Developed by Google, Flan T5 Base is a language model that excels at few-shot performance, achieving strong results even compared to larger models. With a context window of 512 tokens, it is capable of handling a wide range of tasks and languages, including English, Spanish, Japanese, and many others.
Input
Output
Context
1K
Max Output
0K
Parameters
247.6M
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Automatically route workloads to the right model for every task, every time.