LLM API Speed Test
Batch Testing Provider TTFT & Token Output Speed (tok/s).
中文
Privacy First: LocalStorage Only
Testing Dashboard
History Analytics
Configuration
Preset Provider
Protocol Format
OpenAI (v1/chat/completions)
Anthropic (v1/messages)
API URL
Models
Fetch Models
API Key
🔒 Local Only
Test Prompt
Rounds
Start Batch Test
Status
Idle
TTFT
(s)
-
Thinking
(s)
-
Answer
(s)
-
Total Time
(s)
-
Response Preview
Speed
:
-
(tok/s)
Tokens: 0
Awaiting test...
Recent Activity
Time
Round
Provider / Model
TTFT (s)
Thinking (s)
Answer (s)
Speed (t/s)
Total (s)
Provider
All
Model
All
Start Date
End Date
Avg TTFT (s)
-
Avg Speed (tok/s)
-
Total Runs
-
Analytics Data
Clear All Data
Export Filtered CSV
Time
Round
Provider / Model
TTFT (s)
Thinking (s)
Answer (s)
Speed (t/s)
Total (s)