Embedding Models Compared
The 2026 embedding landscape has 4 commercial providers, a tier of free open-weight models that match commercial quality, and Matryoshka compression that cuts storage 92% with minimal recall loss. This article covers how to choose, evaluate, and migrate embedding models for production RAG.
Quick Reference
- →text-embedding-3-small / voyage-4-lite: $0.02/1M tokens — best default for English RAG
- →Voyage 4 family (Jan 2026): shared embedding space across tiers, voyage-4-nano is free + open-weight
- →Cohere Embed v4: multimodal (text + images), 1024 dims, $0.12/1M tokens
- →Google Gemini Embedding 2: 5 input types (text, image, video, audio, docs), tops MTEB v1 English
- →Open-source leaders (2026): Jina v5, BGE-M3, Qwen3-Embedding-8B — competitive with commercial on benchmarks
- →Matryoshka: cut 3072 → 256 dims for 92% storage savings, ~6% recall loss — measure on your data
- →MTEB v2 scores ≠ MTEB v1 — never compare numbers across benchmark versions
The 2026 Embedding Landscape
In 2024, the embedding model choice was: OpenAI, Cohere, or self-host BGE. In 2026, there are three distinct tiers, four major commercial providers, and open-weight models that trade blows with commercial APIs on benchmarks. The most important development: multimodal embeddings are production-ready. Cohere Embed v4, Google Gemini Embedding 2, and Voyage multimodal-3.5 all handle mixed text-and-image content in a single embedding space. If your RAG corpus contains PDFs with figures, product images, or screenshots, single-model multimodal retrieval is now a realistic option.
embedding provider tiers · 3 deployment modes · April 2026
| Model | Dims | MTEB v1 (Eng) | Price/1M | Multimodal | Context |
|---|---|---|---|---|---|
| text-embedding-3-small | 1536 | 62.3 | $0.02 | No | 8K |
| voyage-4-lite | 1024 | ~63 | $0.02 | No | 32K |
| voyage-4 | 1024 | ~68 | $0.06 | No | 32K |
| Cohere Embed v4 | 1024 | — | $0.12 | Text + image | 128K |
| Gemini Embedding 2 | 3072 | 68.32 | $0.20 (free preview) | 5 types | 8K |
| text-embedding-3-large | 3072 | 64.6 | $0.13 | No | 8K |
MTEB v2 launched in 2026 with a different task mix and scoring methodology. A model scoring 72 on MTEB v2 cannot be compared to a model scoring 68 on MTEB v1. Always check which benchmark version a score refers to before using it to choose a model.