R1 0528 vs DeepSeek V4 Flash 0731
Price, context window & benchmark comparison
VS
Compare different models
Verdict: DeepSeek V4 Flash 0731 is 8.5× cheaper than R1 0528 on a typical 3:1 input/output mix. DeepSeek V4 Flash 0731 has the larger context window (1M vs 164K).
| R1 0528 | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Input price / 1M | $0.50 | $0.0434 |
| Output price / 1M | $2.15 | $0.30 |
| Blended price (3:1) | $0.91 | $0.11 |
| Cached input / 1M | $0.35 | $0.035 |
| Context window | 164K | 1M |
| Max output | 33K | 944K |
| Intelligence index | — | — |
| Coding index | — | 69.1 |
| Providers | — | 27 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | No | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2025-05-28 | 2026-07-31 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, R1 0528 or DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is 8.5× cheaper than R1 0528 on a typical 3:1 input/output mix.
R1 0528 vs DeepSeek V4 Flash 0731: which has a bigger context window?
R1 0528: 163,840 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: R1 0528 ≈ $2,075, DeepSeek V4 Flash 0731 ≈ $236.80.
More comparisons
R1 0528 vs Gemini 4 CarbonR1 0528 vs Claude Fable 5.2R1 0528 vs Gemini Omni 1.2 FlashR1 0528 vs Gemini Omni 1.1 FlashR1 0528 vs Hy4R1 0528 vs GLM 5.3 FlashX LegalR1 0528 vs GPT-6.1 TerraR1 0528 vs GPT-6.1 Terra ProR1 0528 vs Kimi K3.1 ProR1 0528 vs MiniMax M3.1 FlashR1 0528 vs DeepSeek V4.1 Flash 1017R1 0528 vs Nemotron 3.5 Super VLR1 0528 vs Gemini 4 ArgonR1 0528 vs Claude Haiku 5.5R1 0528 vs Nano Banana 2.1R1 0528 vs Mistral Large 4DeepSeek V4 Flash 0731 vs Gemini 4 CarbonDeepSeek V4 Flash 0731 vs Claude Fable 5.2DeepSeek V4 Flash 0731 vs Gemini Omni 1.2 FlashDeepSeek V4 Flash 0731 vs Gemini Omni 1.1 FlashDeepSeek V4 Flash 0731 vs Hy4DeepSeek V4 Flash 0731 vs GLM 5.3 FlashX LegalDeepSeek V4 Flash 0731 vs GPT-6.1 TerraDeepSeek V4 Flash 0731 vs GPT-6.1 Terra Pro