Head to head
GPT-4.1 nano vs DeepSeek V4 Flash
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.
| GPT-4.1 nano | DeepSeek V4 Flash | |
|---|---|---|
| Provider | OpenAI | DeepSeek |
| Input / MTok | $0.1 | $0.14 |
| Output / MTok | $0.4 | $0.28 |
| Cache read / MTok | $0.025 | $0.0028 |
| Context window | 1,047,576 | 1,000,000 |
| Blended 1M in + 3M out | $1.30 | $0.98 |
| Status | ga | ga |