{"id":"hs-embed-1","slug":"hs-embed-1","name":"hs-embed-1","orgId":"vectorize","family":"hs-embed-1","releaseDate":null,"availability":"ga","openWeights":true,"license":"MIT","paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://hindsight.vectorize.io/blog/2026/11/03/hindsight-models","hfRepo":null,"modalities":["text"],"aliases":["hs-embed-1","hindsight-ai/hs-embed-1","hs embed 1","hindsight embed 1","hindsight embedding model"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-03","announced":"2026-11-03","blurb":"Vectorize's 112M multilingual text embedding model for Hindsight memory recall: 384-dimension vectors (truncatable to 64) over inputs up to 8,192 tokens in eight languages. Open weights (MIT) on Hugging Face, also served on the Hindsight Inference API.","api":"live","apiModelId":"hs-embed-1","openWeights":"yes","params":{"text":"112M (111,728,256 stored parameters; 98M are the token embedding table, so each pass runs a 13M-parameter transformer)","source":"https://huggingface.co/hindsight-ai/hs-embed-1"},"facts":[{"label":"Type","value":"Multilingual text embedding model; mean pooling, cosine similarity, no query or document prompts"},{"label":"Base model","value":"hotchpotch/bekko-embedding-v1-a25m (fine-tuned)"},{"label":"Dimensions","value":"384, truncatable to 256, 128 or 64"},{"label":"Context","value":"8,192 tokens"},{"label":"Languages","value":"English, Spanish, French, German, Portuguese, Japanese, Korean, and Simplified and Traditional Chinese"},{"label":"Weights","value":"Hugging Face hindsight-ai/hs-embed-1: FP16 safetensors (FP32 on an fp32 branch) and an int8 ONNX export; serves on Text Embeddings Inference on CPU or GPU"},{"label":"License","value":"MIT"},{"label":"API","value":"Hindsight Inference POST /v1/embeddings (OpenAI Embeddings compatible), $0.005 per 1M input tokens"},{"label":"Siblings","value":"hs-decide-1-flash and hs-rerank-1, released the same day (separate pages)"}],"claims":["Lab claim: overall mean of 56.8 over twelve retrieval benchmarks (including NanoBEIR, MIRACL, BEAM, LongEmbed and LMEB) against 54.6 for granite-embedding-97m-multilingual-r2 and 50.3 for multilingual-e5-small.","Lab claim: 16.5 ms median query latency on two CPU threads."],"sources":[{"kind":"lab","title":"Introducing Hindsight Models (Hindsight blog)","url":"https://hindsight.vectorize.io/blog/2026/11/03/hindsight-models","date":"2026-11-03"},{"kind":"lab","title":"Vectorize announcement on X","url":"https://x.com/Vectorizeio/status/2117647994048704588","date":"2026-11-03"},{"kind":"lab","title":"hs-embed-1 benchmarks (Hindsight Benchmarks)","url":"https://benchmarks.hindsight.vectorize.io/models/embeddings"},{"kind":"repo","title":"hindsight-ai/hs-embed-1 on Hugging Face","url":"https://huggingface.co/hindsight-ai/hs-embed-1"}],"firstBenchmark":null},"organization":{"id":"vectorize","name":"Vectorize","slug":"vectorize","country":null,"url":"https://vectorize.io","color":"#11110F","mark":"V"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 3, 2026; no independent results yet.","lead":"As of Nov 22, 2026, hs-embed-1 is pending benchmarks on isitsota: announced Nov 3, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}