Model•active

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is the current model served by the deepseek-flash API alias, with a one-million-token context window and native image understanding.

Official siteVerified Oct 3, 2026

Overview

DeepSeek documents up to 384K output tokens, text and image input, thinking and non-thinking modes, tool calls, JSON output, Responses API support, and Anthropic-compatible access.

Model specifications

Family: DeepSeek V4
Context: 1,000,000 tokens
Input: Text, Image
Output: Text
Open weights: No
Capabilities: Reasoning, Vision, Tool Use, Function Calling, Structured Output

Related entities

Related by Develops

Companyactive

DeepSeek

DeepSeek develops language models, an API platform, and agent-oriented model tooling, including hosted DeepSeek V4 models and open-weight DeepSeek V3 and R1 research families.

Available Via

APIactive

DeepSeek API

DeepSeek API provides access to the current DeepSeek V4 models through OpenAI-compatible and Anthropic-compatible interfaces.

Belongs To

Model Familyactive

DeepSeek V4

DeepSeek V4 is a DeepSeek model family represented in iilib by DeepSeek V4 Pro and DeepSeek V4.1 Flash.