--- title: "Embeddings" description: "Model selection, Matryoshka truncation, and multimodal embeddings - condensed current practice" url: "https://agentsurface.dev/docs/agent-retrieval/embeddings" index: https://agentsurface.dev/llms.txt lastVerified: 2026-10-29 lastModified: 2026-10-29T11:29:43.000Z --- Embeddings are dense vectors that represent text (or images, audio, video) semantically, powering nearest-neighbor search. Choose based on cost, latency, privacy boundary, and corpus shape, then validate on your own data. ## Model selection [#model-selection] | Model | Dims | Cost (per 1M tokens) | Notes | | --------------------------------------------- | ----------------------------------------------------------- | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- | | OpenAI `text-embedding-3-large` | 3,072 (Matryoshka) | $0.13 | Highest-quality OpenAI embedding. Check the file-search tool docs before assuming you can choose its embedding model or dimensions. | | OpenAI `text-embedding-3-small` | 1,536 (Matryoshka) | $0.02 | Cheaper, nearly comparable quality for many domains. | | Voyage 4 Large | 1,024 default (256, 512, 2,048 optional) | $0.12 | Highest-quality Voyage retrieval embedding. | | Voyage 4 | 1,024 default (256, 512, 2,048 optional) | $0.06 | Balanced Voyage embedding. | | Voyage 4 Lite | 1,024 default (256, 512, 2,048 optional) | $0.02 | Lower cost and latency; shares a vector space with the rest of the Voyage 4 family. | | Cohere Embed 5 Pro `embed-v5.0-pro` | 2,048 default (256, 512, 768, 1,024, 1,536 optional) | $0.12 text | Launched 2026-09-30. Text and image, 128K-token context. Use Cohere's pricing page for image units. | | Cohere Embed 5 Fast `embed-v5.0-fast` | 2,048 default (256, 512, 768, 1,024, 1,536 optional) | $0.08 text | Launched 2026-09-30. Same inputs and context as Pro at lower cost. | | Cohere Embed v4 `embed-v4.0` | 1,536 (Matryoshka) | $0.12 text / $0.47 image | Previous Cohere generation; still available. Multimodal (text + image), 128K-token context. | | Gemini Embedding 2 `gemini-embedding-2` | 3,072 default (128-3,072; 768, 1,536 and 3,072 recommended) | Verify current pricing | Multimodal: text, image, video, audio and documents. Check modality support before relying on it. | | Open-source (BGE-M3, E5-Mistral, Nomic Embed) | Varies | Free (self-hosted) | Competitive on MTEB for many domains; you own infrastructure, latency, and updates. | Voyage's 4-generation models share one vector space, so you can index with a larger model and query with a smaller one without re-indexing. Cohere's Embed 5 Pro and Fast also share an embedding space (per the launch post). Confirm current pricing and model availability before committing - this table is a snapshot. ## Matryoshka truncation [#matryoshka-truncation] Matryoshka-trained models (OpenAI 3-large/small, Voyage 4 family, Cohere Embed v4 and 5, Gemini Embedding 2) let you truncate both stored and query vectors to a smaller dimension without re-embedding the corpus. Stored and query vectors must use the same dimension - a nearest-neighbour comparison across mismatched dimensions doesn't work: ```typescript const stored = await openai.embeddings.create({ model: "text-embedding-3-large", input: text, dimensions: 256, // stored at the truncated dimension }); const query = await openai.embeddings.create({ model: "text-embedding-3-large", input: userQuery, dimensions: 256, // must match the stored dimension }); ``` Truncating to 256–512 dimensions often costs some accuracy versus the full vector, in exchange for faster queries and lower storage. A loss of roughly 2–5% is a rough rule of thumb, not a published benchmark: the real figure varies by model, dimension pair, corpus and metric, so measure recall@k or nDCG on your own workload before you pick a size. ## API versus self-hosted [#api-versus-self-hosted] Use a hosted API when scale is under roughly 1M documents/month, latency under 500ms is acceptable, and you want a vendor-maintained model. Self-host when embedding volume is high enough that per-token cost dominates, or when data cannot leave your infrastructure. Domain-specific or specialized models (legal, medical, code) can outperform generalist embeddings on niche corpora - compare with recall@k or nDCG on your own data before switching. ## Multimodal embeddings [#multimodal-embeddings] Use multimodal embeddings when source documents include images, slides, charts, or video, or when queries need to cross modalities ("find documents with a chart like this image"). Voyage Multimodal 3.5 (text, image, video; unified 1,024-dim space), Cohere Embed 5 (`embed-v5.0-pro`, `embed-v5.0-fast`; text, image), Cohere Embed v4 (`embed-v4.0`) and Gemini Embedding 2 (text, image, video, audio, documents) are selected options, not an exhaustive list; CLIP and SigLIP are common open-source baselines. For PDFs and visually complex documents, a late-interaction approach (ColPali-style, treating pages as images) can outperform OCR-then-chunk pipelines - see [RAG Patterns](https://agentsurface.dev/docs/agent-retrieval/rag-patterns). ## See also [#see-also] - [OpenAI Embeddings API](https://platform.openai.com/docs/guides/embeddings) - [Voyage AI pricing](https://docs.voyageai.com/docs/pricing) - [Cohere Embed docs](https://docs.cohere.com/docs/embeddings) - [MTEB Leaderboard](https://huggingface.co/mteb)