Hosted models for the steps around your LLM: reranking, embeddings and typed decisions. Point your Cohere or OpenAI client at inference.hindsight.vectorize.io and keep your code. hs-rerank-1 and hs-embed-1 are the most accurate small open models on our benchmarks and run fast on a CPU; hs-decide-1-flash answers yes/no, pick-one and how-likely questions in 167 ms, instead of an LLM call. From $0.005 per 1M tokens, $5 free credit, open weights on Hugging Face.
We build Hindsight, an open-source memory system for AI agents. A memory system is full of small judgments: is this fact new? Which of these memories matter? Is this evidence enough to answer? We used to send every one of them to an LLM: seconds of latency and a bill for every token, just to get a yes or no back.
So we trained small models for those steps. Today we're releasing them as Hindsight Models, with open weights on Hugging Face and a hosted Hindsight Inference API:
• hs-rerank-1 (114M): a reranker, drop-in for Cohere Rerank. More accurate than gte-reranker-modernbert-base, and 6x faster on a CPU.
• hs-embed-1 (112M): embeddings, drop-in for OpenAI Embeddings. 16.5 ms per query on a CPU.
• hs-decide-1-flash (0.8B): a decision model. Ask it typed questions (pick one, how likely, where on a scale) and get probabilities back in about 167 ms. Rerank with it and it also drops the documents that don't help.
Inside Hindsight, the decision model made memory up to 2.5x cheaper, with better answers from six of the seven LLMs we tested. Every number and the method behind it is in the launch post and on benchmarks.hindsight.vectorize.io.
You pay for input tokens only, from $0.005 per 1M, and new accounts get $5 of free credit. Try every model in the Playground before you write any code, or run the open weights yourself.
What would you use a decision model for? We're here all day to answer questions.
the typed decision model is the part i'd try first
there are plenty of small yes or no steps in a workflow where waiting for a full chat response feels excessive
Congrats! How well does hs-decide-1-flash generalize beyond agent memory—for example, to support ticket routing? Would a clear prompt and a few examples be enough to get started, or would it need fine-tuning?
About Hindsight Models and Inference API on Product Hunt
“Small, fast models for reranking, embeddings and decisions”
Hindsight Models and Inference API launched on Product Hunt on November 4th, 2026 and earned 73 upvotes and 6 comments, placing #22 on the daily leaderboard. Hosted models for the steps around your LLM: reranking, embeddings and typed decisions. Point your Cohere or OpenAI client at inference.hindsight.vectorize.io and keep your code. hs-rerank-1 and hs-embed-1 are the most accurate small open models on our benchmarks and run fast on a CPU; hs-decide-1-flash answers yes/no, pick-one and how-likely questions in 167 ms, instead of an LLM call. From $0.005 per 1M tokens, $5 free credit, open weights on Hugging Face.
Hindsight Models and Inference API was featured in API (98.9k followers), Developer Tools (523.3k followers) and Artificial Intelligence (484k followers) on Product Hunt. Together, these topics include over 246.8k products, making this a competitive space to launch in.
Who hunted Hindsight Models and Inference API?
Hindsight Models and Inference API was hunted by Chris Bartholomew. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Reviews
Hindsight Models and Inference API has received 3 reviews on Product Hunt with an average rating of 5.00/5. Read all reviews on Product Hunt.
Want to see how Hindsight Models and Inference API stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt 👋 Chris from Vectorize here.
We build Hindsight, an open-source memory system for AI agents. A memory system is full of small judgments: is this fact new? Which of these memories matter? Is this evidence enough to answer? We used to send every one of them to an LLM: seconds of latency and a bill for every token, just to get a yes or no back.
So we trained small models for those steps. Today we're releasing them as Hindsight Models, with open weights on Hugging Face and a hosted Hindsight Inference API:
• hs-rerank-1 (114M): a reranker, drop-in for Cohere Rerank. More accurate than gte-reranker-modernbert-base, and 6x faster on a CPU.
• hs-embed-1 (112M): embeddings, drop-in for OpenAI Embeddings. 16.5 ms per query on a CPU.
• hs-decide-1-flash (0.8B): a decision model. Ask it typed questions (pick one, how likely, where on a scale) and get probabilities back in about 167 ms. Rerank with it and it also drops the documents that don't help.
Inside Hindsight, the decision model made memory up to 2.5x cheaper, with better answers from six of the seven LLMs we tested. Every number and the method behind it is in the launch post and on benchmarks.hindsight.vectorize.io.
You pay for input tokens only, from $0.005 per 1M, and new accounts get $5 of free credit. Try every model in the Playground before you write any code, or run the open weights yourself.
What would you use a decision model for? We're here all day to answer questions.
Launch post: https://hindsight.vectorize.io/b...