Price check $0.000020–$0.200 per listed input unit 17 published rates · pay as you go

Vertex AI Embeddings Usage Pricing

Model Unit Rate
Online input 1,000 input tokens $0.00015
Batch input 1,000 input tokens $0.00012
  • Online and batch output requests have no charge.
Model Unit Rate
Online input 1,000 characters $0.000025
Batch input 1,000 characters $0.000020
  • Online and batch output requests have no charge.
Model Unit Rate
Online text input 1M tokens $0.200
Batch text input 1M tokens $0.100
Online image input image $0.00012
Batch image input image $0.000060
Online video input frame $0.00079
Batch video input frame $0.00040
Online audio input second $0.00016
Batch audio input second $0.000080
  • No charges for output tokens.
Model Unit Rate
Embeddings for Multimodal: Text 1,000 characters input $0.00020
Embeddings for Multimodal: Image image input $0.00010
Embeddings for Multimodal: Video Plus second of video $0.002
Embeddings for Multimodal: Video Standard second of video $0.001
Embeddings for Multimodal: Video Essential second of video $0.00050
  • Video Plus provides up to 15 embeddings per minute of video.
  • Video Standard provides up to 8 embeddings per minute of video.
  • Video Essential provides up to 4 embeddings per minute of video.
Pricing Alerts

Track Vertex AI Embeddings pricing

Get an email when Vertex AI Embeddings's pricing changes — plus the weekly SaaS Price Watch: verified price changes and deals across 3,000+ products. One-click unsubscribe.

View Vertex AI Embeddings API Pricing
Compare Vertex AI Embeddings with alternativesAdjust seats, lock a tier, add up to 2 more products side-by-side. Shareable URL.
Quick Answer
Last verified:
High confidence

Vertex AI Embeddings uses usage-based pricing from $0.000020 to $0.200 per listed input unit as of September 2026. Usage cost depends on the selected model and generation volume.

  • 17 documented hidden costs beyond list price
  • G2 rating: 4.3 out of 5 from 650 reviews (as of Aug 2026)
Last verified: | Sources: 1 pricing pages and reviews

How much does Vertex AI Embeddings cost?

Vertex AI Embeddings uses usage-based pricing from $0.000020–$0.200 per listed input unit. The published rate card contains 17 per-generation prices; there is no monthly subscription price for this API tier.

Vertex AI Embeddings Pricing Overview

Vertex AI Embeddings uses usage-based pricing from $0.000020–$0.200 per listed input unit across 17 published rates.

Vertex AI Embeddings with a no upfront commitment minimum commitment.

There are at least 17 documented hidden costs beyond Vertex AI Embeddings's list price, including implementation, training, and add-on fees.

This pricing was last verified in August 10, 2026 from 1 independent source.

View Vertex AI Embeddings API Pricing

Vertex AI Embeddings currently publishes four embedding offerings with 17 charged input rates. Units differ by offering: tokens, characters, images, video frames, audio seconds, and video seconds. The detailed rate card below preserves each vendor-listed unit.

How Vertex AI Embeddings Pricing Compares

Compare Vertex AI Embeddings pricing against top alternatives in Embedding APIs.

Jina Embeddings $0-$500 per million tokens Compare → Mixedbread $0-$20/month Compare → Nomic Embed Custom pricing Compare →

Compare Vertex AI Embeddings vs Alternatives

Before committing to Vertex AI Embeddings, compare pricing with these 3 alternatives in the same category.

VSJina Embeddings
Free

Developers evaluating Jina embeddings for non-commercial projects

Full comparison
VSMixedbread
Free

Hobbyists and evaluators trying Mixedbread

Full comparison
VSNomic Embed
Custom

Developers self-hosting embeddings

Full comparison

All Vertex AI Embeddings alternatives & migration guides

What Companies Actually Pay for Vertex AI Embeddings

Review scores
TrustRadius 8.6out of 10 (285)
G2 4.3out of 5 (650)
Third-party review aggregates, as of Aug 2026
Top pricing complaints
Steep Learning Curve and Complex User InterfaceComplex and Unpredictable Pricing/High Costs

How Vertex AI Embeddings Pricing Compares

Software Starting Price Top Price
Vertex AI Embeddings $0.000020 $0.200 per listed input unit
Jina Embeddings Free $500 per million tokens
Mixedbread Free $20/month
Nomic Embed Custom Custom
Voyage AI $0.02 per million tokens $0.18 per million tokens
OpenAI Embeddings $0.02 per million tokens $0.13 per million tokens

Detailed pricing comparisons:

Browse all Embedding APIs pricing →

17 Vertex AI Embeddings Hidden Costs Beyond the List Price

Beyond the listed price, Vertex AI Embeddings has at least 17 documented hidden costs that can significantly increase total cost of ownership.

Watch for 17 hidden costs
  • Idle Endpoints $2,642 per month
    critical 1 source
    industry "Vertex AI does not support automatic scale-to-zero for deployed models, meaning charges accrue continuously until an endpoint is explicitly undeployed."
  • Storage Costs
    medium 1 source
    industry "Standard Cloud Storage is priced at $0.020/GB-month, while SSD-backed storage costs $0.170/GB-month."
  • Data Transfer (Egress) Fees
    medium 1 source
    industry "Large batch prediction jobs or frequent model downloads can lead to unexpected charges."
  • Management Fees
    low 1 source
    industry "Management Fees: Vertex AI may add management fees on top of the underlying Compute Engine costs."
  • Data Storage $700-$800 per month
    medium 1 source
    industry "Standard Cloud Storage costs $0.020 per GB-month, while SSD-backed storage is $0.170 per GB-month"
  • Network Usage (Egress Fees) $0.12 per GB
    high 1 source
    industry "Large batch prediction jobs or frequent model downloads can lead to unexpected charges"
  • Reasoning Tokens
    medium 1 source
    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."
  • Long-Context Pricing
    medium 1 source
    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."
  • Logging and Storage
    low 1 source
    industry "Logging and Storage: Additional costs are associated with data storage fees, network usage charges, and logging, which are often not prominently advertised."
  • LiveAPI Session Re-billing
    medium 1 source
    industry "LiveAPI Session Re-billing: Charges can occur per turn for all tokens in the Session Context Window, including accumulated tokens from previous turns."
  • Vertex AI Vector Search $700-$800 per month
    medium 1 source
    industry "There are also indexing costs."
  • Custom Training and AutoML $2.93 per hour
    medium 1 source
    industry "AutoML training charges by compute hours (e.g., $10-$50/hour)."
  • text-embedding-005 Model Cost $0.10 per 1 million input tokens
    low 1 source
    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."
  • Associated Google Cloud Services $4.00 per 1,000 standard queries
    medium 1 source
    industry "Each of these services has its own pricing structure, contributing to the overall implementation cost."
  • Grounding Surcharges $14 per 1,000 queries (Gemini 3), $35 per 1,000 queries (Gemini 2), $2.50 per 1,000 prompts (customer data)
    medium 1 source
    industry "Grounding with customer data costs $2.50 per 1,000 prompts."
  • Data Transfer and Logging $122.88
    medium 1 source
    industry "Grounding with customer data costs $2.50 per 1,000 prompts."
  • Continuous Billing for Deployed Models
    high 1 source
    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 ..."
Tip

Ask your Vertex AI Embeddings sales rep about these costs upfront. Getting them in writing before signing can save you from surprise charges later.

Full hidden costs breakdown →

Intelligence sourced from 3 independent sources
industry TrustRadius Enterprise reviews G2 B2B reviews
Key claims include inline source attribution. Data verified against multiple independent sources. 17 source citations total.

Vertex AI Embeddings Contract Terms

Vertex AI Embeddings contracts do not auto-renew. Changes require advance notice. These terms are sourced from verified buyer experiences.

Contract Terms
Minimum Commitment no upfront commitment

Vertex AI Embeddings Pricing FAQ

01 How much does Gemini Embedding cost?

Gemini Embedding input costs $0.00015 per 1,000 tokens online and $0.00012 per 1,000 tokens in batch. Output has no charge.

02 How much do non-Gemini text embeddings cost?

Embeddings for Text, excluding Gemini Embedding, costs $0.000025 per 1,000 characters online and $0.00002 in batch. Output has no charge.

03 How is Gemini Embedding 2 priced?

Gemini Embedding 2 charges separately by modality. Online and batch text input cost $0.20 and $0.10 per 1M tokens; image input costs $0.00012 and $0.00006 per image; video costs $0.00079 and $0.0004 per frame; audio costs $0.00016 and $0.00008 per second.

04 What does multimodalembedding cost?

multimodalembedding costs $0.0002 per 1,000 text characters, $0.0001 per image, and $0.0020, $0.0010, or $0.0005 per video second for Plus, Standard, or Essential density.

Is this pricing incorrect? — we'll verify and update it.