DeepSeek V4 Pro 0423 vs DeepSeek V4.1 Flash
Price, context window & benchmark comparison
VS
Compare different models
Verdict: DeepSeek V4.1 Flash is 5.6× cheaper than DeepSeek V4 Pro 0423 on a typical 3:1 input/output mix. DeepSeek V4.1 Flash scores higher on the Artificial Analysis Intelligence Index (39.5 vs 30.4).
| DeepSeek V4 Pro 0423 | DeepSeek V4.1 Flash | |
|---|---|---|
| Input price / 1M | $0.94 | $0.14 |
| Output price / 1M | $1.88 | $0.42 |
| Blended price (3:1) | $1.17 | $0.21 |
| Cached input / 1M | $0.0783 | $0.0042 |
| Context window | 1M | 1M |
| Max output | 384K | 131K |
| Intelligence index | 30.4 | 39.5 |
| Coding index | 59.4 | — |
| Providers | 16 | 26 |
| Best provider uptime (30m) | 100.0% | 100.0% |
| Vision input | No | Yes |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-04-24 | 2026-09-10 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, DeepSeek V4 Pro 0423 or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is 5.6× cheaper than DeepSeek V4 Pro 0423 on a typical 3:1 input/output mix.
DeepSeek V4 Pro 0423 vs DeepSeek V4.1 Flash: which has a bigger context window?
DeepSeek V4 Pro 0423: 1,048,576 tokens. DeepSeek V4.1 Flash: 1,048,576 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: DeepSeek V4 Pro 0423 ≈ $2,819, DeepSeek V4.1 Flash ≈ $490.00.
More comparisons
DeepSeek V4 Pro 0423 vs GLM 5.3 PrimeDeepSeek V4 Pro 0423 vs Qwen3.8 Max PrimeDeepSeek V4 Pro 0423 vs Command A+DeepSeek V4 Pro 0423 vs GPT-6 Luna ProDeepSeek V4 Pro 0423 vs GPT-6 LunaDeepSeek V4 Pro 0423 vs GPT-6 Sol ProDeepSeek V4 Pro 0423 vs GPT-6 SolDeepSeek V4 Pro 0423 vs Claude Opus 5.5DeepSeek V4 Pro 0423 vs MiMo-V2.6-Pro-UltraSpeedDeepSeek V4 Pro 0423 vs MiMo-V2.6-FlashDeepSeek V4 Pro 0423 vs Grok 4.7DeepSeek V4 Pro 0423 vs Qwen3.8 Omni FlashDeepSeek V4 Pro 0423 vs GLM 5.3 FlashXDeepSeek V4 Pro 0423 vs GPT-6 AstraDeepSeek V4 Pro 0423 vs GPT-6 Astra ProDeepSeek V4 Pro 0423 vs Qwen3.8 Max (0902)DeepSeek V4.1 Flash vs GLM 5.3 PrimeDeepSeek V4.1 Flash vs Qwen3.8 Max PrimeDeepSeek V4.1 Flash vs Command A+DeepSeek V4.1 Flash vs GPT-6 Luna ProDeepSeek V4.1 Flash vs GPT-6 LunaDeepSeek V4.1 Flash vs GPT-6 Sol ProDeepSeek V4.1 Flash vs GPT-6 SolDeepSeek V4.1 Flash vs Claude Opus 5.5