Unverified50% confidenceFactExact time
PDF, audio, and video inputs are currently supported only through AI SDK 7; the TypeSafe-compatible API and the Decisions API support only text and image inputs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/11/2026
First Seen
Valid until: 2/9/2027
Sources
Related Entities
Related Claims
UnverifiedIn the { type: 'file' } content block of the standard AI SDK message format, the mediaType field declares the MIME type (such as image/png or image/jpeg), and the data field accepts a Buffer, Uint8Array, or base64 string.69% similarUnverifiedGlimpse's video input scenario requires AI SDK 7 support and specifies the sampling frame rate via the video_fps parameter in providerOptions.66% similarVerifiedGoogle AI Studio supports multimodal input, including text, images, audio, and video63% similarUnverifiedFor purely AI-generated vector graphics and stickers with no identifiable people or private property in the image, leaving Model Release and Property Release (or Adobe's Releases column) blank is a compliant practice.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1161028API
curl https://kongchang.com/api/v1/knowledge/claims/1161028MCP
get_claim(id=1161028)