DeepSeek V4 Flash 0423 vs GPT-6 Luna Pro

Price, context window & benchmark comparison

DeepSeek V4 Flash 0423

DeepSeek

$0.0886 / $0.18

Input / Output · per 1M tokens

GPT-6 Luna Pro

OpenAI

$0.10 / $0.50

Input / Output · per 1M tokens

Compare different models

Verdict: DeepSeek V4 Flash 0423 is 45% cheaper than GPT-6 Luna Pro on a typical 3:1 input/output mix. GPT-6 Luna Pro has the larger context window (1.1M vs 1M).

	DeepSeek V4 Flash 0423	GPT-6 Luna Pro
Input price / 1M	$0.0886	$0.10
Output price / 1M	$0.18	$0.50
Blended price (3:1)	$0.11	$0.20
Cached input / 1M	$0.0177	$0.01
Context window	1M	1.1M
Max output	384K	128K
Intelligence index	24.2	—
Coding index	56.2	—
Providers	—	6
Best provider uptime (30m)	—	100.0%
Vision input	No	Yes
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-04-24	2026-09-22
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, DeepSeek V4 Flash 0423 or GPT-6 Luna Pro?

DeepSeek V4 Flash 0423 is 45% cheaper than GPT-6 Luna Pro on a typical 3:1 input/output mix.

DeepSeek V4 Flash 0423 vs GPT-6 Luna Pro: which has a bigger context window?

DeepSeek V4 Flash 0423: 1,048,576 tokens. GPT-6 Luna Pro: 1,050,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4 Flash 0423 ≈ $265.80, GPT-6 Luna Pro ≈ $450.00.

More comparisons