LLM API Monitor Report Updated: 2026-09-08 22:32:46

Total Checks 528
Success 407
Failed 121
Success Rate 77.1%
Avg Response 2948ms

Success Rate Trend

0%25%50%75%100%09-07 2209-07 2309-08 0009-08 0109-08 0209-08 0309-08 0409-08 0509-08 0609-08 0709-08 0809-08 0909-08 1009-08 1109-08 1209-08 1309-08 1409-08 1509-08 1609-08 1709-08 1809-08 1909-08 2009-08 21
View All Logs →
Model Total Success Failed Rate Avg (ms) Errors
anthropic/claude-4.7-opus 24 0 24 0.0% 0 1 ✕
anthropic/claude-4.8-opus 24 0 24 0.0% 0 1 ✕
anthropic/claude-fable-5 24 0 24 0.0% 0 1 ✕
anthropic/claude-opus-5 24 0 24 0.0% 0 1 ✕
anthropic/claude-sonnet-5 24 0 24 0.0% 0 1 ✕
claude-haiku-4-5 24 24 - 100.0% 1505 -
claude-opus-4-5 24 24 - 100.0% 1873 -
claude-opus-4-6 24 24 - 100.0% 1954 -
claude-opus-4-7 24 24 - 100.0% 1545 -
claude-opus-4-8 24 24 - 100.0% 1663 -
claude-opus-5 24 24 - 100.0% 1955 -
claude-sonnet-4-5 24 24 - 100.0% 2049 -
claude-sonnet-4-6 24 24 - 100.0% 1448 -
claude-sonnet-5 24 24 - 100.0% 2510 -
deepseek-v4-flash 24 24 - 100.0% 652 -
deepseek-v4-pro 24 24 - 100.0% 1133 -
gemini-3-flash-preview 24 23 1 95.8% 11331 1 ✕
gemini-3.1-pro-preview 24 24 - 100.0% 4454 -
gpt-5.4 24 24 - 100.0% 5063 -
kimi-k3 24 24 - 100.0% 3048 -
qwen3.6-plus 24 24 - 100.0% 4222 -
qwen3.7-plus 24 24 - 100.0% 4057 -
No models match the filter.