hs-decide-1-flash is Vectorize's open 0.8B model for agent memory. It supports eight languages and costs $0.02 per million hosted input tokens.
By Vectorize (Hindsight) · Released 3 Nov 2026
Vectorize's Hindsight team fine-tuned this 0.8B model from Qwen3.5-0.8B for agent memory. It returns probabilities for choice, score and yes/no questions in one pass. Hindsight first tried these judgments with Jev, then trained its own model to check whether facts are new and evidence is enough. It uses the same System One request shape.
Quick answers
What is hs-decide-1-flash by Vectorize (Hindsight)?
hs-decide-1-flash: Vectorize's Hindsight team fine-tuned this 0.8B model from Qwen3.5-0.8B for agent memory.
The 9 November serving update adds a Transformers model class and System One HTTP server without new weights. Python 3.12 or later and an appropriate PyTorch installation are required. The server answers one request at a time. A lower max-request-tokens setting makes it refuse longer inputs so Hindsight can split them; timeout and concurrency settings still apply. This is a documented runtime route, without a new hardware speed measurement.
English, Spanish, French, German, Portuguese, Japanese, Korean and Chinese
Context
65,536 tokens per request (trained)
Price
$0.02 per million input tokens on Hindsight Inference; input only · Compare prices
Access
Open weights; vLLM plugin or Transformers on CPU, Apple Silicon and supported GPUs; hosted POST /v1/systemone
Claims and sources
In Hindsight's own 1.2.0 evaluation, quality rises for six of seven LLMs. glm-5.3-flash goes from 73.8 to 87.1 and deepseek-v4.1-flash from 81.9 to 85.1; gemini-3.1-flash-lite goes from 87.1 to 86.6. That model is also the judge, so its rows are self-graded. Costs fall for five LLMs. vendor reportedsource
glm-5.3-flash with the decision model scores 87.1 at $7.72 per thousand cases, against 89.0 at $147 for gemini-3.8-flash alone. Costs use list prices and an equal mix of four memory operations. vendor reportedsource
Median decision-model latency is 167 ms, with 350 ms at p90. The replaced LLM calls had median latencies of 1 to 7 seconds, depending on the model. vendor reportedsource
Reflect costs 4.6x less with gemini-3.8-flash, while quality drops from 94.1 to 91.2. With gemini-3.1-flash-lite, reflect quality drops from 94.1 to 85.3. vendor reportedsource
Against three other 0.8B models, its mean across eight benchmarks is 75.6, ahead of 74.5, 73.4 and 66.6. On the public Decision Index it trails StartLux-Decision 0.8B Instant, 36.1 to 53.8. vendor reportedsource
Across its evaluation, Hindsight reports 3.1 LLM calls per case with the decision model, against 4.5 before. This is an evaluation-wide mean; individual memory operations and workloads differ. vendor reportedsource
Hindsight uses hs-decide-1-flash to prune and deduplicate recall, check whether evidence answers a request, consolidate new facts and decide whether a memory could change a knowledge page. It first tried this with Jev. In the team's own Hindsight 1.2.0 evaluation, glm-5.3-flash plus the decision model scores 87.1 at $7.72 per thousand cases, against 89.0 at $147 for gemini-3.8-flash alone. Reflect quality falls with some LLMs. gemini-3.1-flash-lite judges all runs and also appears in the comparison.