Quick Answer
Last verified:
High confidence

Vertex AI Embeddings offers usage-based pricing from $0.000020–$0.200 per listed input unit as of September 2026. Plans: Gemini Embedding (usage-based), Embeddings for Text (Excluding Gemini Embedding) (usage-based), Gemini Embedding 2 (Unified Multimodal) (usage-based), and multimodalembedding (usage-based). Usage cost depends on the selected model and generation volume.

Use the interactive pricing calculator to estimate your exact cost based on team size and requirements.

  • Free tier: No free tier available

Vertex AI Embeddings offers 4 pricing tiers: Gemini Embedding, Embeddings for Text (Excluding Gemini Embedding), Gemini Embedding 2 (Unified Multimodal), multimodalembedding. Paid plans include Gemini Embedding (usage-based), Embeddings for Text (Excluding Gemini Embedding) (usage-based), Gemini Embedding 2 (Unified Multimodal) (usage-based). The Embeddings for Text (Excluding Gemini Embedding) plan is character-priced text embedding workloads.

Last verified: | Sources: 1 pricing pages and reviews
Know Before You Buy — See Vertex AI Embeddings Plans

Vertex AI Embeddings lists $0.00002-$0.2/listed input unit, but hidden costs like implementation and support add to the total as of September 2026. Key hidden costs: idle endpoints, storage costs, data transfer (egress) fees. Verified from 1 sources by CostBench.

Hidden Costs Breakdown

1

Idle Endpoints

critical overage

Deployed models not actively handling requests incur continuous charges until explicitly undeployed, as Vertex AI does not support automatic scale-to-zero.

industry

Vertex AI does not support automatic scale-to-zero for deployed models, meaning charges accrue continuously until an endpoint is explicitly undeployed.

2

Storage Costs

medium addon

Storing models in Vertex AI Model Registry, datasets in Cloud Storage, and vector indexes in Vector Search all incur data storage fees.

industry

Standard Cloud Storage is priced at $0.020/GB-month, while SSD-backed storage costs $0.170/GB-month.

3

Data Transfer (Egress) Fees

medium overage

Moving data out of Google Cloud incurs egress fees, with large batch prediction jobs or frequent model downloads potentially leading to unexpected charges.

industry

Large batch prediction jobs or frequent model downloads can lead to unexpected charges.

4

Management Fees

low addon

Vertex AI may add management fees on top of the underlying Compute Engine costs.

industry

Management Fees: Vertex AI may add management fees on top of the underlying Compute Engine costs.

5

Data Storage

medium addon

Storing models in Vertex AI Model Registry, datasets in Cloud Storage, and vector indexes in Vertex AI Vector Search all incur data storage fees.

industry

Standard Cloud Storage costs $0.020 per GB-month, while SSD-backed storage is $0.170 per GB-month

6

Network Usage (Egress Fees)

high overage

Moving data out of Google Cloud incurs egress fees, which can lead to unexpected charges for large batch prediction jobs or frequent model downloads.

industry

Large batch prediction jobs or frequent model downloads can lead to unexpected charges

7

Reasoning Tokens

medium overage

For generative AI models like Gemini, 'thinking tokens' are billed as output, which can significantly inflate the effective cost of a request.

industry

Reasoning Tokens: For generative AI models like Gemini, "thinking tokens" are billed as output, which can significantly inflate the effective cost of a request, potentially doubling or tripling it.

8

Long-Context Pricing

medium overage

Prompts exceeding a certain token count can trigger higher rates, effectively doubling the cost for larger contexts.

industry

Long-Context Pricing: Prompts exceeding a certain token count (e.g., roughly 200,000 tokens for Gemini 2.5 Pro) can trigger higher rates, effectively doubling the cost for larger contexts.

9

Logging and Storage

low addon

Additional costs are associated with data storage fees, network usage charges, and logging, which are often not prominently advertised.

industry

Logging and Storage: Additional costs are associated with data storage fees, network usage charges, and logging, which are often not prominently advertised.

10

LiveAPI Session Re-billing

medium overage

Charges can occur per turn for all tokens in the Session Context Window, including accumulated tokens from previous turns.

industry

LiveAPI Session Re-billing: Charges can occur per turn for all tokens in the Session Context Window, including accumulated tokens from previous turns.

11

Vertex AI Vector Search

medium implementation

This infrastructure-based service bills per node-hour for hosting the vector index, with costs depending on machine type, index size, and replica count, and also includes indexing costs.

industry

There are also indexing costs.

12

Custom Training and AutoML

medium training

Training jobs are billed per node-hour based on machine type and attached accelerators, while AutoML training charges by compute hours.

industry

AutoML training charges by compute hours (e.g., $10-$50/hour).

13

text-embedding-005 Model Cost

low implementation

The text-embedding-005 model costs $0.10 per 1 million input tokens.

industry

Reasoning Tokens: For generative AI models like Gemini, "thinking tokens" used for internal reasoning are billed as output tokens, which can inflate the effective cost of a request by five to tenfold beyond the visible response.

14

Associated Google Cloud Services

medium implementation

Using Vertex AI Embeddings often involves other GCP services like Cloud Storage, Compute Engine, or Vertex AI Vector Search, each with its own pricing structure.

industry

Each of these services has its own pricing structure, contributing to the overall implementation cost.

15

Grounding Surcharges

medium addon

Using grounding features, such as Google Search grounding or grounding with customer data, adds separate usage-based charges.

industry

Grounding with customer data costs $2.50 per 1,000 prompts.

16

Data Transfer and Logging

medium addon

Standard Google Cloud costs for data storage, network usage (egress), and logging services are additive to Vertex AI Embeddings costs.

industry

Grounding with customer data costs $2.50 per 1,000 prompts.

17

Continuous Billing for Deployed Models

high overage

Other deployed models and resources, such as Vertex AI Workbench instances and Vector Search nodes, bill continuously even with zero traffic.

industry

Continuous Billing for Deployed Models: Similar to idle endpoints, other deployed models and resources, such as Vertex AI Workbench instances and Vector Search nodes, bill continuously even with zero traffic, leading to unexpected expenses if not properly managed and scaled to zero.

Frequently Asked Questions

01 What hidden costs should I budget for with Vertex AI Embeddings?

Beyond the license fee, budget for: Idle Endpoints ($2,642 per month); Data Storage ($700-$800 per month); Network Usage (Egress Fees) ($0.12 per GB); Vertex AI Vector Search ($700-$800 per month); Custom Training and AutoML ($2.93 per hour); text-embedding-005 Model Cost ($0.10 per 1 million input tokens); Associated Google Cloud Services ($4.00 per 1,000 standard queries); Grounding Surcharges ($14 per 1,000 queries (Gemini 3), $35 per 1,000 queries (Gemini 2), $2.50 per 1,000 prompts (customer data)); Data Transfer and Logging ($122.88). Exact totals depend on your deployment size and negotiated terms.

02 Does Vertex AI Embeddings charge for implementation?

Vertex AI Embeddings implementation is not included in the license cost. This infrastructure-based service bills per node-hour for hosting the vector index, with costs depending on machine type, index size, and replica count, and also includes indexing costs.. Estimated impact: $700-$800 per month.

03 How much does Vertex AI Embeddings support cost?

Premium support pricing for Vertex AI Embeddings depends on your tier and contract terms. See the sourced cost breakdown above for any verified figures we have.

04 Are there overage or storage costs with Vertex AI Embeddings?

Deployed models not actively handling requests incur continuous charges until explicitly undeployed, as Vertex AI does not support automatic scale-to-zero.. Estimated impact: $2,642 per month.

05 What add-ons cost extra with Vertex AI Embeddings?

Add-on pricing for Vertex AI Embeddings varies by feature. The sourced cost breakdown above lists any verified add-on costs we have.

Now You Know the Real Cost — See Vertex AI Embeddings Plans

Check current Vertex AI Embeddings pricing

Prices and terms change; verify against the live pricing page.

See Vertex AI Embeddings Pricing