alt Hacker NewsI recently made an AI Agent and surprisingly coding with DeepSeek V4 Flash is quite cheap. It probably has to do with the aggressive prompt caching. I'm using OpenRouter with Novita AI as the preferred provider.
Replies
kagamino • yesterday at 5:21 PM
Same here, deepseek v4 flash on opencode go. It's cheap, fats and good enough to follow my instructions
➕ show 1 reply
Deepseek v4 via deepseek themselves is significantly cheaper.
Because (1) Huawei collab and (2) vLLM etc dont implement half of the inference optimisations deepseek proposed in their paper.