UberLLM lets you call Google Gemini models with the standard OpenAI SDK — no separate Google Cloud setup — routed to the cheapest healthy provider. UberLLM gives you one OpenAI-compatible API key and base URL for 380+ models, routing each request to the cheapest healthy provider with no inference markup and free starter credits.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Nano Banana 2 (image-to-image) | $0.0000 | $0.0000 |
| Nano Banana Pro (image-to-image) | $0.0000 | $0.0000 |
| Nano Banana 2 Lite (image-to-image) | $0.0000 | $0.0000 |
| Gemini 3.1 Flash TTS | $0.0000 | $0.0000 |
| Veo3 Fast (image-to-video) | $0.0000 | $0.0000 |
| Veo3 Full (image-to-video) | $0.0000 | $0.0000 |
| Veo3.1 Fast (image-to-video) | $0.0000 | $0.0000 |
| Veo3.1 Full (image-to-video) | $0.0000 | $0.0000 |
| Gemini Omni Flash (image-to-video) | $0.0000 | $0.0000 |
| Gemini Omni Flash (reference-to-video) | $0.0000 | $0.0000 |
| Veo 3 Fast Text-to-Video | $0.0000 | $0.0000 |
| Veo 3 Full Text-to-Video | $0.0000 | $0.0000 |
Live prices via UberLLM · full pricing table →
No — through UberLLM you call Gemini with the OpenAI SDK and one UberLLM key, no Google Cloud project required.