token.app › Compare › GPT-6 Luna Pro vs DeepSeek V4 Flash 0731
GPT-6 Luna Pro vs DeepSeek V4 Flash 0731
GPT-6 Luna Pro is 3.3× cheaper per token on a blended 3:1 basis. GPT-6 Luna Pro accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-6 Luna Pro | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | OpenAI | DeepSeek |
| Input $/1M | $0.100 | $0.440 |
| Output $/1M | $0.500 | $1.32 |
| Blended $/1M | $0.200 | $0.660 |
| Context window | 1.1M | 1.0M |
| Max output | 128K | 131K |
| Released | Sep 2026 | Jul 2026 |
| Licence | Proprietary | Open weights |
Choose GPT-6 Luna Pro if…
- Costs less per token — $0.200 vs $0.660 blended
- Larger context window (1.1M)
- Newer model (released Sep 2026)
Choose DeepSeek V4 Flash 0731 if…
- Open weights — self-hostable
FAQ
Which is better, GPT-6 Luna Pro or DeepSeek V4 Flash 0731?
We do not hold independently-run benchmark scores covering both GPT-6 Luna Pro and DeepSeek V4 Flash 0731, so we make no quality claim. Their pricing and specifications are compared on this page.
Is GPT-6 Luna Pro cheaper than DeepSeek V4 Flash 0731?
GPT-6 Luna Pro is cheaper: $0.200 versus $0.660 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.440. Output alone: $0.500 vs $1.32.
What context windows do GPT-6 Luna Pro and DeepSeek V4 Flash 0731 have?
GPT-6 Luna Pro: 1,050,000 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes GPT-6 Luna Pro and DeepSeek V4 Flash 0731?
GPT-6 Luna Pro is made by OpenAI. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons