API platform providing access to Google's Gemini multimodal AI models.
Categories
Undy API offers 73 LLM API models.
API pricing per token ranges from $0.300 to $450.00/M (input).
Speed benchmark average: 136 tok/s.
https://vip.undyingapi.com| Time | Model | Speed | Latency |
|---|---|---|---|
| Aug 30, 12:07 PM | grok-3-beta | 19.01 tok/s | 4.52s |
| Aug 27, 02:49 PM | gemini-2.5-flash-lite | 296.41 tok/s | 1.49s |
| Aug 17, 09:30 AM | gpt-4.1-nano | 148.83 tok/s | 1.10s |
| Aug 17, 09:28 AM | gpt-4o-mini | 59.52 tok/s | 1.02s |
| Aug 17, 09:20 AM | gpt-5-nano | 162.88 tok/s | 6.22s |
| Aug 16, 04:52 PM | gpt-5-chat | 131.48 tok/s | 0.74s |