Head to head
DeepSeek V4 Flash vs GPT-4.1 nano
On a blended workload of one million input tokens and three million output tokens, DeepSeek V4 Flash is 1.3× cheaper than GPT-4.1 nano.
| DeepSeek V4 Flash | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Input / MTok | $0.14 | $0.1 |
| Output / MTok | $0.28 | $0.4 |
| Cache read / MTok | $0.0028 | $0.025 |
| Context window | 1,000,000 | 1,047,576 |
| Blended 1M in + 3M out | $0.98 | $1.30 |
| Status | ga | ga |