Unverified50% confidenceFactExact time
Decision 3.0 image input supports multiple images per request, with a maximum resolution of 1.6 MP.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedDecision Models support vision capabilities; Clave and Clave Flash require version 0.3.5.1 or above and must include vision weights, images must be encoded as base64 (URLs and dataURLs are not accepted), all questions share the same batch of images, and state is still required.70% similarUnverifiedOpenAI GPT-4V adopts a tile-plus-thumbnail strategy that dynamically adjusts token consumption based on image resolution, and high-resolution images may be cut into multiple 512×512 tiles for separate processing.68% similarVerifiedTencent released Image 3.5 Preview, with generation capability improved by approximately 30% over the previous generation, supporting fusion retouching with up to 5 reference images, a maximum resolution of 2K, and generating one 2K image via Tencent Cloud API for only 0.15 yuan with no charge for rejected images.67% similarUnverifiedDecision 3.0 can process text and images simultaneously in a single call67% similarUnverified工作流为每个视频概念触发3次独立的图像生成，而非一次，以提供风格基准测试的选样空间63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003460API
curl https://kongchang.com/api/v1/knowledge/claims/1003460MCP
get_claim(id=1003460)