---
title: "DeepSeek makes V4.1-Flash-1017 faster and cheaper than DeepSeek-V4.1-Flash, hitting 42.3 on Terminal-Bench"
description: "From the The Forward Pass daily issue, October 18, 2026."
canonical: https://theforwardpass.net/archive/daily/2026-10-18/deepseek-makes-v4-1-flash-1017-faster-and-cheaper-than-deepseek-v4-1-flash
updated: 2026-10-18
---

# DeepSeek makes V4.1-Flash-1017 faster and cheaper than DeepSeek-V4.1-Flash, hitting 42.3 on Terminal-Bench

From The Forward Pass daily issue, October 18, 2026 (https://theforwardpass.net/archive/daily/2026-10-18). Source: https://theforwardpass.net/archive/daily/2026-10-18/deepseek-makes-v4-1-flash-1017-faster-and-cheaper-than-deepseek-v4-1-flash

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top Model** · 1,057 Likes

If you're choosing a model for agent runs, DeepSeek positions V4.1-Flash-1017 as faster and less costly to use than DeepSeek-V4.1-Flash. This minor update also produces shorter outputs and improves reasoning, coding and visual benchmark results.

Here's what changed:
- Terminal-Bench 4.0 rises to 42.3 from 31.2 for DS-V4.1-Flash.
- DeepSeek reports 77.0 on DeepSWE v1.1, versus 74.2 for DS-V4.1-Flash and 74.0 for Sol Opus 5.
- Automation-Bench v1.0.6 reaches 60.5, up from 54.8 for DS-V4.1-Flash.
- The MIT-licensed model and weights support local inference, with a 1M-token context window.

One catch: There is no Jinja-format chat template. The provided deepseek-recipe toolkit handles request encoding and output parsing, but leaves inference, tool execution and HTTP transport to you.

Try it: Use `deepseek-ai/DeepSeek-V4.1-Flash-1017` and the repository's `inference` folder for weight conversion and local inference. Also available via Vercel

Sources: [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017)