AI spend is growing fast, and most of it arrives unattributed. Your business needs to go deeper than the top-line total, understanding which team, project, or product is driving that cost. AI provider invoices don't carry that detail on their own, but your LiteLLM gateway already does: every request is priced and tagged by team, key, and model.

Ternary now documents a direct path to bring that gateway detail into your unified technology P&L. Point LiteLLM's built-in FOCUS export at a bucket you control, ingest it through Bring Your Own Data, and pair it with your AI provider invoice in the Billing Rules Engine: the invoice supplies the dollars, the gateway supplies the proportions. The output is a zero-sum reallocation of real invoiced spend across teams and cost centers that is reconciled to the bill, not estimated.

• Team, model, and provider breakdowns - report on AI spend by team, model, and provider, alongside your other cloud costs.
• User- and key-level granularity - map LiteLLM's Tags field to break down by user and API key with no extra tagging work.
• Invoice-true reconciliation - Reallocate Costs billing rules split invoiced AI dollars using gateway proportions.

Requires a self-hosted LiteLLM proxy (v1.98.0+) writing its FOCUS export to a GCS or S3 bucket.

Learn how to get started with our LiteLLM AI Gateway guide.

AI assistants are now the first place people go to ask questions about their business, including questions about AI and technology spend. The problem comes when someone asks "what did we spend on AI last quarter," the assistant either guesses, or someone pastes in a CSV that's already stale by the time it's answered. That's a governance gap: judgment made on secondhand data, outside any controls, outside your permission model.

The Ternary MCP server closes it. Connect Claude, ChatGPT, VS Code, or any MCP-compatible assistant directly to your live technology P&L. No more exports, copy-paste, or shadow spreadsheets standing in for the system of record. Data spans every Custom Label, Custom Measure and provider integrated into Ternary. Ask questions of your data from Anthropic, AWS, Azure, GCP, Oracle Cloud, Alibaba Cloud, Databricks, Snowflake, MongoDB Atlas, OpenAI, and any custom source brought in via BYOD.

• "What did we spend on BigQuery last quarter, broken out by project?"
• "Is the Q3 infrastructure budget on track, at risk, or over?"
• "What moved on the Engineering dashboard this week, and which services drove it?"
• "Pull the saved AI Observatory report and show me token spend by model family."

What it does:

• Live cost queries - The assistant discovers your real dimensions and measures, then runs queries against FOCUS-normalized, finance-grade attribution - the same data model behind every report in Ternary.
• Saved reports and dashboards, on demand - Pull existing reports or ask what changed on a dashboard week-over-week, with drivers surfaced automatically.
• Budget status, instantly - Spend to date, projected month-end, and health status.
• Governed by design - OAuth-authenticated, read-only, and permission-scoped to exactly what the requesting user can already see in Ternary. No new access is created.

Learn more on how to connect your preferred AI assistant here.

AI spend is not a single line item. It's Anthropic models running via AWS Bedrock. It's Azure OpenAI alongside direct OpenAI API calls. It's Gemini, Grok, Qwen, and a dozen other models procured through different channels, billed in different formats, and invisible to any single reporting surface.

AI Observatory is Ternary's global dashboard for AI spend and token usage. A single, governed view across every AI provider, vendor, model family, and version in your technology portfolio. This dashboard will be consistently updated to reflect the latest models.

Unified AI Schema Powering Observatory is a provider-agnostic framework that normalizes AI-specific data from every source into a standardized schema. This enables consistent querying, reporting, and analysis regardless of where the spend originates. Every record is attributed by provider, publisher, modality, input/output tokens, model, and version. Claude, ChatGPT, OpenAI's reasoning models and Whisper, Moonshot Kimi, xAI Grok, Alibaba Qwen, Zhihu GLM, MiniMax, Amazon Nova and Titan are all in one place and in the same format.

What you can do with it

• Cloud Provider AI Analysis - Break down AI spend procured via GCP, AWS, and Azure, with vendor and model-level attribution across Anthropic, OpenAI, Google, Meta, and more.
• AI Guardrails - Create budgets and alerts around token usage and cost by model, provider, or any dimension. Control what happens at the point of consumption, not after the invoice arrives.
• Allocate, Showback, and Chargeback - Use Ternary's Billing Rules Engine to attribute AI spend directly to the teams, products, and cost centers that incurred it.
• Custom Labels - Existing label rules apply to AI spend automatically. Create new labels to organize AI investment in ways that map to your business.

A Starting Point, Not a Ceiling. Ternary's AI Observatory is designed as a launchpad. Every report underlying the dashboard is available in the Ternary Reporting Engine, ready to be filtered, grouped, and customized to reflect the specific dimensions, models, and cost structures that matter to your business.

AI Observatory is available now. Navigate to AI Observatory in the left-hand navigation to get started.

Custom Labels are only as powerful as the people who can use them confidently. Until now, only admins could see the logic behind a label. This left every other user in the Ternary Reporting Engine to interpret cost categorizations without context or understanding of the logic behind them.

All Custom Labels now carry descriptions available to all users. These descriptions are authored either by the admin who built them or generated directly from the underlying rule logic by AI. When anyone interacts with a Custom Label throughout Ternary, the intent and logic behind that label is visible, in plain language, right where they need it.

The result is that every cost categorization in your technology estate is now self-documenting. Consistent interpretation, across every user, every report, every review.

To add a description, open any Custom Label, enter your description manually or select Generate with AI to derive it from the rule logic automatically. To view the description, hover your mouse over the (i) icon next to the Custom Label name when viewing a filter.

We’ve introduced the Notification Center, a centralized place to manage subscriptions across Ternary.

What’s new:

• My Subscriptions. View and manage all active subscriptions in a single table. Filter by type, trigger, or delivery channel, and edit or unsubscribe directly.
• Owned Content. See who is subscribed to reports, dashboards, budgets, and alert rules you own, and manage subscribers without leaving the page.
• Supported subscription types. Reports, Dashboards, Budgets, and Alert Rules are all supported.

Why it matters:

• Previously, subscriptions were managed across individual resource pages with no centralized view. The Subscription Center brings everything into one place, making it easier to manage notifications and understand who is receiving updates.
  
  

Custom Measures give you the flexibility to define your own calculations directly within Ternary, enabling you to transform raw cloud cost data into business-specific metrics without exporting to external tools.

What’s included

• Spreadsheet-style formula editor. Build formulas in a code editor with line numbers and syntax highlighting. Standard arithmetic operators (+, -, *, /) and parentheses are supported for order of operations.
• Guided sidebar. Available columns are grouped and displayed in a unified sidebar, with FOCUS standard columns highlighted. You can click “Insert” next to any column or function to add it directly to your formula.
• Example use case. Create metrics such as Effective Savings Rate using a formula like:
   (ListCost - EffectiveCost) / ListCost
• Metric management. Name your metric before saving, and manage created metrics from within the Reporting Engine. Saved metrics can be added as measures to reports.

Why it matters:

Custom Measures moves Ternary beyond cost visibility alone. By enabling users to define their own business logic directly on cloud billing data, teams can normalize costs, calculate savings rates, and begin layering efficiency metrics into their reporting workflows.

Because formulas prioritize FOCUS standard columns, users can write once and measure consistently across cloud providers, reinforcing multi-cloud compatibility.

This is the first step in a broader Custom Measures roadmap with additional capabilities planned in future releases

The Ternary Optimization Hub is a new multi-cloud experience that simplifies how teams surface and act on savings opportunities across AWS, Azure, and Google Cloud.

This centralized dashboard brings together usage, rate, and anomaly insights with interactive filters and KPIs to help you quickly identify high-impact savings across your environment.

Ternary already provides resource utilization recommendations by service and provider (for example, Compute → Azure Virtual Machines). With the Ternary Optimization Hub, these insights are now unified into two clear categories: idle recommendations and rightsizing recommendations. You can easily filter, refine, and drill into specific opportunities with greater clarity and control.

Why it matters

The Ternary Optimization Hub enables you to prioritize action more effectively, collaborate with better context, and unlock greater value from your multi-cloud spend.

Ternary now supports direct integration with Databricks, making it easy to ingest your Databricks usage and cost data into the Ternary Reporting Engine for unified reporting and analysis.

You can now view Databricks costs alongside your existing multi-cloud infrastructure and technology vendor spend, giving you a more complete view of your organization's usage and cost drivers.

Why it matters

This integration helps FinOps and engineering teams track Databricks consumption in the same place as cloud and SaaS data, reducing silos and improving visibility across environments.

How to get started

Visit our Databricks integration documentation for setup instructions and configuration guidance.

Ternary now supports both legacy and Multiprice Committed Use Discount (CUD) models for Google Cloud.

Google’s new Multiprice CUD billing model introduces a shift from credit-based savings to a net pricing consumption model, along with updates to BigQuery export schemas, SKU identifiers, and Marketplace Procurement API flows.

Key dates

• July 15, 2025: All new Google Cloud billing accounts default to the Multiprice CUD model. Existing accounts without active CUDs can opt in at any time.
• January 21, 2026: Google will automatically migrate all remaining accounts to the Multiprice model.

Why it matters

With this support, Ternary ensures continuity in reporting and optimization workflows as Google transitions to its new CUD model. Customers can continue tracking commitment utilization and cost efficiency without disruption, regardless of which model their billing account is using.

We’re excited to announce that you can now import your own time-series cost or billing data into Ternary using our new Bring Your Own Data capability.

This feature allows you to import external data sources such as SaaS costs, data center spend, internal finance system outputs, revenue data, and more, and analyze them alongside your existing cloud integrations in a single, unified reporting experience.

How it works

Data can be ingested using one of the following methods:

• A cloud storage bucket
• A BigQuery table path

Once connected, your data will appear within the same dashboards, filters, and reporting views used for your native cloud spend.

Why it matters

This integration gives teams a broader view of organizational spend by combining cloud and non-cloud cost data in one place. It removes the need for disconnected spreadsheets or tools and helps finance, engineering, and operations teams align around a shared source of truth.

How to get started

To enable this feature, please contact Ternary Customer Success at success@ternary.app. 

For comprehensive setup instructions and supported ingestion formats, view our documentation article.