DeepSeek V4.1-Flash-1017

mit

DeepSeek-V4.1-Flash-1017 hybrid model with both non-thinking and thinking (default) modes.

Context
1M
Max output
384K
Input price
$0.15/1M tokens
Output price
$0.6/1M tokens
Alias ofdeepseek-flash

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDdeepseek-flash-2026-10-17
Provider DeepSeek
Creator deepseek
Familydeepseek-chat
Licensemit
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output384K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepseek.com/v1/chat/completions
CompletionsPOST
Legacy text completionhttps://api.deepseek.com/v1/completions

Pricing

Input
$0.15
Output
$0.6
Cache write
—
Cache read
$0
Batch in
—
Batch out
—

Family Comparison: deepseek-chat

ModelContextMax outPricing
DeepSeek V4———
DeepSeek V3.2 (Chat)—384K$0.14$0.28
DeepSeek V3.2 (Chat)—384K$0.14$0.28
DeepSeek V4-Flash1M384K$0.14$0.28
DeepSeek V4.1-Flash-10171M384K$0.15$0.6
DeepSeek V3.2 (Chat)128K8K$0.28$0.42
DeepSeek V3.2 (Reasoner)128K64K$0.28$0.42
DeepSeek V41M384K$0.66$1.98
DeepSeek V4-Pro-08131M384K$0.66$1.98

API

GET/v1/models/deepseek/deepseek-flash-2026-10-17

DeepSeek V4.1-Flash-1017

deepseek-flash-2026-10-17

DeepSeek-V4.1-Flash-1017 hybrid model with both non-thinking and thinking (default) modes.

alias → deepseek-flash
Changes · 2 entries
deepseek-flash-2026-10-17createca7a400Nov 2, 2026, 03:02 AM
deepseek-flash-2026-10-17createb2f45bfOct 29, 2026, 03:29 AM