armandmcqueen.dev
← All runs

glm-5.3-flash

8/27/2026, 2:02:48 PM · 1 tests · run 52211bf0-0081-43fc-b34d-ea23f2a2d8e0

summarize-memex

ok

Summarizes an ~11k-token essay to ~500 words (long input, reasoning minimized).

  • Read ~10238 input tokens, wrote 564 words (1922 output tokens) in 44884ms.
Result
{
  "wordCount": 564,
  "inputTokens": 10238,
  "outputTokens": 1922,
  "latencyMs": 44884
}
dbb037e5-e42b-4977-b48b-d96ae9193eda
Aug 27, 2026, 14:02:48

zai:glm-5.3-flash

Input
10,238
Output
1,922
Reasoning
1,179
Answer
743
Cache Read
10,176
Cost
$0.0013
Mode
streaming
Cost breakdown
Input $0.000009Output $0.000961Cache read $0.000305
Latency
44.9s
TTFT
27.5s
Tok/s
42.8
Tok/s (adj)
42.8