I understand that the context tokens for Gemini Tuned Models via the AI Studio is roughly 16k tokens. Is this the same as when calling via an API? I’m having trouble locating the documentation for that (if any).
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Friends, I need urgent help. I cannot connect the model to my own website | 8 | 215 | October 8, 2024 | |
| Request payload size exceeds the limit: 50000 bytes | 1 | 168 | December 16, 2024 | |
| Context Cache Creation with Pro Model Variants | 1 | 74 | November 27, 2024 | |
| Where/how do I find *remaining* tokens/requests count after making a request? | 0 | 122 | September 30, 2024 | |
| Understanding the limit of fine-tuned Gemini Flash | 1 | 313 | October 21, 2024 |