM capability without a provider account of its own. There is no API key to obtain, no endpoint URL or model name to enter, and no credential to rotate. ABBYY selects, hosts, and maintains the model, and can update it without any change on your side. When the entitlement is enabled, a connection named **ABBYY Phoenix Model** appears under **ADMIN → Configuration → Connections**, shown with a padlock icon and the description **Managed by ABBYY**. Because ABBYY owns the credential behind it, the connection is read-only: you can **test** it, but you cannot edit or delete it, and its credentials are never displayed, not even masked. ### Two ways to use it The connection is one thing. What you can do with it depends on where you use it. | | Prompt-based activity, in Advanced Designer | Custom activity script, in a Process skill | | :- | :- | :- | | Effort | Select the connection from a dropdown. No code | You write the activity script | | The prompt | Built for you by the activity | Yours to construct | | The response | Mapped to your output fields automatically | Yours to parse and write back | | Control | The activity's own options | What you attach, page images, response validation, retries, and where field positions come from | If your goal is LLM extraction with the least work, use the prompt-based activity and select **ABBYY Phoenix Model** from the LLM Connection dropdown. For the steps, see [Extract data with prompt-based activities](/vantage/documentation/skills/prompt-extraction). A shared connection is not a shared capability. The techniques in [Call ABBYY Phoenix Plus from a Custom activity](/vantage/documentation/skill-designer/process/custom-activity/phoenix-llm-session) are script work. Sending OCR JSON or page images, validating the response, and taking field positions from the OCR layer have no equivalent in the prompt-based activity. That activity builds the prompt and maps the response for you. ### Calling it from a script Phoenix Plus can also be invoked from a [Custom activity](/vantage/documentation/skill-designer/process/custom-activity/custom-activity) inside a Process skill, so the model runs as a step in your workflow with the payload and the response under your control. Contact your ABBYY account team. After it is enabled, the **ABBYY Phoenix Model** connection appears in your tenant's connections list. In the Process skill designer, add a **Custom** activity at the point in the workflow where you want the model to run. For the steps, see [Custom activity](/vantage/documentation/skill-designer/process/custom-activity/custom-activity). The script opens a chat session against the managed connection and attaches what the model should see, typically the OCR JSON export and your instructions. Page images can be attached too, within a message size limit. For the session API, the limits, and worked examples, see [Call ABBYY Phoenix Plus from a Custom activity](/vantage/documentation/skill-designer/process/custom-activity/phoenix-llm-session). The script asks for structured JSON and receives a parsed object, which later steps in the process can consume like any other transaction data. No HTTP plumbing, authentication, or provider-specific integration code is required. That work is what the entitlement removes. You still write the activity script itself, and two constraints shape how you write it: * Each message has a size limit that counts image content, so large page images must be managed rather than assumed. * The model reads and classifies. It does not measure. Take field positions and bounding boxes from the Vantage OCR layer, never from the model. Both are covered in [Call ABBYY Phoenix Plus from a Custom activity](/vantage/documentation/skill-designer/process/custom-activity/phoenix-llm-session). ## Using your own LLM connection A tenant administrator adds credentials for a provider account you hold, and skill designers select that connection in a prompt-based activity. A tenant administrator adds a connection to a provider under **ADMIN → Configuration → Connections**. For the steps, see [Configure LLM connections](/vantage/documentation/skills/connections). In Advanced Designer, add a **Prompt-based** activity to a Document Skill and select the LLM connection it should use. For the steps, see [Extract data with prompt-based activities](/vantage/documentation/skills/prompt-extraction). When you publish the skill, the selected connection becomes the skill's default in the Vantage Web Portal, under **Skill Catalog → \[skill] → Parameters**. A tenant administrator can override it per environment without republishing. For more information, see [Document skill parameters](/vantage/documentation/skill-designer/skill-parameters/document-skill-params). ## When to use LLMs Prompt-based LLM extraction needs no training data and adapts quickly to new fields and layouts. Each extraction calls a model, so it costs more and runs slower than a trained model, and results can vary slightly between runs. | Use prompt-based LLM extraction when | Prefer traditional extraction when | | :- | :- | | Documents have variable or semi-structured layouts | Documents are highly structured or template-based | | You have little or no training data | You process high volumes and need the lowest cost per document | | You need to prototype or add fields quickly | You need fast, deterministic, repeatable results | | Documents span multiple languages | Processing must run offline | ## Data handling and security When a skill uses **your own LLM connection**, the document content is sent to the external provider you connect to and is processed on that provider's infrastructure, subject to the provider's terms and data policies. Choose a provider that meets your data-residency and compliance needs. **Microsoft Foundry** supports Azure-based data residency and compliance controls. With **Custom (OpenAI-Compatible)**, content goes to the endpoint you name in the connection, so data residency follows wherever you run that endpoint. When a skill or script uses **ABBYY Phoenix Plus**, document content is sent to the model endpoint ABBYY operates for this service rather than to a provider account of your own. ### Where Phoenix Plus processes your data Phoenix Plus runs in three regions, and your tenant uses the region it is deployed in. You do not choose the region per request. | Region | Processing | Storage | | :- | :- | :- | | United States | In region | In region | | European Union | In region | In region | | Australia | **May be processed outside the region** | In region | In the United States and the European Union, requests are processed within that geography, pinned to specific data centres inside it. In Australia, the current deployment may process data outside the region, although stored data remains within it. If your obligations require that document content is processed only within Australia, raise this with your ABBYY account team before Phoenix Plus is enabled for your tenant. ### How your content is used Content you send to ABBYY Phoenix Plus, and the responses it returns: * Is **not available to other customers**. * Is **not available to the provider of the underlying model**. * Is **not used by that provider to improve their models**. * Is **not used to train any generative AI foundation model** without your permission. * Is **not used to improve any first-party or third-party product** without your explicit permission or instruction. ### What is retained **ABBYY does not retain the content you send to Phoenix Plus, or the responses it returns.** The service is designed not to hold them. The regional table above describes where processing happens and where any storage at the platform layer would reside. It does not mean ABBYY keeps a copy of your documents. What your own skills do with the data is separate and under your control. A Custom activity script that writes a model response into a document field, or logs it, stores that content in your tenant in the ordinary way, subject to your own data-retention settings. Protect the credentials stored in each connection you configure yourself: * Never share API keys or include them in a connection's description. * Rotate credentials regularly. * Use separate connections for development and production. * Grant each key the least privilege it needs. These steps do not apply to the ABBYY Phoenix Model connection, which stores no credential of yours and never displays the credential it uses. ## Cost and token usage Usage of **your own LLM connection** is billed by the provider, based on the number of tokens processed. Cost scales with document length, prompt complexity, the document format sent to the model, and the number of fields you extract. Monitor usage in your provider's dashboard, and use smaller, faster models for simple tasks. **ABBYY Phoenix Plus** is not billed by an external provider. Access is a contracted entitlement arranged with your ABBYY account team, and consumption is metered by ABBYY. Your own LLM connections are not metered this way, because they bill through your provider instead. Phoenix Plus consumption is not currently shown in the Vantage interface; for consumption figures, contact your account team. Because usage draws on your entitlement rather than a provider account you control, consider the volume before pointing a bulk reprocessing job at a skill that uses it. ## Supported providers and models Vantage supports several LLM providers for connections you configure yourself, each with its own connection fields and models. For the current list, see [Supported LLM providers and models](/vantage/documentation/llms/supported-providers-models). ABBYY Phoenix Plus does not appear there, because it has no connection fields to configure and its model is selected by ABBYY. ## What's next Set up a tenant-level connection to an LLM provider. Build a prompt-based extraction activity in Advanced Designer. The session API, message limits, and how to handle field positions. ## Related topics * [Skill Designer overview](/vantage/documentation/skill-designer/skill-designer) * [Document skill parameters](/vantage/documentation/skill-designer/skill-parameters/document-skill-params)