Google DeepMind's open-weight embedding model for local search across text, code, images, audio, and video.
- Embedding price
- Open weights; self-hosted
- Input capacity
- 8,192 shared tokens across text and media
Resources
Top AI Embedding Models for Search & RAG
Embedding models turn text, code, images, audio, and documents into vectors for semantic search, recommendations, clustering, and RAG. Compare cost, context, dimensions, accepted inputs, retrieval controls, and hosting choices.
Showing 1–8 of 8 models
Google · Live
Gemini Embedding 2
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.
- Embedding price
- Text $0.20 / 1M tokens; multimodal rates vary
- Input capacity
- 8,192 text tokens; media has separate limits
OpenAI · Live
text-embedding-3-large
OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.
- Embedding price
- $0.13 / 1M tokens
- Input capacity
- 8,191 input tokens
Cohere · Live
Cohere Embed 4
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
- Embedding price
- Hosted unit price not published
- Input capacity
- 128K tokens
Voyage AI · Live
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.
- Embedding price
- $0.12 / 1M tokens after 200M free
- Input capacity
- 32K tokens
Voyage AI · Live
Voyage Context 4
Voyage AI's document-aware embedding model that automatically creates vectors for chunks while preserving information from the surrounding document.
- Embedding price
- $0.12 / 1M tokens after 200M free
- Input capacity
- 32K per internal pass; longer documents split automatically
Voyage AI · Live
Voyage Code 4
Voyage AI's specialist embedding model for finding relevant code from natural-language questions or other source-code context.
- Embedding price
- $0.12 / 1M tokens after 200M free
- Input capacity
- 32K tokens
Mistral AI · Live
Mistral Embed
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.
- Embedding price
- $0.10 / 1M tokens
- Input capacity
- 8K tokens
What to compare
- Embedding price
- Current provider price per million input tokens or the closest published billing unit.
- Input capacity
- Maximum content accepted in one embedding input, using the provider's documented token basis.
- Vector dimensions
- Supported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
How to use this library
Compare the job, not the hype.
A curated cross-category set of frontier, specialist, and category-defining models with practical API information for real product decisions.
Cody does not run a universal quality leaderboard. Provider claims are labeled, pricing excludes taxes and optional tools, and production buyers should verify the live provider terms before choosing a model.
- 01
Use first-party documentation for technical limits, lifecycle, pricing, regional access, and data policies whenever it exists.
- 02
Compare models only inside the same category and retain each provider's measurement basis.
- 03
Show Not published when a provider has not published a comparable fact instead of estimating it.
- 04
Treat prices and availability as dated snapshots and link every page to live provider documentation.
Speed keeps its units
Voice latency, text throughput, video render time, and world-model frame rate are not interchangeable.
Unknown stays unknown
A missing release date, country list, or latency number is labeled as unpublished instead of estimated.
Every fact has a date
Model pages link to the underlying source and show when pricing, access, and policies were last checked.
Put the model to work
Pick the model, then give it a better brief.
Use Cody's expanded prompt playbooks and curated agent skills to turn a model choice into a repeatable workflow.