DeepSeek: DeepSeek V4 Flash 0423 vs NVIDIA: Nemotron 3 Super
They cost about the same for input tokens: DeepSeek: DeepSeek V4 Flash 0423 $0.08358 per M, NVIDIA: Nemotron 3 Super $0.085 per M. DeepSeek: DeepSeek V4 Flash 0423 is 2.4× cheaper for output tokens: DeepSeek: DeepSeek V4 Flash 0423 costs $0.16716 per M and NVIDIA: Nemotron 3 Super costs $0.40 per M. About the same: DeepSeek: DeepSeek V4 Flash 0423 takes up to 1,048,576 tokens of context and NVIDIA: Nemotron 3 Super up to 1,000,000.
| DeepSeek: DeepSeek V4 Flash 0423 | NVIDIA: Nemotron 3 Super | |
|---|---|---|
| Model id | deepseek/deepseek-v4-flash | nvidia/nemotron-3-super-120b-a12b |
| Input | $0.08358 per M | $0.085 per M |
| Output | $0.16716 per M | $0.40 per M |
| Context length | 1,048,576 tokens | 1,000,000 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | deepseek | nvidia |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.