token.app › Compare › R1 0528 vs GPT-5.6 Luna
R1 0528 vs GPT-5.6 Luna
GPT-5.6 Luna is 4.1× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| R1 0528 | GPT-5.6 Luna | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Input $/1M | $0.500 | $0.100 |
| Output $/1M | $2.15 | $0.600 |
| Blended $/1M | $0.912 | $0.225 |
| Context window | 164K | 1.1M |
| Max output | 33K | 128K |
| Released | May 2025 | Jul 2026 |
| Licence | Open weights | Proprietary |
Choose R1 0528 if…
- Open weights — self-hostable
Choose GPT-5.6 Luna if…
- Costs less per token — $0.225 vs $0.912 blended
- Larger context window (1.1M)
- Newer model (released Jul 2026)
FAQ
Which is better, R1 0528 or GPT-5.6 Luna?
We do not hold independently-run benchmark scores covering both R1 0528 and GPT-5.6 Luna, so we make no quality claim. Their pricing and specifications are compared on this page.
Is R1 0528 cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $0.912 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.100. Output alone: $2.15 vs $0.600.
What context windows do R1 0528 and GPT-5.6 Luna have?
R1 0528: 163,840 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes R1 0528 and GPT-5.6 Luna?
R1 0528 is made by DeepSeek. GPT-5.6 Luna is made by OpenAI.