Search
Uses: /encode · /score
Retrieval in two moves: /encode turns documents and queries into vectors for fast recall, then /score reranks the shortlist for precision. Pick a dense, sparse, or multi-vector embedder and pair it with a cross-encoder.
Featured models
Encode · /encode
| Model | Size | Quality | Latency | Throughput | Cost $/1M | |
|---|---|---|---|---|---|---|
| NovaSearch/stella_en_1.5B_v5 Dense | 1.5B | 0.4219ndcg@10 | 258 ms | 12.8K tok/s | $0.017 | |
| NovaSearch/stella_en_400M_v5 Dense | 435M | 0.4125ndcg@10 | 116 ms | 27.1K tok/s | $0.0082 | |
| Alibaba-NLP/gte-multilingual-base MultilingualLong contextDense | 305M | 0.3677ndcg@10 | 57 ms | 55.1K tok/s | $0.0040 | |
| No models match. | ||||||
Measured on L4; other hardware shows "—" until benchmarked. Pick a benchmark to rank by quality.
For similar models, browse the full
/encode catalog →
Score · /score
| Model | Size | Quality | Latency | Throughput | Cost $/1M | |
|---|---|---|---|---|---|---|
| mixedbread-ai/mxbai-rerank-large-v2 MultilingualLong context | 1.5B | 0.6914ndcg@10 | 767 ms | 1.9K tok/s | $0.118 | |
| BAAI/bge-reranker-v2-m3 MultilingualLong context | 568M | 0.6763ndcg@10 | 92 ms | 30.0K tok/s | $0.0074 | |
| BAAI/bge-reranker-base Multilingual | 278M | 0.5926ndcg@10 | 45 ms | 21.3K tok/s | $0.010 | |
| No models match. | ||||||
Measured on L4; other hardware shows "—" until benchmarked. Pick a benchmark to rank by quality.
For similar models, browse the full
/score catalog →
Examples
End-to-end projects from our examples that put this task to work.
Find the best retrieval strategy for your RAG
Head-to-head retrieval ablation across encoder, reranker and multi-vector pipelines on 1,854 SEC 10-K queries, ranked by NDCG@10.
Private fine-tuned compliance RAG A domain-tuned LoRA encoder and a custom cross-encoder that reranks and prunes context in one forward pass.
Self-hosted product search in 5 min Amazon-style search from three SDK calls: extract attributes, encode descriptions, score-rerank candidates.
Find SOTA embedding models by MTEB task Describe your task in plain language and search ~14K Hugging Face embedding models, ranked by MTEB scores.
Multimodal product classifier with embeddings NLI, text and image retrieval, and cross-encoder reranking over a hierarchical product taxonomy.
Featured picks are still being finalized. Latency, throughput and cost are real where we've benchmarked the model on the selected GPU; "—" means no measurement there. Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Compare (0)Compare →