> ## Documentation Index > Fetch the complete documentation index at: https://docs.vortexiq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Google Gemini on Vortex IQ > Monitor Google Gemini health, cost and reliability signals, and catch incidents and runaway spend early. Monitor Google Gemini health, cost and reliability signals, and catch incidents and runaway spend early. No changes are made without the configured approval policy. Read-only operations do not modify the connected system; schedules, access scopes, API usage and data handling remain governed by Vortex IQ controls. [Connect or manage this source](https://app.vortexiq.ai/workbench/settings/sources) ยท [How connecting works](/integrations/connector-catalogue) | **14** | **3** | **Build your own** | **17** | **1** | | ------------------- | ---------------- | ------------------ | ---------------- | -------------- | | performance signals | automated checks | automated fixes | proven workflows | API operations | ## Monitor performance 14 performance signals. Signals with an alert band can raise Nerve Centre alerts; every signal supports a merchant-configured watcher. | Signal | Outcome | Alert behaviour | What it tracks | | --------------------------------- | ----------------------- | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Gemini API Health** | Catalogue quality | Alert band 90 / 70 | Composite 0-100: 60 for the API being reachable and the key authenticating on /v1beta/models, plus up to 40 for a non-empty model catalogue. No spend input (spend is not | | **Models Available** | Control risk and change | Watch only | Count of entries in GET /v1beta/models the key can see. Renders with any valid Gemini API key. | | **Avg Input Token Limit** | Catalogue quality | Watch only | Mean of inputTokenLimit over models that report one, from /v1beta/models. | | **Gemini Spend (30d)** | Control risk and change | Alert band 10 / 50 | Gemini spend is NOT exposed by generativelanguage.googleapis.com; it is billed through Google Cloud. Degrades with reason billing\_via\_gcp unless a linked GCP billing expo | | **Gemini Usage Trend (30d)** | Control risk and change | Alert band 0 / -50 | Gemini request/token usage is NOT exposed by the Gemini API (no usage endpoint). Degrades with reason billing\_via\_gcp unless a linked GCP billing export supplies it. Neve | | **Latest Model** | Catalogue quality | Watch only | displayName (or name) of the model with the highest numeric leading version parsed from the version field across /v1beta/models. | | **Max Context Window** | Catalogue quality | Watch only | Maximum inputTokenLimit across all models in /v1beta/models (largest input context available). | | **Max Output Tokens** | Catalogue quality | Watch only | Maximum outputTokenLimit across all models in /v1beta/models. | | **Model Families** | Catalogue quality | Watch only | Distinct model families from /v1beta/models, grouping name by its family stem (e.g. gemini-2.5, gemini-2.0, gemini-1.5, text-embedding). Counted per family. | | **Preview / Experimental Models** | Catalogue quality | Watch only | Count of models whose name or version contains 'preview' or 'exp' from /v1beta/models (not yet GA). | | **Vision-Capable Models** | Catalogue quality | Watch only | Count of models whose description or displayName matches a multimodal keyword (vision, image, audio, multimodal) from /v1beta/models. Heuristic: Gemini exposes no explici | | **countTokens Models** | Customer experience | Watch only | Count of models whose supportedGenerationMethods includes countTokens, from /v1beta/models. | | **embedContent Models** | Customer experience | Watch only | Count of models whose supportedGenerationMethods includes embedContent, from /v1beta/models. | | **generateContent Models** | Customer experience | Watch only | Count of models whose supportedGenerationMethods includes generateContent, from /v1beta/models. | ## Audit risks and opportunities A fix status appears only where the action, inputs, approval, verification and recovery controls are mapped. Candidate remediations are never executable. | Check | Severity | Outcome | Why it matters | Fix status | | ------------------------------------------------------------------ | -------- | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- | | **API key invalid, expired or lacking the scopes the cards need** | high | Control risk and change | Once this credential fails, VortexIQ stops seeing usage, cost and health data from this platform entirely, and every finding here that depends on it goes stale from that moment, silently, un | Report only | | **Spend up more than 50% vs the prior period** | high | Run operations | Spend on this platform rose more than 50% versus the prior period. A jump this size is either a deliberate scale-up worth confirming was intentional, or an unbounded process, a stuck job, a | Report only | | **Usage dropped more than 50% vs the prior period (silent stall)** | medium | Control risk and change | Usage halving against the prior period is the earliest sign of a silent stall: a broken schedule, an expired credential, or a team that quietly stopped. | Report only | ### Build your own automated fixes 3 checks report findings on Google Gemini today. Turn any finding into an automated fix with a Vortex IQ workflow: **13,885 read and write operations across 229 connectors** are available as building blocks, with approval, verification and rollback on every change. ## Automate approved work Vortex IQ is integrated with **1 read** and **0 write** operations across v1betamodels on Google Gemini. Combine them with anything from the **13,885 operations across 229 connectors** to automate the work in your own words. Changes follow the merchant's configured approval policy: the target, proposed change, affected records, risk, reversibility and verification plan are shown before execution. Read-only operations do not modify the connected system. [Create a workflow](https://app.vortexiq.ai/workbench/flows/create?connector=gemini) | Resource | Read operations | Write operations | | ------------ | --------------- | ---------------- | | v1betamodels | 1 | 0 | Signed-in users see the full catalogue in the workflow builder, filtered to the sources they have connected. ### Proven workflow templates (17) | Workflow | For | Also available on | Tested alongside | What it does | | --------------------------------- | ----------------------- | ----------------------------------------------------------------------------------------------------- | --------------------------------------------------- | ------------------------------------------------------------------------------------------ | | **Brand Voice Compliance Review** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | flags off-brand, unsupported or inconsistent product claims and proposes corrections. | | **Catalogue Completeness Guard** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | scores required fields by category and routes the highest-revenue gaps first. | | **Duplicate Copy Resolver** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | detects reused descriptions and produces differentiated drafts from verified attributes. | | **New SKU Content Factory** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | turns approved source data into complete draft PDPs with a human review queue. | | **PDP Enrichment Queue** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | finds thin product pages, generates on-brand copy, and batches changes for approval. | | **Product Claim Evidence Check** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | identifies unsubstantiated claims and requires evidence or removal before publish. | | **Seasonal Content Refresh** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | identifies stale seasonal language and prepares date-safe updates with expiry/rollback. | | **Supplier Copy Normaliser** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | converts inconsistent feeds into house style while preserving factual specifications. | | **Variant Consistency Sweep** | Product content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, Anthropic | reconciles names, options, specifications and copy across product families. | | **Brief Approval Router** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | sends briefs to the correct legal, SEO, product and brand approvers based on content type. | | **Brief-to-Draft Pipeline** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | produces evidence-backed article drafts with sources, brand rules and approval status. | | **Campaign Asset Repurposer** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | turns an approved core message into channel-specific drafts without auto-publishing. | | **Content Calendar Builder** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | creates a channel-ready editorial calendar from launches, seasonality and search demand. | | **Content Freshness Watch** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | finds decaying or outdated pages, explains why they matter and opens refresh tasks. | | **Editorial QA Gate** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | checks links, claims, tone, formatting, metadata and calls to action before approval. | | **Evergreen Refresh Queue** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | schedules evidence and date checks for high-value guides. | | **Launch Story Pack** | Content manager | OpenAI, DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude) | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic | creates coordinated blog, email and social drafts from verified product information. | 3 further designed workflows are in validation and become activatable only once proven against a live account. Prototypes are never presented as ready. *** *Generated from the connector capability graph. Counts reflect the servable registry after alias normalisation and de-duplication, and refresh automatically when the registry changes.*