DeepSeek V4.1 Flash 1017

New

deepseek/deepseek-v4.1-flash-20261017

DeepSeek V4.1 Flash 1017 is a text and image input model with a text output. It has a context length of 1,048,576 tokens and supports tools and reasoning. The model is open-weight, with input priced at $0.30 per million tokens and output at $1.20 per million tokens.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providerdeepseek
releasedOct 17, 2026
context1.0M
input / M$0.30

Specifications

What the API gives you

Context window
1.0M tokens
Max output
393K tokens
Input price
$0.30 / 1M tokens
Output price
$1.20 / 1M tokens
Cache read
$0.006 / 1M tokens
Modalities
text, image → text
Knowledge cutoff
—
Released
Oct 17, 2026

Measured evidence

Public benchmark record

Design Arena Coding
1333 Elo2026-10-20
Design Arena UI
1309 Elo2026-10-20
Design Arena Website
1311 Elo2026-10-20
LMArena WebDev‡
1664 Elo2026-10-19max effort

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Frontend & UIEstablished evidence

    82% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    36% of intended weighted task evidence across 2 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 3 of 3 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Debugging & Code ReviewProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

  1. #6Best LLM for Coding
  2. #8Best LLM for Frontend & UI

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.