Price checkPer per million tokens
text-embedding-004 (Standard)Customtext-embedding-004 (Batch)CustomGemini Embedding (gemini-embedding-001)Custom
See all 4 plans

All Vertex AI Embeddings Plans & Pricing

Plan Monthly Annual Best For
View all features by plan (compare side-by-side)

text-embedding-004 (Standard)

  • $0.000025 per 1,000 characters (online requests)
  • 768-dimension text embeddings
  • Supports task types: RETRIEVAL_QUERY, SEMANTIC_SIMILARITY, CLASSIFICATION
  • Configurable output dimensionality

text-embedding-004 (Batch)

  • $0.00002 per 1,000 characters (batch requests)
  • 20% discount vs online pricing
  • Asynchronous processing, results within hours
  • Ideal for bulk document indexing workloads

Gemini Embedding (gemini-embedding-001)

  • $0.15 per 1 million input tokens (standard API)
  • Batch API at $0.075 per 1 million tokens (50% off)
  • Up to 2,048 input tokens per request
  • 3,072 output dimensions (configurable)

Gemini Embedding 2 (multimodal)

  • $0.25 per 1 million text/image/video tokens (standard API)
  • $0.50 per 1 million audio tokens (standard API)
  • Batch API at $0.125 per 1 million tokens (50% off)
  • Supports text + image inputs in a single embedding space
  • Public Preview as of March 10, 2026
See Vertex AI Embeddings Plans
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:
Estimate

Vertex AI Embeddings costs $0.07 to $0.25 per per million tokens as of July 2026, with 4 plans available. Pricing depends on your chosen tier, contract length, and negotiated discounts.

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: text-embedding-004 (Standard), text-embedding-004 (Batch), Gemini Embedding (gemini-embedding-001), Gemini Embedding 2 (multimodal).

Compared to other embedding apis software, Vertex AI Embeddings is positioned at the budget-friendly price point.

  • 17 documented hidden costs beyond list price
  • Contracts auto-renew — within the first 30 days for some annual plans purchased through partners
Last verified:

How much does Vertex AI Embeddings cost?

Vertex AI Embeddings pricing ranges from $0.07 to $0.25/per million tokens across 4 plans. Plans include text-embedding-004 (Standard) (custom pricing), text-embedding-004 (Batch) (custom pricing), Gemini Embedding (gemini-embedding-001) (custom pricing), Gemini Embedding 2 (multimodal) (custom pricing).

Vertex AI Embeddings Pricing Overview

Vertex AI Embeddings has 4 pricing plans ranging from $0.07 to $0.25/per million tokens. The text-embedding-004 (Standard) plan requires contacting sales for a custom quote. The text-embedding-004 (Batch) plan requires contacting sales for a custom quote. The Gemini Embedding (gemini-embedding-001) plan requires contacting sales for a custom quote. The Gemini Embedding 2 (multimodal) plan requires contacting sales for a custom quote.

Vertex AI Embeddings contracts auto-renew, with a no upfront commitment for general usage-based pricing 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 May 30, 2026.

See Vertex AI Embeddings Plans

Vertex AI Embeddings is Google Cloud's managed embedding API, providing access to multiple models for converting text and images into dense vector representations. The API supports semantic search, retrieval-augmented generation (RAG), classification, and clustering workloads. Current offerings include text-embedding-004 (character-priced, $0.000025/1K chars), Gemini Embedding (token-priced at $0.15/M tokens), and Gemini Embedding 2 — Google's first multimodal embedding model at $0.25/M tokens for text/image/video (Public Preview since March 10, 2026). All models offer a 50% batch API discount for asynchronous workloads.

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
Third-party review aggregates, as of Jul 2026
Top pricing complaints
Complex and Unpredictable PricingSteep Learning Curve and ComplexityDocumentation IssuesLimited Transparency in Resource Usage and Billing

How Vertex AI Embeddings Pricing Compares

Software Starting Price Top Price
Vertex AI Embeddings $0.075/per million tokens $0.25/per million tokens
Jina Embeddings Free $500/per million tokens
Mixedbread Free $20/month
Nomic Embed Custom Custom
Voyage AI Free $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 up to $7,889
    high 1 source
    industry "For example, a forgotten A100 endpoint can generate an invoice of approximately $2,642 per month, or even up to $7,889 for a single forgotten endpoint."
  • Data Storage Fees $0.170/GB-month
    medium 1 source
    industry "Standard Cloud Storage costs around $0.020/GB-month, while SSD-backed storage is about $0.170/GB-month."
  • Network Usage Charges (Egress) up to $0.23/GB
    medium 1 source
    industry "Large batch prediction jobs or frequent model downloads can lead to unexpected charges."
  • Long Conversation Context
    high 1 source
    industry "Long Conversation Context: For generative AI models, every turn in a long conversation resends prior context as input tokens, leading to significantly higher billing than a simple per-call rate might suggest."
  • Associated Google Cloud Services $800 per month
    medium 1 source
    industry "Standard Cloud Storage costs around $0.020/GB-month, while SSD-backed storage is about $0.170/GB-month."
  • Management Fees
    low 1 source
    industry "Management Fees: Vertex AI may add management fees on top of underlying Compute Engine costs."
  • Training and Prediction Compute $2.93 per hour
    medium 1 source
    industry "Large batch prediction jobs or frequent model downloads can lead to unexpected charges."
  • Compute Resources for Training $2.50-$4.00 per hour
    medium 1 source
    industry "Vertex AI Vector Search (formerly Matching Engine) pricing is infrastructure-based, billed per node-hour, with a moderately sized index on three replicas costing roughly $700-$800/month."
  • Prediction Request Costs $100-$10,000 per 1 million predictions
    high 1 source
    industry "At high volumes, 1 million predictions could range from $100 to $10,000."
  • Token Consumption (Gemini 2.5 Pro) $1.25-$10.00 per million tokens
    high 1 source
    industry "For instance, Gemini 2.5 Pro costs $1.25 per million input tokens (for contexts ≤200K) and $10.00 per million output tokens."
  • Vertex AI Vector Search Infrastructure $700-$800/month
    high 1 source
    industry "Vertex AI Vector Search (formerly Matching Engine) pricing is infrastructure-based, billed per node-hour, with a moderately sized index on three replicas costing roughly $700-$800/month."
  • Vector Search Index Build/Update $0.45-$3.00 per GiB
    medium 1 source
    industry "Index build/update (batch) costs $3.00 per GiB processed, and streaming updates cost $0.45 per GiB inserted."
  • Logging and Monitoring
    low 1 source
    industry "Logging and Monitoring: While not explicitly detailed with figures, these are common operational costs in cloud environments."
  • Compute Node Costs for Vector Search
    high 1 source
    industry "The cost varies based on machine type, index size, and replica count."
  • Custom Model Training/Fine-tuning $21.25/hour per custom training node
    high 1 source
    industry "Model Training and Prediction Costs: While the Embedding APIs generate embeddings from pre-trained models, if buyers opt for custom model training or fine-tuning of embedding models, these activities incur separate charges based on compute resourc..."
  • Vertex AI Pipeline Costs $0.03 per run
    low 1 source
    industry "Pipeline Costs: Orchestrating embedding generation and related tasks through Vertex AI Pipelines incurs a charge per run, for example, $0.03 per run, in addition to associated training/storage compute charges."
  • Generative AI Support Charges
    medium 1 source
    industry "Network Usage Charges: Transferring data to and from Vertex AI Embeddings, and between other Google Cloud services, will incur network egress fees."
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 1 independent sources
industry
Key claims include inline source attribution. Data verified against multiple independent sources. 19 source citations total.

Vertex AI Embeddings Contract Terms

Vertex AI Embeddings contracts auto-renew. Changes require within the first 30 days for some annual plans purchased through partners. These terms are sourced from verified buyer experiences.

Contract Terms
Auto-Renewal Yes
Cancellation Notice within the first 30 days for some annual plans purchased through partners
Minimum Commitment no upfront commitment for general usage-based pricing
Based on 1 verified source

How to Negotiate Vertex AI Embeddings Pricing

Vertex AI Embeddings contracts are negotiable. These 1 tactics are sourced from real buyer experiences and procurement specialists.

Negotiation Playbook 1 tactics
Leverage PPAs and CUDs high success

For larger enterprise agreements, buyers can utilize Private Pricing Agreements (PPAs) and Committed Use Discounts (CUDs) to introduce specific terms.

industry analysis
High success Medium Low / difficult

Full negotiation guide →

Vertex AI Embeddings Pricing FAQ

01 How much do Vertex AI Embeddings cost?

Vertex AI Embeddings pricing depends on the model. The older text-embedding-004 model charges $0.000025 per 1,000 characters for online requests and $0.00002 per 1,000 characters for batch. The newer Gemini Embedding (gemini-embedding-001) costs $0.15 per million input tokens, and Gemini Embedding 2 (multimodal, Public Preview) costs $0.25 per million text/image/video tokens ($0.50/M for audio). All models offer a 50% batch discount.

02 Does Vertex AI Embeddings have a free tier?

Vertex AI Embeddings does not have a dedicated free tier, but new Google Cloud accounts receive a $300 free credit that can be applied to embedding API usage. After credits are exhausted, all requests are billed at the standard per-character or per-token rates.

03 What is the difference between text-embedding-004 and Gemini Embedding on Vertex AI?

text-embedding-004 is the older model priced per character and supports up to 2,048 input tokens with 768-dimension outputs. Gemini Embedding (gemini-embedding-001) is token-priced, supports up to 2,048 tokens, and outputs up to 3,072 dimensions, offering improved benchmark performance. Gemini Embedding 2 additionally supports multimodal inputs (text + images) in a unified embedding space.

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