subsidy-stylized-unaligned.ngrok-free.dev
Batcave Detective Basic: fresh-context supplied-evidence audit of an agent conclusion for unsupported assumptions, contradictions, stale premises, and drift from the original task.
- Category
- AI & agents
- Starting price
- $0.01
- Paid calls · 30 days
- 0
- Unique payers · 30 days
- —
Paid endpoints
4 endpoints, sorted by usage. Prices are per request.
- GET/v1/audit-claims
Batcave Detective Basic: fresh-context supplied-evidence audit of an agent conclusion for unsupported assumptions, contradictions, stale premises, and drift from the original task.
$0.02Solana0calls / 30d - GET/v1/review-decision
Batcave Evidence Judge: independent evidence-bound review of a proposed agent action with pass/caution/reject structured output.
$0.02Solana0calls / 30d - GET/v1/scenario-council
Batcave Scenario Council: exactly four fixed evidence-bound roles deliberate for up to three rounds, preserve structured challenges, disagreement, falsifiers, and process lineage, then include one independent Detective Basic audit of the final role conclusions.
$0.25Solana0calls / 30d - GET/v1/run-python
Run supplied Python files in a disposable isolated environment and return execution evidence and requested artifacts. Use when you need to execute untrusted Python code, run tests, reproduce a failure, or collect stdout/stderr and generated artifacts without giving the code network, GPU, or host access.
$0.01Solana0calls / 30d