New API

API Provider Performance Test Results

Host Addressapi.huajinet.link

Supported Models3 models

Supported Models

3 models

Model Name	Test Count	Average Output Speed	Average First Token Latency
gemini-2.5-flash	5	17911.37 t/s	14.53s
llama-4-maverick	5	0.00 t/s	-s
qwen3	5	59.87 t/s	5.39s

Total Tests

15

Total Tests

Average Tokens/Second

5990.42 t/s

0.00 - 28154.49 t/s

Average First Token Latency

6.64s

0.00 - 18.94s

Last Test Time

8/12/2025, 4:58:31 PM

Last Test Time

Top Models Performance

1

gemini-2.5-flash

Test Count: 5

17911.37 t/s

Average Speed

2

qwen3

Test Count: 5

59.87 t/s

Average Speed

3

llama-4-maverick

Test Count: 5

0.00 t/s

Average Speed

Recent Test Records

3 records

Test Time	Model	Average Output Speed	Average First Token Latency	Total Tokens
8/12/2025, 4:58:31 PM	qwen3	59.87 t/s	5.39s	4914
8/12/2025, 4:58:17 PM	llama-4-maverick	0.00 t/s	-s	0
8/12/2025, 4:53:44 PM	gemini-2.5-flash	17911.37 t/s	14.53s	5399