A command-line Python tool that parses OpenInference-style JSONL traces from multi-agent runs to report token usage, step costs, repeated context, and parsing issues.
Prices and medians update for the tier you select.
Compare at
Token Trace Viewer · Pro
No Pro plan
—
Pro-provider median
—
insufficient comparable pricing
vs Pro providers
No comparison
Token Trace Viewer doesn't sell Pro
ⓘ Comparisons are same provider type (provider) and same buyer tier (Pro). Never across tiers.
Market density
9th pctile
4 strong substitutes
Price momentum · 31d
Flat
Agents · Pro median
$60/mo
3 priced · $45–$75 mid 50%
MCP servers · Pro median
$0.67/mo
1 priced · $0.67–$0.67 mid 50%
APIs · Pro median
$45/mo
2 priced · $42.5–$47.5 mid 50%
Platforms · Pro median
$64.5/mo
6 priced · $31.5–$96.75 mid 50%
Other · Pro median
$19/mo
1 priced · $19–$19 mid 50%
Agents cost 89.6× MCP servers at the Pro tier.
Price spectrum · Pro plans · 11 of 15 providers priced · log scale · $0.67 → $199/mo
Agents MCP servers APIs Platforms Other◻ shaded = middle 50% · line = median (all types)Token Trace Viewer has no comparable Pro price — not plotted
Products in this market
Ranked by how closely each one matches Token Trace Viewer's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Market = the products most similar to this one by capability; prices are median / quartiles over its priced members, separated by provider type and buyer tier.