Compare AI models: DeepSeek V4.1 Flash 1017 vs GPT-6 Luna

DeepSeek V4.1 Flash 1017DeepSeekHollow points use fallbacks · hover for details
GPT-6 LunaOpenAIHollow points use fallbacks · hover for details

ReasoningCodingCost efficiencyContext windowMultimodalTool use

Normalized model capability scores
Model	Reasoning	Coding	Cost efficiency	Context window	Multimodal	Tool use
DeepSeek V4.1 Flash 1017	56/100	100/100	71/100	82/100	33/100	50/100 — Tool calling supported; no comparable benchmark
GPT-6 Luna	50/100 — Reasoning supported; no comparable benchmark	45/100	72/100	98/100	50/100	50/100 — Tool calling supported; no comparable benchmark

Overview

Author

Context length

1.1M

Reasoning

True

Input modalities

Text, Image

Text, Image, Pdf

Output modalities

Text

Providers

Pricing

Input

$0.10/ 1M

Output

$0.60/ 1M

$0.50/ 1M

Cached input

$0.003/ 1M

$0.01/ 1M

MomentumLast 2 mo

Unique users

32K

640K

Completed sessions

528,434

5,079,393

Token share

0.09%

0.31%

Tokens

1.1T+100%

3.5T+100%

AUG 30OCT 24

RetentionWeek 1

Returning users

Pending

66.7%6.5K user-weeks

Related comparisons. Other model pairs to check.