skip to content
gigarouter gigarouter
models / embeddings · coming soon

CDE Small V1

jxm/cde-small-v1

published Sep 2024 · updated May 2025

CDE Small V1 is a contextual document embedding model that integrates context tokens for improved retrieval, achieving state-of-the-art on MTEB among models under 400M parameters.

est. price
~$0.008
/ 1M tokens · estimated, set at launch
API providers
0
downloads / mo
190

specs

TaskText Embedding for Retrieval
ArchitectureBERT-based two-stage contextual architecture
ParametersUnder 400 million
LicenseNot specified

about this model

cde-small-v1 is a text embedding model that integrates context tokens into the embedding process, using a two-stage architecture to condition document and query embeddings on a representative subset of the corpus. The first stage embeds a fixed number of representative documents (512 by default) to produce dataset embeddings. The second stage then embeds individual queries or documents while conditioning on these dataset embeddings, enabling contextualized representations that outperform standard biencoders.

Key Strengths

As of October 1, 2024, cde-small-v1 is the best small model (under 400 million parameters) on the MTEB leaderboard for text embedding, achieving an average score of 65.00. Without corpus information, performance drops to 63.8, still competitive. The model achieves state-of-the-art MTEB results without hard negative mining, score distillation, dataset-specific instructions, intra-GPU example-sharing, or extremely large batch sizes, as detailed in the accompanying paper (arXiv:2410.02525).

Usage Notes

The model uses task-specific prefixes: search_query: for queries and search_document: for documents. Embeddings are normalized and should be compared via dot product or cosine similarity.

best for

FAQ

What is CDE Small V1 best for?

It is optimized for dense retrieval tasks where contextual document embeddings improve performance, especially out-of-domain.

Is CDE Small V1 deprecated?

Yes, the model is deprecated; the improved CDE Small V2 is recommended with higher MTEB score (65.58).

How does the two-stage embedding process work?

First, embed a subset of the corpus to create dataset embeddings; second, embed queries and documents conditioned on those context embeddings.

How can I call CDE Small V1 via the API on gigarouter?

Use the OpenAI-compatible endpoint with an API key, providing prompts with the appropriate prefixes for queries and documents.

What input format does the model expect?

Text up to 512 tokens; use prefixes "search_query: " for queries and "search_document: " for documents.

not yet live

We're benchmarking and onboarding CDE Small V1 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related embeddings models

compare all →