Model index
DeepSeek·DeepSeek V / R

DeepSeek-V3.1

A hybrid reasoning model unifying thinking and non-thinking modes and extending API context to 128K.

LegacyLanguageReasoningCodingAgentOpen weights
MODEL NUMBER286
First public date
2025-08-21
Organization
DeepSeek
Family
DeepSeek V / R
01

Specifications

Only published specifications are shown.

Context
128,000 tokens
Input modalities
Text
Output modalities
Text
Open weights
Yes
Status
Legacy
02

Overview

Release dates

— DeepSeek-V3.1 released model weights. ↗

03

Specifications alongside predecessor

Compared with DeepSeek-V3 ↗

PreviousDeepSeek-V3671B · 128K ctx
CurrentDeepSeek-V3.1— · 128K ctx
04

Architecture & capabilities

05

Release history

Open weights

DeepSeek-V3.1 released model weights.

View source
06

Related models

Select a card to view the related model.

07

Sources

Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.