Unverified50% confidenceFactExact time
Agnes-3.0-Flash is a multimodal model with 33B parameters that supports joint understanding of text, images, and video
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Agnes platform currently provides free API access to the text model Agnes 2.0 Flash, an image generation model, and a video generation model.71% similarUnverifiedAgnes platform's video model supports image-to-video generation and can produce 720P/1080P dynamic videos with audio.67% similarUnverifiedMultimodal large models can simultaneously process images, video frames, and text, and establish semantic associations between these modalities.63% similarUnverifiedQwen3 27B是原生多模态模型，支持视觉输入，弥补了DeepSeek V-Flash无法处理图像的短板63% similarUnverifiedV4.1 Flash is natively multimodal in design, capable of directly viewing and understanding image content.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916666API
curl https://kongchang.com/api/v1/knowledge/claims/916666MCP
get_claim(id=916666)