A practical guide to how Smith measures usage, what affects how quickly you draw on your monthly credit, how the included AI models compare, and how to get the most out of your subscription day to day. Applies to both standalone Smith subscriptions and Smith access bundled with Catalyst, Compass, Diligent, or Ontario.
What's Included in Your Plan
Smith gives your team secure, governed access to leading AI models on your enterprise data. Every Smith user gets the same platform capabilities, regardless of how Smith was provisioned for your organization: the core workspace, three AI models, document ingestion, personas, governance, and audit trail.
How your organization accesses Smith
Smith reaches users through one of two routes. The route your organization uses determines how billing works, but the platform features and usage mechanics are identical in both cases.
Standalone Smith subscription
Your organization signed up for Smith directly. Billing is a fixed monthly fee plus per-seat charges as your team grows, with monthly usage credit included.
Pricing details are in the next section.
Bundled with another EBM product
Smith was enabled through your existing subscription to Catalyst, Compass, Diligent, or Ontario. There is no additional base fee or per-seat charge. Billing is purely consumption-based, drawn from your monthly Smith usage credit.
Skip ahead to "What Is a Prompt" if pricing details don't apply to you.
Platform capabilities (every Smith user)
Whichever route applies to your organization, every Smith user gets the same platform features:
Claude Haiku 4.5, GPT-5.1, and Gemini 2.5 Pro included as standard. Seven additional models available as add-ons for a one-time $50 unlock fee per model.
A monthly allowance shared across your team. Drawn down based on model and complexity, not a fixed prompt count. Standalone Smith subscriptions include $125 per month; bundled users have an allowance set by their parent subscription.
A dedicated workspace for your documents, files, and data sources, indexed once and queried on demand. Standalone Smith subscriptions include 20 GB.
Upload files once, query them indefinitely. Smith only retrieves documents you explicitly select or reference.
Customize how Smith responds with personas built around your team's needs. Prompt libraries are coming soon.
Visibility of every interaction. Users can export chat files; a self-serve audit trail for admins is coming soon.
Standalone Smith pricing
This section applies to standalone Smith subscriptions only. If your organization accesses Smith through a Catalyst, Compass, Diligent, or Ontario subscription, billing is consumption-based against your usage credit, and the section below does not apply.
BASE PACKAGE AT A GLANCE
$500
per month
5 users
included
$125
monthly usage credit
~5,000
prompts/month*
*Estimate based on the default model (Claude Haiku 4.5) at standard complexity.
New standalone Smith subscriptions get a 30-day risk-free trial. A card is required at sign-up but you will not be charged until your trial ends, and you'll receive a notification before it does. All base plan features are unlocked during your trial. The trial does not apply to organizations accessing Smith through another EBM product.
Adding users
Seats are added directly from the Roster Management page with no contracts and no waiting. Per-seat pricing reduces as your team grows, and each added seat brings additional monthly usage credit.
USERS 1 TO 5
Included
Five seats are bundled into the base $500/month package.
USERS 6 TO 10
$75 / user / month
Each added seat includes an extra $25 usage credit on top of your team's monthly pool.
USERS 11 AND ABOVE
$50 / user / month
Per-seat rate reduces from the eleventh seat onwards. Every seat retains full feature access.
Add-on AI models
Beyond the three included models, Smith supports seven additional AI models that can be unlocked at a one-time fee of $50 per model. Most teams find the three included models cover the majority of their work. Add-on models are worth considering when there is a specific workflow gap, such as the very fastest responses for high-volume simple queries, the highest-quality analytical depth for M&A or complex modeling work, or the most capable reasoning available for the most demanding analyzes.
To unlock an add-on today, contact our Support team. The model is installed in your instance by next working day. Self-serve unlocking from within the Roster Management page is COMING SOON
What Is a Prompt, and How Is Usage Measured?
Every time you submit a question or request to Smith, that counts as one prompt. One submission equals one prompt, regardless of how long or complex your question appears to be.
Usage, however, is measured in dollars rather than prompt count. Each prompt draws a small amount from your monthly usage credit based on how much processing the AI performs to produce your answer. Before generating a response, Smith reads your question, processes your conversation history, and analyzes any files you have selected or referenced by name. All of that processing counts toward the cost of the prompt.
The practical implication: a three-word question that triggers retrieval of five large workspace documents uses more credit than a detailed paragraph-long question with no document context. Question length is almost irrelevant. What the system reads on your behalf is what matters.
When you submit a prompt, Smith breaks your question, conversation history, and any referenced documents into small units called tokens. Tokens are how AI models measure the volume of text they process. More tokens means more processing, which is why document-heavy prompts draw more credit than short, standalone questions. You don't need to track tokens directly; your usage credit and the complexity tiers below handle this for you.
The Four Prompt Complexity Tiers
Prompts are automatically categorized into one of four tiers based on how much the AI processes. These tiers are not labels you assign; they are determined by the volume of information Smith handles to produce your answer.
Smith answers from memory or with a quick lookup; no large document retrieval is involved. These prompts use the smallest amount of credit.
Examples:
- "Rewrite this email and make it more formal."
- "What does working capital mean?"
- "Summarize this paragraph in plain English."
Usually involves retrieving content from a document, drafting a short narrative, or a moderate level of reasoning. The most common tier in production. These prompts work best with relatively small files (a few pages, or a CSV with a single table of around 500 rows) without complex calculations involved.
Examples:
- "Pull the top 10 customers by gross margin from the uploaded board pack."
- "Draft variance commentary for Q1 2026 revenue vs budget."
- "What were the primary drivers of EBITDA decline in Q3?"
- "List all covenant terms mentioned in this credit agreement."
Complex tasks requiring large document contexts, multi-part answers, or multiple data sources in a single prompt. Typically draws roughly two to five times the credit of a Standard prompt.
Examples:
- "Analyze this 30-page management report and identify the top 3 risks to EBITDA next quarter, with supporting evidence."
- "Review this credit agreement and flag every clause with a financial implication, organized by risk level."
- "Compare this year's board pack to last year's and produce a structured summary of what has changed."
Multiple sources processed in parallel, multi-model comparison runs, or a long session with substantial conversation history. Reserve these for genuinely high-stakes decisions where the depth of the answer materially changes the outcome.
Examples:
- "Run this M&A target summary through all three models and compare their risk assessments side by side."
- "Review these five vendor contracts simultaneously and identify inconsistencies in payment terms, penalty clauses, and termination rights."
- "Process this 100-page due diligence document and produce a structured executive summary."
A routine question can register as a Power-tier prompt if it is asked midway through a long session. Smith includes your conversation history as context in every new prompt, which adds processing overhead as sessions grow. Starting a fresh session when moving to a new topic keeps prompt complexity low.
What Affects Your Usage
Six factors determine how much of your monthly credit any given prompt draws. Understanding these helps you use Smith efficiently without changing how much work you do. The first three are the highest-impact and the most controllable.
IMPACT KEY
The three included models process prompts at different rates. Claude Haiku 4.5 is the most credit-efficient and the recommended default. GPT-5.1 and Gemini 2.5 Pro use approximately 1.5x the credit of Haiku per Standard prompt, so defaulting to either for routine queries draws down credit noticeably faster than necessary.
Smith can run multiple AI models simultaneously and compare their outputs side by side. Each model runs the full processing pipeline independently, so running three models at once uses three times the credit of a single-model prompt. Use this feature intentionally rather than as a default.
When you select Workspace documents for a prompt, or reference them by name, Smith retrieves and analyzes their content to inform the answer. More documents, or larger documents, means more processing per prompt. This is the most common reason short questions register in a heavier complexity tier. Smith only queries documents you explicitly select or reference; it does not automatically search your full Workspace.
Smith includes your full conversation history as context in each new prompt, which keeps answers contextually relevant within a session. A session with 50 prior messages carries substantially more overhead per new prompt than a fresh one. For unrelated topics, starting a new session is the most efficient approach.
Files attached directly in a chat session are re-processed in full with every prompt that references them. A 50-page report attached in session and referenced across ten prompts sends that report's full content ten times. For documents you'll query more than once, uploading them to your Workspace is significantly more efficient: they're indexed once and retrieved only when selected.
Smith triggers a web search when a question requires current information from outside your Workspace. This happens automatically when needed and counts as a small additional step. Most financial queries against your own documents and data don't require it.
Model selection, multi-model runs, and document retrieval volume are the three highest-impact factors and the most controllable. Understanding these three gives you significant ability to manage your usage credit without changing how much you use the platform.
Choosing the Right AI Model
Smith includes three AI models, each with a distinct strength profile. The platform's model selector shows a price scale (1 to 4) and a brief description for each model so you can make an informed choice at the point of selection.
The recommended default. Fast, capable, and the most credit-efficient model in the package.
Best for:
Most daily financial queries: document Q&A, variance commentary drafting, data lookups, summarization, and contract clause extraction. Start here unless the task clearly demands more.
Skip when:
Complex multi-document synthesis or high-stakes analytical work where answer depth materially changes the output.
The step-up for structured reasoning and multi-step logic.
Best for:
Complex variance and bridge analysis, structured data extraction, multi-step financial reasoning, contract analysis requiring inference across clauses, and scenario modeling. Step up to GPT-5.1 when Haiku gives a technically correct but shallow answer.
Skip when:
Simple lookups and routine queries where Haiku performs equally well. No need to step up if Haiku already delivers.
The long-reader. The largest context window of the three, built for large documents.
Best for:
Analysis of very large documents (100+ page board packs, multi-contract review, full due diligence files), complex synthesis across many sources in a single prompt, and investor narrative development. Choose this when the volume of material is the challenge.
Skip when:
Routine queries and standard document retrieval. Gemini 2.5 Pro uses approximately 1.5x the credit of Haiku at Standard complexity, so reserve it for workloads that genuinely benefit from its long context.
Tips for Getting More from Your Credit
Five practices make a meaningful difference to how efficiently your team uses its monthly credit, without changing the quality or volume of work you get done.
Haiku handles the large majority of daily financial queries effectively and is the most credit-efficient model in your package. Make it the default. Step up to GPT-5.1 when a task requires deeper reasoning, or to Gemini 2.5 Pro when working with very large documents. The difference in answer quality for routine queries is minimal; the difference in credit draw is significant.
Smith carries your full conversation history into every new prompt in a session. This is valuable for maintaining context within a topic, but when you move to a different question or project, that accumulated history adds unnecessary overhead. Starting a new session keeps your prompts lean and your credit efficient.
Files uploaded to your Workspace are indexed once and retrieved only when you explicitly select them or reference them by name. Files attached directly within a chat are re-processed in full every time. For any document your team queries more than once, recurring board packs, standard templates, or active contracts, the Workspace is the right place for it.
Running two or three models simultaneously gives you multiple analytical perspectives on a single question, which is genuinely valuable for high-stakes decisions. It also uses two or three times the credit of a single-model prompt. For routine queries, a single model is faster and more efficient. Reserve multi-model mode for the decisions where diverse perspectives materially improve the output.
A precisely framed question gets a better answer in fewer exchanges. Vague prompts often require follow-up clarifications, each of which counts against your credit. Front-loading the relevant context, the reporting period, the specific document, the exact question, reduces the number of back-and-forth turns and produces a more useful first response.
If your team adopts only two of these practices, make them tips 2 and 3: starting fresh sessions for new topics and uploading documents to the Workspace rather than attaching them in session. These are the single biggest adjustments most teams can make immediately.
Common Questions
It depends on how your organization chose to access Smith. If you subscribe to Catalyst, Compass, Diligent, or Ontario, your admin can opt in to Smith from within that product, in which case there is no additional base subscription fee or per-seat charge. Billing for bundled users is purely consumption-based against your monthly Smith usage credit. Standalone Smith subscriptions are also available for organizations that want Smith without a parent product, with a fixed monthly fee plus per-seat charges. If you're not sure which route applies to your organization, your admin or our Support team can confirm.
For standalone Smith subscriptions, your base package includes $125 in monthly usage credit, supporting an estimated 5,000 prompts using the default model at standard complexity. For bundled access through Catalyst, Compass, Diligent, or Ontario, your usage allowance is set by your parent subscription. Teams using Claude Haiku 4.5 for standard financial queries will generally stay comfortably within their allowance; teams running multi-model comparisons on large documents daily will use more. A real-time view of your team's credit balance and consumption inside the Roster Management page is COMING SOON. In the meantime, contact our team for your current usage figures.
Pop-up notifications when your team's usage reaches a configurable percentage of your cap are COMING SOON. The default threshold will be 80%, with admin control to adjust between 50% and 95% from the Roster Management page. The same area will also show a real-time view of your current spending against your cap. Until then, contact our team if you'd like a usage check at any point in the month.
For standalone subscriptions, self-serve credit purchases in $50 increments from the Roster Management page are COMING SOON, alongside cap adjustments. For now, contact our team to top up your credit or raise your cap; top-ups take effect immediately within the billing month. For bundled users, additional usage allowance is handled through your parent subscription; contact your account manager.
The two most common reasons are session length and document volume. If the question was asked midway through a long session, the accumulated conversation history adds processing overhead to every new prompt. Equally, if you had selected several large documents from your Workspace for Smith to reference, that raises the complexity of the prompt regardless of how short the question itself was. Starting a fresh session and being selective about which documents you include will usually resolve this.
Yes. Seven additional models can each be unlocked at a one-time fee of $50 per model for standalone Smith subscriptions. To request an unlock today, contact our team and the model will typically be installed in your instance by the next working day. Self-serve unlocking from the Roster Management page is COMING SOON. For bundled users, model availability is governed by your parent subscription; contact your account manager. The in-platform model selector shows each model's usage cost indicator and a plain-language description of what it's best for.
Yes. Standalone Smith admins can add seats today directly from the Roster Management page, with no contracts and no waiting. Users 6 through 10 are billed at $75 per user per month with $25 usage credit added per seat; from the eleventh seat onwards the rate reduces to $50 per user per month. Bundled users add seats through their parent product (Catalyst, Compass, Diligent, or Ontario), which governs seat counts and any associated charges. Every seat in either case retains full Smith feature and model access.
Yes. Smith operates in a private, secure workspace. Your data is never used to train AI models, and it never leaves your infrastructure. All data is stored in encrypted storage. For full detail on certifications, encryption, hosting, and access controls, see the Smith security article. For enterprise-specific security or compliance questions, contact our team directly.
The three included models, Claude Haiku 4.5, GPT-5.1, and Gemini 2.5 Pro, are built into your base subscription and cover the majority of use cases. Seven add-on models extend your access to the full AI portfolio at a one-time unlock fee of $50 per model. They are worth considering for specific workflow needs: very high-volume simple queries, the highest-quality analytical writing, or the most demanding reasoning tasks. The platform's model selector guides you through each option at the point of selection.
Access the Roster Management page by clicking your profile image in Smith and selecting it from the dropdown menu. The actions below apply to standalone Smith subscriptions; for bundled access, plan-level changes are handled through your parent subscription.
Manage seats
Add or remove users. New seats activate immediately, no contracts.
Roster Management LIVE
View usage & manage caps
Real-time credit balance, current spend, and cap configuration.
Contact Support SOON
Unlock add-on models
Request additional models at $50 per model. Installed by our team, typically next working day.
Contact Support SOON
Related Articles
Security and Account
A complete view of how Smith protects your data, including hosting, encryption, certifications, access controls, and account management.
Workspaces
How to upload, organize, and reference documents in your Workspace. The most credit-efficient way to query files Smith will see more than once.
Conversations
How sessions work in Smith, including when to start a new one. Directly relevant to keeping your prompts lean and your credit efficient.
Next Steps: You now have a clear picture of how usage works in Smith and the highest-leverage habits for getting more from your monthly credit. The two practices that make the biggest difference immediately are starting fresh sessions for new topics and uploading recurring documents to your Workspace. For full details on data protection and access controls, see the Security and Account article.
Comments
0 comments
Article is closed for comments.