DeepSeek V4 Flash is ~90% cheaper than GPT 5.4 Mini and ~70% cheaper than Gemini 3.1 Flash Lite For devs pushing ~500M tok/month, this is th…

DeepSeek V4 Flash is ~90% cheaper than GPT 5.4 Mini and ~70% cheaper than Gemini 3.1 Flash Lite For devs pushing ~500M tok/month, this is the difference between: GPT 5.4 Mini: ~394/mo Gemini 3.1 Flash Lite: ~131/mo DeepSeek V4 Flash: ~71/mo ... roughly ~3,900/dev/yr back Deep Agents CLI makes it easy to get started using these models: https://docs.langchain.com/oss/python/deepagents/cli/overview deepseek flash is so cheap that we had to change our aggregation formula in honeycomb to not round away its tiny charges

Source: Harrison Chase (X) | 2026-05-11