Inspect usage

Read today’s totals and monthly rollups from the SDK.

Use these methods to read org-wide usage totals. They are useful for dashboards, quota checks, and billing reports.

tex.usage.today()                    # today's usage + daily quota
tex.usage.summary()                  # current calendar month
tex.usage.summary(month="2026-03")   # specific month

These helpers are read-only. They do not count toward your quota.

tex.usage.today()

status = tex.usage.today()

tokens_in_used · int

Tokens you’ve sent us today (UTC day).

tokens_out_used · int

Tokens we’ve returned to you today.

tokens_in_limit · int

Daily ingress cap. 1_000_000 on the free tier.

tokens_out_limit · int

Daily egress cap. 5_000_000 on the free tier.

period · str

Always "day_utc".

period_start · str

ISO 8601 timestamp at 00:00 UTC today.

period_end · str

ISO 8601 timestamp at 00:00 UTC tomorrow.

status = tex.usage.today()
print(f"in:  {status.tokens_in_used:,} / {status.tokens_in_limit:,}")
print(f"out: {status.tokens_out_used:,} / {status.tokens_out_limit:,}")
print(f"resets at: {status.period_end}")

tex.usage.summary(month=None)

Calendar-month rollup, UTC.

month · str | None

"YYYY-MM". Omitted = current month.

period · str

Always "month".

start · str

ISO 8601 timestamp of the first second of the month.

end · str

ISO 8601 timestamp of the first second of the next month.

tokens_in · int

Total ingress tokens for the month.

tokens_out · int

Total egress tokens for the month.

import pandas as pd

months = ["2026-01","2026-02","2026-03","2026-04","2026-05"]
df = pd.DataFrame([
    {"month": m, **tex.usage.summary(month=m).__dict__}
    for m in months
])
df.set_index("month")[["tokens_in","tokens_out"]].plot.bar()

Patterns

• Per-response usage is on every remember and recall:

  hits = tex.recall(q="...", session_id=sid)
  print(hits.usage.tokens_in, hits.usage.tokens_out)
  

• Quota-aware routing - turn off non-essential memory paths past 90%:

  if tex.usage.today().tokens_in_used > 0.9 * tex.usage.today().tokens_in_limit:
      return generate_without_memory(query)
  

  Cache usage.today() on your side for up to 60 seconds. Use it as a soft guard, not a strict limiter.

• Usage charts - call summary(month="YYYY-MM") for each of the last 6 months and render the results in your charting library.

Next: Handle errors

Every exception class and how to handle it.