API Provider Performance Test Results
| Model Name | Test Count | Average Output Speed | Average First Token Latency |
|---|---|---|---|
gemini-2.0-flash | 20 | 177.30 t/s | 0.98s |
gemini-2.0-flash-lite-preview-02-05 | 15 | 188.38 t/s | 1.06s |
o3-mini | 15 | 148.38 t/s | 7.42s |
Phi-4 | 10 | 43.07 t/s | 1.32s |
qwen2.5-72b-instruct | 10 | 92.64 t/s | 2.57s |
gemini-1.5-flash-latest | 10 | 252.88 t/s | 1.26s |
gemini-1.5-flash-8b | 10 | 275.08 t/s | 1.28s |
deepseek-r1 | 10 | 25.85 t/s | 5.73s |
o3-mini-all | 10 | 74.59 t/s | 5.09s |
gpt-4o | 5 | 135.41 t/s | 1.43s |
gpt-4o-mini | 5 | 78.22 t/s | 1.05s |
qwen2.5-7b-instruct | 5 | 34.15 t/s | 1.01s |
BLOOMZ-7B | 5 | 875.69 t/s | 2.46s |
qwen-72b | 5 | 102.22 t/s | 3.11s |
claude-3-5-sonnet-20241022 | 5 | 39.36 t/s | 4.75s |
deepseek-reasoner | 5 | 29.86 t/s | 4.71s |
deepseek-v3 | 5 | 26.71 t/s | 3.41s |
gemini-1.5-flash | 5 | 158.26 t/s | 0.91s |
gemini-1.5-flash-002 | 5 | 239.65 t/s | 1.62s |
gemini-2.0-flash-exp | 5 | 125.02 t/s | 1.40s |
gemini-2.0-flash-thinking-exp-01-21 | 5 | 230.82 t/s | 7.47s |
glm-4-flash | 5 | 25.16 t/s | 1.30s |
Total Tests
14.60 - 3707.84 t/s
0.70 - 17.16s
Last Test Time
BLOOMZ-7B
Test Count: 5
875.69 t/s
Average Speed
gemini-1.5-flash-8b
Test Count: 10
275.08 t/s
Average Speed
gemini-1.5-flash-latest
Test Count: 10
252.88 t/s
Average Speed
gemini-1.5-flash-002
Test Count: 5
239.65 t/s
Average Speed
gemini-2.0-flash-thinking-exp-01-21
Test Count: 5
230.82 t/s
Average Speed
| Test Time | Model | Average Output Speed | Average First Token Latency | Total Tokens |
|---|---|---|---|---|
| 4/6/2025, 11:36:58 AM | gemini-2.0-flash | 193.77 t/s | 0.86s | 4410 |
| 4/6/2025, 11:36:09 AM | gemini-2.0-flash | 198.39 t/s | 0.92s | 4433 |
| 4/6/2025, 11:35:27 AM | gemini-2.0-flash | 191.79 t/s | 1.06s | 4243 |
| 2/20/2025, 8:16:04 AM | gemini-1.5-flash-latest | 174.31 t/s | 1.21s | 2279 |
| 2/20/2025, 7:49:24 AM | gemini-1.5-flash-latest | 331.45 t/s | 1.32s | 2184 |
| 2/20/2025, 7:45:38 AM | Phi-4 | 41.62 t/s | 0.90s | 2925 |
| 2/20/2025, 7:44:06 AM | glm-4-flash | 25.16 t/s | 1.30s | 2838 |
| 2/14/2025, 4:31:22 PM | qwen-72b | 102.22 t/s | 3.11s | 3751 |
| 2/14/2025, 4:10:22 PM | gemini-2.0-flash-lite-preview-02-05 | 175.81 t/s | 0.87s | 4109 |
| 2/14/2025, 4:08:38 PM | qwen2.5-72b-instruct | 96.05 t/s | 2.68s | 3940 |