A unified LLM API gateway providing access to multiple AI models through standardized endpoints.
玄黄
About 玄黄
Health Check
100%Recent availability
History (72 pts)
PastNow
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gpt-oss-120b | 1796.31 t/s | 0.49s | 5 |
| glm-4.7-特别版 | 428.83 t/s | 3.12s | 5 |
| 翻译/标题/OCR模型 | 260.68 t/s | 0.91s | 5 |
| gemini-3-flash-preview-search | 179.48 t/s | 6.64s | 5 |
| gemini-3-flash | 155.96 t/s | 4.01s | 5 |
| grok-4.1-fast | 72.98 t/s | 4.71s | 5 |
| claude-opus-4-6-thinking | 43.24 t/s | 1.65s | 5 |
| kimi-k2-instruct | 32.90 t/s | 1.10s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 16, 03:43 AM | 翻译/标题/OCR模型 | 260.68 t/s | 0.91s |
| Feb 16, 03:41 AM | claude-opus-4-6-thinking | 43.24 t/s | 1.65s |
| Feb 16, 03:39 AM | kimi-k2-instruct | 32.90 t/s | 1.10s |
| Feb 16, 03:26 AM | gpt-oss-120b | 1796.31 t/s | 0.49s |
| Feb 16, 03:22 AM | grok-4.1-fast | 72.98 t/s | 4.71s |
| Feb 16, 03:17 AM | gemini-3-flash | 155.96 t/s | 4.01s |
| Feb 16, 03:15 AM | glm-4.7-特别版 | 428.83 t/s | 3.12s |
| Feb 16, 03:13 AM | gemini-3-flash-preview-search | 179.48 t/s | 6.64s |