ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.
Retrieval embeddings, balanced
Find an embedding model that balances retrieval quality against the cost of embedding a task.
Worked example as of 2026-09-23, from the public data image.
Retrieval quality first, cost as a real second term.
Requirements
model.class = vectoriser: Retrieval embeddings require the model class that emits vectors.
Preferences
retrieval: Prefer stronger retrieval quality.-offering.cost_per_task: Among strong embedders, prefer the cheaper task.
Applied template spec
spec_version- 1
where- model.class = vectoriser
optimizeweightsretrieval- 0.7
-offering.cost_per_task- 0.3
Worked answer
Decision status: no_feasible.
No recommendation: the public image has no answer with enough evidence.
Unknown requirements
Some candidates may qualify. Missing facts:
offering.cost_per_task
Missing evidence and possible changes
- no model that meets the requirements has a value for retrieval, offering.cost_per_task
Decision dec_d429d2c4574a974a5576466a on public snapshot snap_05a963d2477ac2fb.
What this template teaches
When an embedder has no hosted price, it is ranked on retrieval alone and the page says the cost is unknown.
The live board uses current data. Its answer can change as evidence changes.
Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.