C
APDSM
APDSM provides a unified API gateway for accessing multiple large language models and AI services through standardized endpoints.
APDSM provides a unified API gateway for accessing multiple large language models and AI services through standardized endpoints.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| zhipu/glm-4.1v-thinking-flash | 85.15 t/s | 9.29s | 5 |
| zhipu/glm-4.1v-thinking-flash | 85.15 t/s | 9.29s | 5 |
| zhipu/glm-4v-flash | 57.69 t/s | 1.20s | 5 |
| qwen/qwen3-coder | 0.00 t/s | 0.80s | 10 |
| qwen/qwen3-coder | 0.00 t/s | 0.80s | 10 |
| qwen/qwen2.5-72b | 0.00 t/s | 0.83s | 5 |
| qwen/qwen2.5-72b | 0.00 t/s | 0.83s | 5 |
| google/gemini-2.0-flash-exp | 0.00 t/s | 0.65s | 5 |
| openai/gpt-oss-20b | 0.00 t/s | 0.64s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 28, 10:43 AM | zhipu/glm-4.1v-thinking-flash | 85.15 t/s | 9.29s |
| Mar 28, 10:43 AM | qwen/qwen2.5-72b | 0.00 t/s | 0.83s |
| Mar 28, 10:42 AM |
| google/gemini-2.0-flash-exp |
0.00 t/s |
0.65s |
| Mar 28, 10:42 AM | openai/gpt-oss-20b | 0.00 t/s | 0.64s |
| Mar 28, 10:42 AM | qwen/qwen3-coder | 0.00 t/s | 0.85s |
| Mar 28, 10:40 AM | qwen/qwen3-coder | 0.00 t/s | 0.76s |
| Mar 28, 10:36 AM | zhipu/glm-4v-flash | 57.69 t/s | 1.20s |