DeepSeek Releases V4 Flash Vision API for Image Understanding
aigclink · x · 2026-08-21
DeepSeek has released API documentation for the deepseek-v4-flash-vision-exp model, enabling image understanding within text conversations. The model supports describing images, OCR, and analyzing charts.
Formats & Limits:
- Supports JPEG, PNG, GIF, and WebP.
- Three input methods:
- Base64 Inline: Best for local files, subject to a 48MiB request limit.
- Public URL: Max 32MiB, must download within 60s.
- Files API: Best for reuse or large files (up to 64MiB), referenced via fileid.
The API is OpenAI-compatible, with Python and cURL examples provided.
Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→
More from Models
- Muse Spark vs Qwen and GLM: US open models still trail on agentic tasks — zsakib_ · 2026-10-16
- Muse Spark 816B gets llama.cpp support just 30 minutes after release — ngxson · 2026-10-16
- 24 AI Systems Recommend $314 Per Visit in Care vs Physicians' $97, a 3.2x Gap — dvir_a · 2026-10-16
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16
- Scale AI launches muse spark open: 816B-param MoE with 1M context, billed as top US open-weight model — jiayi_pirate · 2026-10-16
- NVIDIA HF listing for Qwen3.8-Flash-Next-FP4-Local leaks unannounced Qwen3.8 model — TheZachMueller · 2026-10-16