DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is DeepSeek’s updated multimodal Mixture-of-Experts model for coding, reasoning, and agentic tasks, with native image and text input and a one-million-token context window.
Model
DeepSeek V4.1 Flash 1017 improves on the original V4.1 Flash across software engineering, tool use, reasoning, and visual understanding. DeepSeek reports stronger task performance alongside shorter outputs and reduced task execution time.
The model retains V4.1 Flash’s Causal Encoder-Decoder architecture and compressed sparse attention, designed to reduce the memory and compute required for long-context workloads. It supports image understanding, tool calling, and configurable reasoning effort for multi-step agent workflows.
In DeepSeek’s evaluations, the update improves Terminal-Bench 4.0 from 31.2 to 42.3 and DeepSWE v1.1 from 74.2 to 77.0.
Full results and evaluation settings are available in the DeepSeek model card.
Shared Endpoint
On a Shared Endpoint, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.