All models
Google
Gemini Embedding 2
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.
Plain-English overview
What Gemini Embedding 2 actually is
Gemini Embedding 2 lets a search system compare meaning across several media types instead of maintaining a separate vector model for every format. A text query can retrieve a relevant image, video segment, audio clip, PDF, or passage when they are embedded into the same space.
Developers can choose a smaller output size to reduce database storage or keep the full 3,072 dimensions when retrieval quality matters more. Task types help distinguish search queries from indexed documents, classification, clustering, and other workloads.
Good fit for
- Multimodal search across text and media
- RAG over PDFs, images, audio, and video
- Teams already building with the Gemini API
Category comparison
The facts that matter for embeddings models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Embedding price
- Text $0.20 / 1M tokens; multimodal rates varyCurrent provider price per million input tokens or the closest published billing unit.
- Input capacity
- 8,192 text tokens; media has separate limitsMaximum content accepted in one embedding input, using the provider's documented token basis.
- Vector dimensions
- 128–3,072; 768, 1,536, or 3,072 recommendedSupported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
- Accepted inputs
- Text, image, video, audio, PDFText, code, image, audio, video, PDF, or document-aware input supported by the endpoint.
- Retrieval controls
- Task types, output dimension, title for retrieval documentsQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval.
- Where it runs
- Gemini Developer API and Google AI StudioDirect API, cloud marketplace, private deployment, or self-hosted route documented by the provider.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Assumes 600 tokens per page, processed separately. Actual token counts vary. This covers embedding only, not storage, search, or generated answers.
Gemini Embedding 2
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
- Input tokens
- $0.20 per 1M tokens
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Gemini Embedding 2
Availability
Regions and access stage
Generally available through the Gemini Developer API for text and multimodal embeddings.
Gemini API access follows Google's supported-country list, project billing state, and age requirements.
Check live availabilityData and training
The route matters.
Google's Gemini API terms distinguish unpaid and paid services: content from unpaid services may be used to improve products, while paid-service prompts and responses are not used to improve products.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Gemini Embedding 2 FAQ
What is Gemini Embedding 2?
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space. Gemini Embedding 2 lets a search system compare meaning across several media types instead of maintaining a separate vector model for every format. A text query can retrieve a relevant image, video segment, audio clip, PDF, or passage when they are embedded into the same space.
When was Gemini Embedding 2 released?
Gemini Embedding 2 was released on April 22, 2026 according to the cited provider materials.
Where can I access Gemini Embedding 2?
Generally available through the Gemini Developer API for text and multimodal embeddings. The access routes listed in this guide are Google and Google AI Studio.
How much does Gemini Embedding 2 cost?
Text $0.20 / 1M tokens. Paid standard pricing also lists image, audio, and video input separately. Batch rates are half the standard paid rates; the free tier has different data-use terms.
Where is Gemini Embedding 2 available?
Generally available through the Gemini Developer API for text and multimodal embeddings. Gemini API access follows Google's supported-country list, project billing state, and age requirements.
Is my Gemini Embedding 2 API data used for training?
Google's Gemini API terms distinguish unpaid and paid services: content from unpaid services may be used to improve products, while paid-service prompts and responses are not used to improve products. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Embed$0.10
Mistral AI
- Voyage 4 Large$0.12
Voyage AI
- Voyage Context 4$0.12
Voyage AI
- Voyage Code 4$0.12
Voyage AI
- text-embedding-3-large$0.13
OpenAI
- Gemini Embedding 2$0.20
Google
This model
Related comparisons
Head-to-head comparisons
Gemini Embedding 2 vs text-embedding-3-large
OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.
Open full comparisonGemini Embedding 2 vs Cohere Embed 4
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
Open full comparisonGemini Embedding 2 vs Voyage 4 Large
Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space.
Open full comparisonGemini Embedding 2 vs Voyage Context 4
Voyage AI's document-aware embedding model that automatically creates vectors for chunks while preserving information from the surrounding document.
Open full comparisonGemini Embedding 2 vs Voyage Code 4
Voyage AI's specialist embedding model for finding relevant code from natural-language questions or other source-code context.
Open full comparisonGemini Embedding 2 vs Mistral Embed
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.
Open full comparison
