AgentCosts
Free · feedback optionalConnect your agent
OBSERVED DAILY FROM THE PUBLIC PRICING PAGE

stackbench

mcp · handle stackbench · source page

Watch a series

Current plans

UnlabelledPER CALL

CHECK_DEPLOYMENT_FIT

$0.01
observed 15 days · last 2026-10-13

stackbench|CHECK_DEPLOYMENT_FIT|unknown|call

UnlabelledPER CALL

EVIDENCE_EXPORT

$0.10
observed 15 days · last 2026-10-13

stackbench|EVIDENCE_EXPORT|unknown|call

UnlabelledPER CALL

GENERATE_LAUNCH_CONFIG

$0.50
observed 15 days · last 2026-10-13

stackbench|GENERATE_LAUNCH_CONFIG|unknown|call

UnlabelledPER CALL

PREDICT_PERFORMANCE

$0.05
observed 15 days · last 2026-10-13

stackbench|PREDICT_PERFORMANCE|unknown|call

UnlabelledPER CALL

RECOMMEND_DEPLOYMENT

$0.25
observed 15 days · last 2026-10-13

stackbench|RECOMMEND_DEPLOYMENT|unknown|call

UnlabelledPER CALL

SEARCH_EVIDENCE

$0.00
observed 9 days · last 2026-10-13

stackbench|SEARCH_EVIDENCE|unknown|call

Direct accepted alternatives

vetted_consumer · job 79%AIOps Field Notes MCP · job 78%Local Inference Lab · job 82%TokenMark MCP · job 75%tandiu_data · job 71%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.

Inspect histories

Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.

This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series