gemini-4VIDEO
Pydantic AI adds Gemini 4 Argon long decode support
Pydantic AI now supports Gemini 4 Argon long decode: one request stops at 32K output tokens (64K streamed), and it follows Google's continuation token to return one combined response.
Pydantic
@pydanticArchived 21 days agoOriginally posted 2026.10.14
Pydantic @pydanticOriginally posted 2026.10.14
Pydantic AI now supports Gemini 4 Argon, with long decode. One Argon request stops at 32K output tokens (64K streamed). Set a bigger output budget and Pydantic AI follows Google's continuation token for you: one agent run, one combined response. https://pydantic.io/ifgZJ
x.com/pydantic/status/2110163720080965663Archived 2026.10.14 10:19