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.
Model APIs
With Model APIs, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.
modal endpoint create --shared --model deepseek-ai/DeepSeek-V4.1-Flash-1017 Dedicated Endpoint
DocsA Dedicated Endpoint is your own deployment of DeepSeek V4.1 Flash 1017, on an inference stack that Modal tunes and autoscales. Bring fine-tuned weights if you have them. Compute is billed by the second, and only while it runs.
modal endpoint create --model deepseek-ai/DeepSeek-V4.1-Flash-1017 Related resources
Latest updates
Scaling Intelligence: A landmark commission and exhibition
Sandbox resourcing: burst, don't reserve
Why you're paying for capacity you aren't using, and how to pay only for what you use.
Modal becomes a gVisor maintainer
Modal runs upwards of 40 million gVisor containers every day. Here's why we bet on it, what we've built into it, and where we want to take it next.