A unified API gateway providing access to multiple large language models (LLMs) and AI services through a single interface.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gpt-4.1-nano-2025-04-14 | 592.40 t/s | 1.03s | 10 |
| gemini-2.0-flash | 176.13 t/s | 1.19s | 10 |
| deepseek-v3-1-terminus | 59.15 t/s | 1.57s | 20 |
| deepseek-v3-1-250821 | 57.75 t/s | 1.40s | 25 |
| deepseek-ai/DeepSeek-V3-0324 | 39.10 t/s | 1.37s | 35 |
| deepseek-ai/DeepSeek-R1-0528 | 33.42 t/s | 25.94s | 10 |
| deepseek/deepseek-v3-0324 | 26.61 t/s | 1.81s | 5 |
| deepseek-ai/DeepSeek-V3.2-Exp | 21.02 t/s | 3.34s | 10 |
| deepseek-ai/DeepSeek-V3.2-Exp | 21.02 t/s | 3.34s | 10 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Dec 30, 07:11 AM | deepseek-ai/DeepSeek-V3.2-Exp | 20.88 t/s | 2.51s |
| Dec 30, 07:00 AM | deepseek-v3-1-terminus | 45.32 t/s | 2.13s |
| Dec 30, 02:52 AM | gpt-4.1-nano-2025-04-14 | 222.46 t/s | 0.80s |
| Dec 30, 02:49 AM | gemini-2.0-flash | 181.28 t/s | 1.02s |
| Dec 28, 04:11 AM | deepseek-v3-1-terminus | 78.34 t/s | 0.64s |
| Dec 28, 04:07 AM | deepseek-ai/DeepSeek-V3.2-Exp | 21.16 t/s | 4.17s |
| Dec 20, 03:20 AM | gpt-4.1-nano-2025-04-14 | 962.34 t/s | 1.25s |
| Dec 20, 03:12 AM | deepseek-v3-1-terminus | 58.86 t/s | 2.20s |
| Nov 27, 04:51 AM | gemini-2.0-flash | 170.98 t/s | 1.37s |
| Oct 13, 05:29 AM | deepseek-v3-1-250821 | 66.69 t/s | 1.02s |