{"id":"hs-decide-1-flash","slug":"hs-decide-1-flash","name":"hs-decide-1-flash","orgId":"vectorize","family":"hs-decide-1-flash","releaseDate":null,"availability":"ga","openWeights":true,"license":"Apache 2.0","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-decide-1-flash","hindsight-ai/hs-decide-1-flash","hs decide 1 flash","hindsight decide 1 flash","hindsight decision model"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-03","announced":"2026-11-03","blurb":"Vectorize's 0.8B decision model for the Hindsight agent-memory system: instead of generating text, it returns a probability for every answer option in one forward pass. Open weights (Apache 2.0) on Hugging Face, also served on the Hindsight Inference API.","api":"live","apiModelId":"hs-decide-1-flash","openWeights":"yes","params":{"text":"0.8B (752,393,024 stored parameters in the safetensors)","source":"https://huggingface.co/hindsight-ai/hs-decide-1-flash"},"facts":[{"label":"Type","value":"Decision model: one forward pass returns a probability for each answer option; it generates no text"},{"label":"Question types","value":"choice (2 to 255 options), score (2 to 10 ordered levels) and noul (yes or no); several questions can share one request"},{"label":"Base model","value":"Qwen/Qwen3.5-0.8B"},{"label":"Context","value":"Trained on requests up to 65,536 tokens; longer requests are rejected"},{"label":"Languages","value":"English, Spanish, French, German, Portuguese, Japanese, Korean and Chinese"},{"label":"Weights","value":"Hugging Face hindsight-ai/hs-decide-1-flash, bfloat16, not gated; serves on vLLM with a plugin that adds POST /v1/systemone"},{"label":"License","value":"Apache 2.0"},{"label":"API","value":"Hindsight Inference (inference.hindsight.vectorize.io) POST /v1/systemone, System One compatible, $0.02 per 1M input tokens; also accepted on the Cohere-compatible /v1/rerank to drop irrelevant documents"},{"label":"Use in Hindsight","value":"Opt-in in Hindsight 1.2.0 for consolidation, reflect and knowledge-page judgments, plus optional recall pruning and dedup"},{"label":"Siblings","value":"hs-embed-1 and hs-rerank-1, released the same day (separate pages)"}],"claims":["Lab claim: inside Hindsight, six of seven LLMs give better answers and five get cheaper with hs-decide-1-flash taking the small judgments; on gemini-3.8-flash the operations it joins cost 2.5x less, spend 1.9x less time in model calls and score 2.2 points higher, while reflect quality dips on some LLMs.","Lab claim: median 167 ms per request (350 ms p90).","Lab claim: mean of 75.6 over eight decision benchmarks against 74.5 for StartLux-Decision 0.8B Instant, 73.4 for d3-lite and 66.6 for decider-0.8b, though it trails on the public Decision Index (36.1 against 53.8 for StartLux)."],"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-decide-1-flash benchmarks (Hindsight Benchmarks)","url":"https://benchmarks.hindsight.vectorize.io/models/decision"},{"kind":"repo","title":"hindsight-ai/hs-decide-1-flash on Hugging Face","url":"https://huggingface.co/hindsight-ai/hs-decide-1-flash"}],"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-decide-1-flash 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":[]}