DeepSeek V4.1 Flash 1017 (Max)

DeepSeekDeepSeekOpen WeightMIT · Usage Commercial

Description

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash with the same architecture and API model name deepseek-flash. It delivers substantial gains on reasoning, coding, agentic, and visual benchmarks, with shorter task runtime and output length. It supports a 1M-token context and up to 384K output tokens. Pricing is unchanged from V4.1-Flash: peak rates are $0.30 input, $0.006 cached input, and $1.20 output per million tokens; off-peak rates are half those amounts. Peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays, excluding Chinese public holidays. Legacy API names deepseek-v4-flash and deepseek-v4-flash-vision-exp are now served by this model.

Date de sortie

2026-10-17

Paramètres

763.2B

Longueur du contexte

1.0M

Modalités

image, text

Radar de capacités

general

coding

reasoning

science

agents

multimodal

Classements

Domaine	#Rang	Score	Source
Capacité agentique	33	55.0	LS
Classement codage	19	93.0	AA
Classement général	21	77.0	AA
Classement multimodal	11	67.0	LS
Raisonnement	20	89.0	LB
Science	56	76.0	AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

AutomationBench

60.5%Aut.

Agents' Last Exam

35.4%Aut.

Program Bench

29.1%Aut.

Code

DeepSWE 1.1

77.0%Aut.

NL2Repo

68.2%Aut.

Reasoning

Humanity's Last Exam (no tools, text-only)

44.0%Aut.

Humanity's Last Exam

42.6%Aut.

Terminal-Bench 4.0

42.3%Aut.

Vision

BabyVision

92.5%Aut.

Chartography

83.0%Aut.

ZEROBench

0.51 / 100Aut.

Indices d'évaluation AA

(Artificial Analysis)

Lcr(Artificial Analysis)

82.7

Scicode(UIUC + Argonne National Lab (2024))

55.9

Intelligence Index(Artificial Analysis)

45.1

Hle(Center for AI Safety + Scale AI (2025))

43.3

Terminalbench V4 0

33.8

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))

Multimodal

Vision

Reasoning

General

Agents

Code

Tool Calling

Math

Tarification

Prix d'entrée$0.3 / 1M tokens

Prix de sortie$1.2 / 1M tokens

Prix mixte (3:1)$0.525 / 1M tokens

Prix de lecture cache$0.003 / 1M tokens

Vitesse

Tokens/sec153.7

Délai du premier token0.98s

Temps de réponse14.00s

Classement des Prix par Fournisseur

15 fournisseurs

Moins cher: DeepSeekPlus cher: Prime Inference

FournisseurEntréeSortie

1DeepSeekMoins cher

2Vercel AI Gateway

$0.075

$0.3

3NanoGPT

$0.1

$0.6

4302.AI

$0.15

$0.6

5OpenRouter

$0.15

$0.6

6Merge Gateway

$0.15

$0.6

7LLM Gateway

$0.15

$0.6

8Novita AI

$0.3

$1.2

9Kilo Gateway

$0.3

$1.2

10Venice AI

$0.3

$1.2

11NEAR AI Cloud

$0.3

$1.2

12EmpirioLabs AI

$0.3

$1.2

13Ofox

$0.3

$1.2

14Arcee

$0.3

$1.2

15Prime Inference

$0.3

$1.2

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes

LLM Stats Artificial Analysis