# Tell HN: Mistrap Pro includes DeepSeek v4.1 Flash 1017

> Source: <https://docs.mistral.ai/models/deepseek-v4-flash-1017>
> Published: 2026-11-01 12:58:35+00:00

October 28, 2026

[License](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE)
Public PreviewThird-partyvv4.1-flash-1017

# DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is a third-party open weight model from DeepSeek, hosted by Mistral, with support for text and image inputs. Ideal for long-context coding and agentic workflows. The model is served without Mistral modifications.

Context

1M

Max output

128k

Price

$0.3

Input/M Tokens

$0.007

Cached input/M Tokens

$1.2

Output/M Tokens

Speed

Performance

Context

1M

Max output

128k

Price

$0.3

Input/M Tokens

$0.007

Cached input/M Tokens

$1.2

Output/M Tokens

Other Models