10.1 Overview

AIUNIFY PROS SUITE can work with multiple AI models and provider families. When model selection is available to your account, the AI Model Selector appears in the Header and allows you to choose which available model will be used by supported AI workflows.

Model selection can affect:

  1. Which AI provider processes a supported request
  2. The characteristics of the generated response
  3. Whether a provider API Key is required
  4. Whether a Model is currently selectable
  5. The Token cost displayed by standard AI generators
  6. Which models appear in your available Model list

The basic workflow is:

Open AI Model Selector

Review Available Models

Choose Model

If available:

Model Selected

or, if credentials are required:

Model Not Available → Settings → Configure API Key → Select Model Again

Review Tool Token Cost

Generate

The current available Model list is loaded dynamically, so this manual does not treat one fixed list of model names as permanently guaranteed.

10.2 Where the AI Model Selector Appears

When AI Model controls are available, the selector appears in the main PROS SUITE Header.

The control displays either:

  1. The currently selected Model Name

or:

  1. Select Model

if no recognized current model is displayed.

Selecting the control opens:

Select AI Model.

10.3 The AI Model Selector Can Be Unavailable

The Header only displays the AI Model Selector when AI settings are enabled for the current PROS SUITE experience.

Therefore, if you do not see a Model Selector:

  1. Do not assume your account is malfunctioning.
  2. Do not attempt to configure hidden administrative settings.
  3. Use the AI functionality currently presented to your account.

This manual covers only the subscriber controls that actually appear.

10.4 Opening the Model Selector

To review available AI Models:

  1. Sign in to AIUNIFY PROS SUITE.
  2. Locate the AI Model control in the Header.
  3. Select the current Model Name or Select Model.
  4. The dropdown opens.
  5. Review the Models currently displayed under:
  6. Select AI Model
  7. Select the Model you want to use.

10.5 Loading Models

When PROS SUITE is still retrieving the available Model collection, the dropdown displays:

Loading models...

Allow loading to complete before choosing a Model.

The list can be refreshed when provider credentials change.

10.6 The Model List Is Dynamic

One of the most important concepts in this chapter is:

The Model dropdown is the authoritative user-facing list of Models currently available to you.

PROS SUITE begins with a source-defined Model catalogue but also requests an updated Model collection from its AI Model service. If that request returns Models, the application updates the available list.

Because of this, Model availability can change without requiring this User Manual to be rewritten every time.

10.7 Do Not Rely on an Old Model List

AI Models can change over time.

A Model that appears in:

  1. An old screenshot
  2. An earlier Knowledge Base article
  3. A previous PROS SUITE session
  4. A marketing image

may not necessarily be available in your current Model Selector.

Always use:

Header → Select AI Model

to determine what is currently available.

10.8 What a Model Entry Shows

Each Model entry in the Selector can display:

  1. Provider icon
  2. Model Name
  3. Short description
  4. Selected-state indicator

The current Model appears with a small indicator on the right side of its entry.

This makes it possible to see both the identity and intended character of the Model before selecting it.

10.9 Model Descriptions

Model entries include short descriptions intended to help distinguish their general characteristics.

The source-defined Model catalogue contains descriptions such as:

  1. Fast and efficient
  2. Reasoning-oriented
  3. Multimodal
  4. Balanced intelligence and speed
  5. High-performance
  6. Instruction-tuned


Use the description as a quick guide rather than assuming every Model is intended for exactly the same type of work.

10.10 Supported Provider Families

The current PROS SUITE model architecture recognizes Model provider families including:

  1. Google
  2. OpenAI
  3. Anthropic
  4. Mistral
  5. Groq
  6. NVIDIA
  7. Other


The specific Models available under each provider can change.

10.11 Current Source-Defined Model Catalogue

The current source contains a fallback catalogue that includes Models associated with providers such as NVIDIA, Google, OpenAI, Anthropic, Mistral, and Groq.

For example, the source-defined collection contains model families such as:

  1. Gemini
  2. GPT
  3. Claude
  4. Mistral/Mixtral
  5. Llama
  6. DeepSeek
  7. Kimi
  8. Nemotron
  9. GLM
  10. MiniMax
  11. Gemma

However:

This is not a promise that every one of those Models will always appear in your live dropdown.

Use the current Model Selector as the operational reference.

10.12 Current Default Model Definition

The source-defined default Model ID is currently:

Gemini 3.6 Flash.

When no saved user Model preference exists, PROS SUITE initializes Model selection using its default Model definition.

10.13 Dynamic Availability Still Matters for the Default

Although the source defines a default Model, the available Model collection itself is dynamic.

If the current Model collection changes and the automatically selected Model is no longer valid, PROS SUITE can return to its configured default when the user has not established a manual selection.

For users, the simplest rule is:

Look at the Model Name shown in the Header to determine your current Model.

10.14 Your Selected Model Is Remembered

When you manually choose a Model, PROS SUITE stores that selection in the browser.

This allows the browser to remember your preferred Model between sessions.

10.15 Model Preference Is Browser-Specific

Because your selected Model is stored locally in the browser, the selection should not be assumed to automatically synchronize to every device.

For example:

Desktop Browser

→ Model A

can coexist with:

Laptop Browser

→ Model B

You may need to choose your preferred Model again on another browser or device.

10.16 Clearing Browser Data Can Reset Your Model Preference

If browser site data is cleared, the saved Model selection can be removed.

When no saved selection exists, PROS SUITE returns to its current default Model behavior.

If your Model unexpectedly changes:

  1. Open Select AI Model.
  2. Review the currently available Models.
  3. Select your preferred Model again.

10.17 How to Change Models

To change the active Model:

  1. Open Select AI Model.
  2. Review the currently available Models.
  3. Read the Model descriptions.
  4. Select the desired Model.
  5. If the Model is available, PROS SUITE changes the current selection.
  6. Confirm that its Name appears in the Header.
  7. If you are using a standard generator, recheck the displayed Token cost.
  8. Continue with your generation.

10.18 Selecting a Model Does Not Automatically Generate Content

Changing the Model only changes the selected AI Model for supported workflows.

It does not automatically:

  1. Send your current Prompt
  2. Generate a response
  3. Regenerate existing content
  4. Delete existing output

After selecting the Model, return to your Tool and initiate the AI operation normally.

10.19 Some Models May Already Be Available

PROS SUITE can recognize that a Model already has the required access configuration available.

When the necessary configuration is available, selecting the Model simply activates it.

You do not need to enter a personal API Key simply because a Model belongs to another provider if PROS SUITE already considers that Model configured and available.

10.20 Some Models Require Your Own Provider API Key

If PROS SUITE does not find the required provider access for the Model, selecting it can open Settings and display:

Model Not Available

with:

“This model requires an API key. Please configure it in Settings.”

This does not mean the Model Selector itself is broken.

It means the selected Model currently requires provider credentials that are not available to the user session.

10.21 What to Do When You See Model Not Available

If you receive:

Model Not Available

  1. Read the message.
  2. PROS SUITE opens the Settings interface.
  3. Select API Keys if it is not already active.
  4. Locate the provider associated with the Model.
  5. Enter the appropriate provider API Key.
  6. Select Save Changes.
  7. Return to the AI Model Selector.
  8. Allow the Model list to refresh if necessary.
  9. Select the Model again.

Chapter 11 covers API Key configuration in detail.

10.22 Settings Can Open Automatically

When a Model requires an API Key that is not currently available, PROS SUITE automatically opens the Settings dialog as part of the unavailable-Model workflow.

You do not need to manually search for Settings after the warning appears.

10.23 API Key Provider Must Match the Model Provider

If a Model belongs to OpenAI, configuring an unrelated Anthropic Key does not satisfy the OpenAI provider requirement.

Likewise:

  1. Google Model → Google/Gemini provider access
  2. OpenAI Model → OpenAI provider access
  3. Anthropic Model → Anthropic provider access
  4. Mistral Model → Mistral provider access
  5. Groq Model → Groq provider access
  6. NVIDIA-hosted Model → NVIDIA provider access

The Settings interface provides separate credential fields for these provider families.

10.24 Current User-Configurable Provider Keys

The current subscriber Settings interface contains:

  1. Gemini API Key
  2. OpenAI API Key
  3. Anthropic API Key
  4. Mistral API Key
  5. Groq API Key
  6. NVIDIA API Key


You do not need to configure all of them.

Configure only providers you intend to use and for which your PROS SUITE workflow requires a user-supplied Key.

10.25 Model List Can Refresh After API Key Changes

When API Key information changes, PROS SUITE refreshes the available Model collection.

Therefore, after adding a provider Key:

  1. Save the configuration.
  2. Return to the Model Selector.
  3. Allow Loading models... to complete if displayed.
  4. Review the updated list.
  5. Select the desired Model.

10.26 Gemini 2.5 Flash Has Special Selector Handling

The current Header selector contains a special case for a Model with the ID:

gemini-2.5-flash

If that Model appears in the available list, the Header allows it to be selected directly without performing the same API-Key availability check applied to other Model entries.

Important

This should not be confused with the source-defined application default, which is currently Gemini 3.6 Flash.

Because Model availability is dynamic, simply use the current dropdown behavior presented to you.

10.27 Do Not Assume One Gemini Version Will Always Be Available

The current source contains multiple Gemini-related references, including different Model versions and the separate selector handling described above.

This is another reason this manual does not tell subscribers:

“Always select Model X.”

Instead:

Use the available Model list and current PROS SUITE defaults as presented in your account.

10.28 Model Selection Applies Across Supported AI Workflows

PROS SUITE maintains a shared selected Model state that is used by supported AI workflows.

For example, the common streaming process sends the current selected Model along with the Tool request.

Specialized applications can also use the same Model choice for their own AI operations.

10.29 Not Every Tool Has to Use Model Selection Identically

PROS SUITE contains different kinds of applications:

  1. Standard generators
  2. Website Builder
  3. Pitch Deck
  4. Game Developer
  5. AI Agents
  6. Media generators
  7. Connected agents
  8. External generation services

Although many workflows use the shared selected Model, this does not establish that every Tool uses every Model in exactly the same way.

A Tool may:

  1. Support the selected Model directly.
  2. Use a specialized AI workflow.
  3. Use an external generation service.
  4. Have additional provider requirements.

Follow the dedicated Tool chapter when specific Model behavior matters.

10.30 Standard Generator Model Behavior

The standard ToolPage sends the currently selected Model into the shared AI generation workflow.

The shared generation request includes:

  1. Prompt
  2. System instructions
  3. Current Model
  4. Tool identity
  5. Optional image
  6. Optional conversation history


This makes the Header Model selection relevant to many of the Suite's standard AI generators.

10.31 Model Selection Can Affect Standard Tool Token Cost

As established in Chapter 9, the shared standard ToolPage checks the selected Model's provider when calculating the displayed Token cost.

The current rule is:

Base Cost

for the normal standard calculation

and, when the selected Model is recognized as an OpenAI-provider Model:

Base Cost × 1.5, rounded upward.

10.32 Recheck Cost After Changing Models

Whenever you change Models inside a standard ToolPage workflow:

  1. Select the desired Model.
  2. Return to the Tool.
  3. Review:
  4. [number] tokens per use
  5. Compare it with:
  6. Your balance: [number] tokens
  7. Generate only after reviewing the updated cost.

This is especially important when switching between provider families.

10.33 Do Not Apply the OpenAI Multiplier to Every Tool Manually

The current 1.5× rule is verified for the shared standard ToolPage.

It is not established as one universal formula for every specialized PROS SUITE operation.

For example:

  1. Website Builder
  2. Pitch Deck
  3. Image generation
  4. Video generation
  5. AI Agents

can have their own usage behavior.

Do not manually calculate their costs using the standard ToolPage rule unless that workspace itself establishes the same behavior.

10.34 Model Choice Is Not the Same as Tool Choice

A Tool defines the task.

A Model defines the AI engine used by supported workflows.

For example:

Content Writer

= Tool

Selected AI Model

= Model used to process that supported writing request

Both decisions matter.

10.35 Choose the Tool First

For most work, begin by selecting the correct specialized Tool.

For example:

Need an Article

→ Article Writer

Need Google Ads

→ Google Ads

Need a Business Plan

→ Business Plan

Then consider whether a different Model is necessary.

Do not use Model selection as a substitute for choosing the right Tool.

10.36 When You May Want to Change Models

Consider changing Models when:

  1. A particular available Model is better suited to your task.
  2. You want to compare results.
  3. You need a provider-specific capability.
  4. Your organization uses a particular provider.
  5. You have configured a provider Key and want to use it.
  6. The current Model produces an unsatisfactory result.
  7. A particular specialized workflow benefits from another currently available Model.

10.37 When You May Not Need to Change Models

Leave the current Model selected when:

  1. The current Model is producing good results.
  2. You are new to PROS SUITE.
  3. You do not have a reason to select another provider.
  4. You do not want to configure another API Key.
  5. You want to avoid unnecessary changes to Token cost.
  6. Your workflow is already functioning correctly.

Changing Models is optional when the current Model meets your needs.

10.38 Do Not Switch Models Randomly Between Every Generation

Constantly changing Models can make it harder to understand why outputs differ.

A better comparison method is:

Same Tool

Same Prompt

Model A

Review Result

Model B

Review Result

This lets you compare Models under similar conditions.

10.39 Different Models Can Produce Different Results

Two Models can respond differently to the same request.

Differences can include:

  1. Writing style
  2. Length
  3. Structure
  4. Reasoning approach
  5. Code output
  6. Instruction following
  7. Formatting
  8. Creativity

Therefore, selecting another Model can be useful when the current result does not meet the objective.

10.40 Model Descriptions Help With Selection

Before changing Models, read the description displayed beneath each Model Name.

For example, source-defined descriptions distinguish characteristics such as:

  1. Advanced reasoning
  2. Fast and efficient
  3. Multimodal
  4. Balanced intelligence and speed
  5. Fast inference


Use those descriptions as a first-level guide.

10.41 Understanding Provider vs. Model

A provider can offer one or more Models.

For example:

Provider

→ Google

Model

→ A particular Gemini model

or:

Provider

→ Anthropic

Model

→ A particular Claude model

Your API Key is generally associated with the provider rather than with one individual PROS SUITE Tool.

10.42 NVIDIA-Hosted Models

The current source-defined catalogue includes several Models routed through the NVIDIA provider family, including models originating from different AI organizations.

For users, this means the Model's branding and the provider used to access it are not always identical.

For example, a Model may have a familiar model-family Name while its provider in PROS SUITE is NVIDIA.

Follow the provider shown/required by PROS SUITE when configuring access.

10.43 Do Not Guess Which API Key a Model Needs

If PROS SUITE reports:

Model Not Available

use the provider relationship presented by the Suite.

Do not assume a Key based solely on the Model's brand Name.

The current Model catalogue explicitly records both:

  1. Model Name
  2. Provider


10.44 Current Provider Status in Settings

Settings includes a:

Current Status:

area for configured provider Keys.

It can display statuses such as:

🟢 Custom Key Set

or:

⚪ Not Configured

For Gemini, the current interface can also display:

🟠 using default/demo.

This can help you understand which personal provider credentials you have already configured.

10.45 You Do Not Need a Key for Every Provider

There is no requirement for a normal user to enter:

  1. Gemini
  2. OpenAI
  3. Anthropic
  4. Mistral
  5. Groq
  6. NVIDIA

all at once.

Configure only those required for Models you actually intend to use.

10.46 Personal API Key Configuration Is Optional Until Needed

A good first-time workflow is:

Use Current Available Model

If it works:

Continue

If you deliberately select another Model and receive:

Model Not Available

Configure the appropriate provider Key

This avoids unnecessary credential configuration.

10.47 Save Changes After Entering a Key

When you configure provider credentials in Settings, select:

Save Changes.

PROS SUITE confirms:

API Keys configuration saved

and:

“Your API keys have been updated successfully.”

Then return to Model selection.

10.48 Cancel Leaves the Settings Dialog

If you opened Settings but decide not to configure another provider, select:

Cancel.

You can continue using an already available Model.

10.49 API Key Configuration and Model Selection Are Separate Steps

The workflow is:

Configure Provider Key

Save Changes

Model List Refreshes

Open Select AI Model

Select Desired Model

Entering an API Key does not itself necessarily mean that Model has become your currently selected Model.

10.50 Model Selection Is Persisted After Manual Choice

When you manually select a Model, PROS SUITE records the choice as a manual selection and stores it locally in the browser.

The browser can then restore that selection when PROS SUITE loads again.

10.51 A Saved Model May Become Unavailable Later

Because the available Model collection can change, a Model previously saved in your browser may later:

  1. Be removed
  2. Be renamed
  3. Require different access
  4. No longer appear in the dropdown

If your Header no longer shows the expected Model correctly:

  1. Open Select AI Model.
  2. Review the current list.
  3. Select another available Model.
  4. Configure a provider Key only if required.

10.52 Model Availability Is Not the Same as Plan Tool Access

Plan access determines whether you can use a PROS SUITE Tool.

Model availability determines which AI Model can be selected for supported Tool operations.

For example:

Business Plan included in your Plan

does not automatically mean:

Every AI Model is available without provider credentials.

These are separate access layers.

10.53 Tokens Do Not Unlock Provider Models

Having a large Token Balance does not automatically satisfy a missing provider API Key requirement.

You can have:

10,000 Tokens

and still receive:

Model Not Available

if the selected Model requires provider access that is not currently configured.

Likewise, having a provider API Key does not replace the need for sufficient PROS SUITE Tokens.

10.54 Model Access, Tool Access, and Tokens Are Three Separate Questions

Before an AI operation, think of three layers:

Layer 1 — Tool Access

Can your PROS SUITE account use the Tool?

Layer 2 — Model Access

Is the selected Model currently available/configured?

Layer 3 — Token Availability

Do you have sufficient PROS SUITE Tokens for the operation?

The ideal state is:

Tool Available + Model Available + Sufficient Tokens

→ Generate.

10.55 Example — Using the Current Model

Suppose Content Writer is already working normally.

Recommended workflow:

  1. Open Content Writer.
  2. Leave the current Header Model unchanged.
  3. Review the Token cost.
  4. Enter your Prompt.
  5. Generate.
  6. Review the result.

You do not need to change Models simply because the Selector exists.

10.56 Example — Selecting an OpenAI Model

Suppose an OpenAI-provider Model appears in the dropdown.

  1. Open Select AI Model.
  2. Select the OpenAI Model.
  3. If PROS SUITE considers provider access available, the Model becomes selected.
  4. If not, Settings opens with:
  5. Model Not Available
  6. Configure the OpenAI provider Key if appropriate.
  7. Save Changes.
  8. Select the Model again.
  9. Return to your standard Tool.
  10. Recheck tokens per use, because the standard ToolPage applies its OpenAI display-cost rule.

10.57 Example — Selecting an Anthropic Model

If an Anthropic Model is available:

  1. Open Select AI Model.
  2. Select the Model.
  3. If provider access is available, proceed.
  4. Otherwise, Settings opens.
  5. Enter the appropriate Anthropic API Key.
  6. Save Changes.
  7. Select the Model again.

The Settings interface identifies Anthropic credentials for Claude-family Models.

10.58 Example — Selecting a NVIDIA-Provider Model

If you select a Model whose provider is NVIDIA:

  1. Open the Model Selector.
  2. Select the Model.
  3. If NVIDIA provider access is not available, Settings opens.
  4. Configure NVIDIA API Key.
  5. Save Changes.
  6. Return to the Selector.
  7. Select the Model again.

The current Settings interface contains a dedicated NVIDIA provider field.

10.59 Example — Comparing Two Models

Suppose you want to compare writing quality.

First Run

Tool:

Content Writer

Prompt:

Use one complete fixed Prompt.

Model:

Model A

Save the result.

Second Run

Keep the same Tool and Prompt.

Change to:

Model B

Recheck Token cost.

Generate again.

Then compare:

  1. Accuracy
  2. Style
  3. Organization
  4. Usefulness
  5. Token cost

This creates a meaningful comparison.

10.60 Troubleshooting — Model Selector Is Missing

If you do not see the Selector:

  1. Confirm you are signed in.
  2. Check the Header at an appropriate screen size.
  3. Continue using the available PROS SUITE AI workflow if no Selector is presented.

The current Header only renders the Model control when AI-settings visibility is enabled.

The ordinary subscriber does not need to manage the platform-level visibility control.

10.61 Troubleshooting — Loading Models Does Not Finish

If Loading models... remains unusually persistent:

  1. Check your internet connection.
  2. Close and reopen the Model dropdown.
  3. Reload the current page.
  4. Confirm that PROS SUITE itself is otherwise functioning.
  5. If you recently changed provider credentials, ensure you saved them.
  6. If the issue continues, use the appropriate AIUNIFY support process.

10.62 Troubleshooting — Model Not Available

If you see:

Model Not Available

“This model requires an API key. Please configure it in Settings.”

the normal resolution is:

Settings → API Keys → Correct Provider → Enter Key → Save Changes → Select Model Again.

10.63 Troubleshooting — API Key Was Added but Model Still Does Not Select

Try:

  1. Confirm Save Changes was selected.
  2. Open the Model Selector again.
  3. Allow the Model list to refresh.
  4. Confirm you configured the correct provider.
  5. Select the Model again.
  6. If necessary, reload PROS SUITE.

The available Model list is refreshed when API Key state changes.

10.64 Troubleshooting — Wrong Provider Key Was Configured

Check the Model's provider.

For example:

Anthropic Model

needs Anthropic provider access—not OpenAI.

Return to:

Settings → API Keys

and configure the correct provider.

10.65 Troubleshooting — Model Changed After Browser Data Was Cleared

This can happen because the manually selected Model is stored in the browser.

Open Select AI Model and choose your preferred Model again.

10.66 Troubleshooting — Model Is Missing from the Dropdown

A previously available Model may no longer appear because the list is dynamically loaded.

Do not attempt to force an old Model Name manually.

Instead:

  1. Review the current Model list.
  2. Read the available descriptions.
  3. Select an appropriate alternative.

10.67 Troubleshooting — Token Cost Increased After Changing Model

If you are using a standard ToolPage and changed to a recognized OpenAI-provider Model, the current Token display can increase according to its verified OpenAI multiplier.

This is expected behavior in the shared standard generator.

Recheck the cost before generating.

10.68 Troubleshooting — Model Works in One Tool but Another Tool Behaves Differently

This can occur because PROS SUITE contains different AI architectures.

A standard generator may use the selected Model directly through the shared streaming workflow, while a specialized Tool may use additional or separate generation processes.

Follow the dedicated chapter for that Tool.

10.69 Troubleshooting — You Have a Provider Key but Insufficient Tokens

Provider access does not replace PROS SUITE Tokens.

If the Model is available but the operation reports insufficient Tokens:

  1. Check Monthly Tokens.
  2. Check the operation cost.
  3. Review your Plan if necessary.

This is a Token issue, not a Model-credential issue.

10.70 Troubleshooting — You Have Tokens but Model Is Unavailable

Likewise, sufficient Tokens do not replace provider access.

If you have enough Tokens but see:

Model Not Available

configure the required provider or use another Model already available.

10.71 Best Practice — Start With the Current Available Model

New users should generally begin with the Model already selected by PROS SUITE.

Learn:

  1. Tool navigation
  2. Prompting
  3. Output review
  4. Token usage

before adding multiple provider credentials and comparing many Models.

10.72 Best Practice — Change Models for a Reason

Good reasons include:

  1. Different result quality
  2. Different Model specialization
  3. Provider preference
  4. Organizational requirements
  5. Need for another currently available capability
  6. Testing the same Prompt across Models

Avoid switching merely because many Model Names are available.

10.73 Best Practice — Recheck Cost Every Time You Change Provider

When using a standard generator:

Model Change

Provider May Change

Displayed Cost May Change

Review Cost Before Generate

This prevents unexpected Token usage.

10.74 Best Practice — Do Not Configure Providers You Do Not Use

Adding every available provider Key gives little benefit if you do not intend to select those Models.

Configure provider access as needed.

This keeps your Setup simpler and makes Model selection easier to understand.

10.75 Best Practice — Compare Models Using Consistent Inputs

If testing quality, keep constant:

  1. Tool
  2. Prompt
  3. Instructions
  4. Context
  5. Output objective

Then change only the Model.

Otherwise, you cannot determine whether the difference resulted from the Model or your changed instructions.

10.76 Best Practice — Save Good Outputs Before Comparing Models

Before generating the same request using another Model:

  1. Copy or Download the current result.
  2. Note which Model produced it.
  3. Change Models.
  4. Generate the comparison version.

This prevents accidentally losing a result you preferred.

10.77 Best Practice — Use Model Descriptions as Guidance, Not Guarantees

Descriptions help summarize a Model's intended strengths, but actual performance depends on:

  1. Your Prompt
  2. Tool design
  3. Task complexity
  4. Input quality
  5. Files/context supplied
  6. Current provider behavior

Test Models on your actual workflow before deciding which one you prefer.

10.78 Best Practice — Keep Sensitive Provider Credentials Private

Your API Keys are sensitive credentials.

Do not:

  1. Place them inside AI Prompts.
  2. Paste them into Chat.
  3. Include them in documents.
  4. Send them to unauthorized users.
  5. Post screenshots showing them.

Enter them only through the appropriate Settings → API Keys fields when needed.

10.79 Model Selection Workflow

The complete user workflow is:

Open PROS SUITE

Header

Select AI Model

Review Current Available Models

Read Name + Description

Choose Model

If available:

Selected

If unavailable:

Model Not Available

Settings → API Keys

Configure Correct Provider

Save Changes

Model List Refreshes

Select Model Again

Return to Tool

Check Token Cost

Generate

10.80 Model Decision Checklist

Before changing Models, ask:

  1. Is my current Model already producing acceptable results?
  2. Is the alternative Model currently visible?
  3. What provider does it use?
  4. Does PROS SUITE already allow me to select it?
  5. Does it require a provider API Key?
  6. Do I have the appropriate provider credentials?
  7. Am I using a standard Tool where Token cost may change?
  8. Have I reviewed the new Token cost?
  9. Am I changing the Model for a specific reason?
  10. Have I saved any previous output I want to compare?

10.81 Model Access Checklist

If a Model cannot be used:

  1. Read the exact error.
  2. Look for Model Not Available.
  3. Open Settings.
  4. Select API Keys.
  5. Identify the correct provider.
  6. Enter the appropriate Key if needed.
  7. Select Save Changes.
  8. Allow the Model list to refresh.
  9. Open Select AI Model again.
  10. Select the Model.
  11. Confirm its Name appears in the Header.
  12. Recheck the Tool's Token cost.

10.82 What Subscribers Do Not Need to Manage

Ordinary PROS SUITE users do not need this manual to explain how to:

  1. Add Models platform-wide
  2. Remove Models platform-wide
  3. Configure global provider credentials
  4. Change system-wide AI settings
  5. Define Model availability for other users
  6. Modify AI infrastructure
  7. Configure Model routing
  8. Modify default Models for the entire platform

Those are not subscriber operations.

The user needs to know only:

Which Models are available to me?

Which one am I using?

Can I select another one?

Does it require my provider Key?

Does switching affect my Token cost?

10.83 Important Current-Version Model Notes

Several source-verified details are worth keeping together:

Default Definition

The current source default is:

Gemini 3.6 Flash.

Dynamic List

The actual available Model collection can be refreshed dynamically.

Saved Preference

A manually selected Model is saved in the browser.

Gemini 2.5 Special Handling

If gemini-2.5-flash appears in the Model list, the Header currently permits direct selection without applying its normal provider-key availability check.

Other Models

The selector checks whether the required provider access is available and otherwise opens Settings with Model Not Available.

For these reasons, the live Selector should always be considered the best source for current user Model availability.

10.84 Model Selection at a Glance

The user-facing model system can be understood as:

TOOL

What do I want to accomplish?

MODEL

Which available AI engine should perform the supported AI work?

PROVIDER ACCESS

Is the required Model/provider available?

TOKEN COST

What does the Tool/action currently cost?

PROMPT

What do I want generated?

OUTPUT

Review the result.

The three important access layers remain:

Tool Access + Model Access + Token Availability

10.85 Chapter Summary

AIUNIFY PROS SUITE provides a shared AI Model Selector in the Header when that functionality is available.

The Selector displays the currently selected Model, opens under:

Select AI Model

and presents dynamically available Models with their Names and descriptions.

The current source recognizes provider families including:

Google, OpenAI, Anthropic, Mistral, Groq, NVIDIA, and Other.

The source-defined default Model is currently Gemini 3.6 Flash, but the available Model collection can be refreshed dynamically, so users should rely on the live Model Selector rather than a permanent list in this manual.

When a Model requires provider access that is not available, PROS SUITE displays:

Model Not Available

“This model requires an API key. Please configure it in Settings.”

and opens Settings.

A manually selected Model is remembered in the browser.

For standard ToolPage generators, Model choice can also affect the displayed Token cost. A recognized OpenAI-provider Model currently applies a 1.5× displayed-cost multiplier, rounded upward, to the standard Tool's base cost.

The recommended operating sequence is:

Choose the Right Tool → Use the Current Model Unless You Have a Reason to Change → Select Another Model When Appropriate → Configure the Correct Provider Only if Required → Recheck Token Cost → Generate → Compare Results

Write Your Comment