LoginStart beta
Ayneye
Cost docsStart beta

Agent cost calculator

Estimate repeated video-query cost before agents touch production traffic.

Video agents can become expensive when every plan, retry, or follow-up question rebuilds visual context. Ayneye moves the repeated work onto durable artifacts: World-State, evidence, timeline, detector report, and cost.json.

Artifact estimate$87
Indexing reference$378
Repeated-context gap$3,693

Agent cost model

LayerWhat happensCost meaning
One-time processingCreate scene_graph, timeline, evidence, costUseful before repeated agent questions
Repeated agent queriesRead compact state and evidenceLower repeated video-understanding work
Agent reasoningText/model/application computeStill costs money and should be budgeted
Human reviewRequired for risky actionsNot optional in security/identity/safety workflows

Implementation pattern

state = ayneye.get_scene_graph(video_id)
evidence = ayneye.get_evidence(video_id)
cost = ayneye.get_cost(video_id)
answer = agent.answer(question, context={"state": state, "evidence": evidence, "cost": cost})
assert answer.cites_evidence
assert not answer.performs_destructive_action

Safety and claim boundary

This is not free infinite querying and not feature equivalence with every GPU video model. It is a way to reduce repeated video-understanding work while preserving evidence and review boundaries.