Usage tallies

mc.usage.tallies()                                                # all-time
mc.usage.tallies(start="2026-05-01", end="2026-05-31")            # bounded range

Parameters

start

str

ISO date ("YYYY-MM-DD"). Inclusive. Omit for no lower bound.

end

str

ISO date. Inclusive. Omit for no upper bound.

format

str

default:"\"models\""

"models" returns a typed UsageResponse; other values pass through to the underlying serializer.

Response shape

res = mc.usage.tallies(start="2026-05-01", end="2026-05-31")
res.to_dicts()
# [
#   {"endpoint": "v2/enrich", "count": 1247},
#   {"endpoint": "v2/resolve", "count": 318},
#   ...
# ]

res.to_df()         # pandas DataFrame   (needs [pandas])
res.to_csv("usage.csv")
res.to_table()      # pretty terminal table   (needs [table])

The exact response shape is server-defined; the SDK surfaces whatever list-of-rows the server returns. Use to_dicts() for the raw shape, to_df() for analysis.

Common patterns

Post-call audit — confirm a specific call actually billed:

res = mc.usage.tallies(start="2026-06-02", end="2026-06-02")
for row in res.to_dicts():
    print(row)

Monitoring feed — periodically poll for use in dashboards / alerts:

import time

while True:
    res = mc.usage.tallies(start=today_iso(), end=today_iso())
    send_to_monitoring(res.to_dicts())
    time.sleep(3600)

Country inference Async + bulk batching

⌘I

Getting started

Endpoints

Power features

Reference

Parameters

Response shape

Common patterns

​Parameters

​Response shape

​Common patterns

Parameters

Response shape

Common patterns