DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash from DeepSeek. It uses the same multimodal Mixture-of-Experts (MoE) architecture, accepts text and image input, and has a context window of up to 1M tokens. DeepSeek reports improved results on reasoning, coding, agentic, and visual benchmarks compared to DeepSeek-V4.1-Flash, along with shorter outputs and faster task completion.

The deepseek-v4.1-flash-1017-maas endpoint is available until at least December 31, 2026. Availability might be extended based on usage and demand. For more information, see Minimum availability for Preview models.

Managed API (MaaS) specifications

View in Model Garden Pricing

Model ID deepseek-v4.1-flash-1017-maas
Modalities
Text Input and output
Image Input only
Audio Not supported
Video Not supported
Capabilities
Consumption options
Supported regions

Model availability

  • Global: global

ML processing

  • Global: global
Quotas
  • global: 1,048,576 maximum output, 1,048,576 context length
Versions
  • deepseek-v4.1-flash-1017-maas
    • Launch stage: Preview
    • Release date: November 16, 2026

Deploy as a self-deployed model

To self-deploy the model, go to the DeepSeek-V4.1-Flash-1017 model card in the Model Garden console and click Deploy model. For more information about deploying open models, see Deploy open models from Model Garden.

What's next