Data Export

# Request logs, specific date range, GPT-4o only, CSV
curl "https://api.spanlens.io/api/v1/exports/requests?from=2026-05-01T00:00:00Z&to=2026-05-15T23:59:59Z&provider=openai&model=gpt-4o&format=csv" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
  -o spanlens-requests.csv

# Traces, last 7 days, JSON
curl "https://api.spanlens.io/api/v1/exports/traces?from=2026-05-08T00:00:00Z&format=json" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
  -o spanlens-traces.json

# Anomaly history, defaults (30 days, CSV)
curl "https://api.spanlens.io/api/v1/exports/anomalies" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
  -o spanlens-anomalies.csv

# Security flags, from a specific date
curl "https://api.spanlens.io/api/v1/exports/security?from=2026-05-01T00:00:00Z" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
  -o spanlens-security.csv

# One million rows, streamed. Pipe straight into jq for filtering.
curl "https://api.spanlens.io/api/v1/exports/requests?format=jsonl&from=2026-01-01T00:00:00Z&limit=1000000" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
  | jq -c 'select(.cost_usd != null and (.cost_usd | tonumber) > 0.01)' \
  > expensive-requests.jsonl

# Each line is a self-contained JSON object:
# {"id":"req_xxx","provider":"openai","model":"gpt-4o-mini-2024-07-18",...}
# {"id":"req_yyy","provider":"anthropic","model":"claude-sonnet-4-5",...}

curl "https://api.spanlens.io/api/v1/exports/requests?format=json&limit=1000" \
  -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN"

# Response shape (buffered, capped at 10,000 rows):
# {
#   "exported_at": "2026-05-19T08:30:00.000Z",
#   "count": 1000,
#   "data": [
#     {
#       "id": "req_xxx",
#       "project_id": "proj_xxx",
#       "provider": "openai",
#       "model": "gpt-4o-mini-2024-07-18",
#       "prompt_tokens": 512,
#       "completion_tokens": 128,
#       "total_tokens": 640,
#       "cost_usd": 0.000096,
#       "latency_ms": 843,
#       "status_code": 200,
#       "error_message": null,
#       "trace_id": null,
#       "created_at": "2026-05-15T09:00:00.000Z"
#     },
#     ...
#   ]
# }

import pandas as pd

token = "YOUR_SUPABASE_ACCESS_TOKEN"

# Small / medium, CSV, single response.
url = "https://api.spanlens.io/api/v1/exports/requests?from=2026-05-01T00:00:00Z&format=csv"
df = pd.read_csv(url, storage_options={"Authorization": f"Bearer {token}"})

# Million-row pipeline, JSONL, streamed line-by-line. Pandas reads it in
# chunks so peak memory stays bounded.
url = "https://api.spanlens.io/api/v1/exports/requests?format=jsonl&limit=1000000"
chunks = pd.read_json(url, lines=True, chunksize=50_000,
                      storage_options={"Authorization": f"Bearer {token}"})
totals = pd.concat(chunk.groupby("model")["cost_usd"].sum() for chunk in chunks).groupby(level=0).sum()
print(totals)