The October 17 update to DeepSeek-V4.1-Flash, with gains across reasoning, coding, agentic tasks and visual benchmarks, and shorter outputs that finish tasks faster and cheaper. Image input and a 1M-token context window
Context Length: 1,048,576 tokens
multimodal
text_generation
featured
recently_added
DeepSeek
API
Loading editor...
MegaNova - AI Inference Cloud for Characters & Enterprise