DeepSeek: DeepSeek V4 Pro 0423 vs Macaron V1 Venti
They cost about the same for input tokens: DeepSeek: DeepSeek V4 Pro 0423 $0.819366 per M, Macaron V1 Venti $0.825 per M. DeepSeek: DeepSeek V4 Pro 0423 is 1.5× cheaper for output tokens: DeepSeek: DeepSeek V4 Pro 0423 costs $1.638732 per M and Macaron V1 Venti costs $2.475 per M. Both read up to 1,048,576 tokens of context.
| DeepSeek: DeepSeek V4 Pro 0423 | Macaron V1 Venti | |
|---|---|---|
| Model id | deepseek/deepseek-v4-pro | mindai/macaron-v1-venti |
| Input | $0.819366 per M | $0.825 per M |
| Output | $1.638732 per M | $2.475 per M |
| Context length | 1,048,576 tokens | 1,048,576 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | deepseek | novita |
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.