DeepSeek V4.1 Flash 1017 Max vs GPT-6 Luna Max compared

DeepSeek V4.1 Flash 1017 Max leads the intelligence index 32.6 to 27.9. Compare price, speed, latency and a clear verdict.

Metric	DeepSeek V4.1 Flash 1017 (Max)	GPT-6 Luna (Max)
Intelligence Index	32.6	27.9
Input price (per 1M tokens)	$0.30	$0.10
Output price (per 1M tokens)	$1.20	$0.50
Output speed (tokens/s)	162	121
Time to first token	1.2s	2.0 min
Release date	2026-10-17	2026-09-22

Metric

DeepSeek V4.1 Flash 1017 (Max)

GPT-6 Luna (Max)

Intelligence Index

32.6

27.9

Input price (per 1M tokens)

$0.30

$0.10

Output price (per 1M tokens)

$1.20

$0.50

Output speed (tokens/s)

162

121

Time to first token

1.2s

2.0 min

Release date

2026-10-17

2026-09-22

DeepSeek V4.1 Flash 1017 (Max) (DeepSeek) and GPT-6 Luna (Max) (OpenAI) meet here on their recorded benchmark, price and speed data. Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test. The widest gap is the wait for the first token: 1.2 seconds for DeepSeek V4.1 Flash 1017 Max against 2.0 minutes for GPT-6 Luna Max.

Throughput and time to first token

Measured output speed is 162 tokens per second for DeepSeek V4.1 Flash 1017 Max and 121 tokens per second for GPT-6 Luna Max. DeepSeek V4.1 Flash 1017 Max is ahead by 34% on throughput. Before any text appears, DeepSeek V4.1 Flash 1017 Max takes 1.2 seconds and GPT-6 Luna Max 2.0 minutes. GPT-6 Luna Max waits 100 times as long before its first token. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

For a 600-token response, first token plus generation comes to roughly 4.9 seconds on DeepSeek V4.1 Flash 1017 Max and 2.1 minutes on GPT-6 Luna Max.

Which is newer

GPT-6 Luna Max came first, on September 22, 2026; DeepSeek V4.1 Flash 1017 Max followed on October 17, 2026. That is close enough to count them as the same generation.

The headline benchmark

The catalogue puts DeepSeek V4.1 Flash 1017 Max at 32.6 and GPT-6 Luna Max at 27.9 on its intelligence index. A lead of this size is hard to dismiss as noise. Put another way, GPT-6 Luna Max would need 17% more on this index to draw level.

Across the 109 active models with an intelligence score in the catalogue, DeepSeek V4.1 Flash 1017 Max ranks 45th and GPT-6 Luna Max ranks 62nd.

There are no coding or math index scores for either model in the catalogue, which keeps this comparison at the aggregate level.

Price per token

DeepSeek V4.1 Flash 1017 Max lists $0.30 per million input tokens and $1.20 per million output tokens; GPT-6 Luna Max lists $0.10 and $0.50. DeepSeek V4.1 Flash 1017 Max costs 2.4 times as much per output token.

A reference job of 1 million input tokens and 200,000 output tokens costs $0.54 with DeepSeek V4.1 Flash 1017 Max and $0.20 with GPT-6 Luna Max, so GPT-6 Luna Max saves $0.34. A bigger example, writing 2,000 drafts of 2,000 output tokens from 300-token prompts, costs $4.98 on DeepSeek V4.1 Flash 1017 Max and $2.06 on GPT-6 Luna Max: a gap of $2.92. On a 3:1 blend of input to output tokens, that works out to $0.525 versus $0.20 per million.

Value for money

Per point of intelligence index, DeepSeek V4.1 Flash 1017 Max costs $0.016 of blended price per million tokens and GPT-6 Luna Max $0.0072. DeepSeek V4.1 Flash 1017 Max costs 2.2 times as much per point, which is the price of its lead.

Quick answers

Is DeepSeek V4.1 Flash 1017 Max better than GPT-6 Luna Max?

Neither wins everywhere: DeepSeek V4.1 Flash 1017 Max scores higher on the intelligence index, 32.6 to 27.9; GPT-6 Luna Max is 62% cheaper on blended price; and DeepSeek V4.1 Flash 1017 Max streams output 1.3 times as fast.

Which model has lower latency?

DeepSeek V4.1 Flash 1017 Max generates output faster, at 162 tokens per second against 121 tokens per second. DeepSeek V4.1 Flash 1017 Max reaches its first token sooner (1.2 seconds against 2.0 minutes).

Are DeepSeek V4.1 Flash 1017 Max and GPT-6 Luna Max from the same company?

DeepSeek V4.1 Flash 1017 Max is made by DeepSeek and GPT-6 Luna Max by OpenAI. DeepSeek V4.1 Flash 1017 Max was released on October 17, 2026 and GPT-6 Luna Max on September 22, 2026.

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

When were DeepSeek V4.1 Flash 1017 Max and GPT-6 Luna Max released?

DeepSeek V4.1 Flash 1017 Max is newer. It was released on October 17, 2026, 25 days after GPT-6 Luna Max (September 22, 2026).

Final whistle

In one line: on balance the numbers favour DeepSeek V4.1 Flash 1017 Max, though GPT-6 Luna Max keeps a case of its own. Pick DeepSeek V4.1 Flash 1017 Max if users are waiting on the first word and you need the higher overall score (32.6 against 27.9). Pick GPT-6 Luna Max if cost matters ($0.50 against $1.20 per million output tokens).

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the DeepSeek V4.1 Flash 1017 (Max) and GPT-6 Luna (Max) pages. The AI Benchmark methodology explains how that data is collected and shown.