DeepSeek V4.1 Flash 1017 across two providers: 213 tok/s vs 143 tok/s
Same prompt, harness, and reasoning effort compared across two providers: DeepSeek Platform ran 1h30m at 213 tok/s with 99.8% cache hits, OpenCode Go 1h18m at 143 tok/s with 98%.
🧵 FINAL ROUND: DeepSeek-v4.1-Flash-1017 - Same prompt, same harness (DSH), same reasoning effort (high), but two different providers. I'll be making another final post comparing the stats, my thoughts in details, and whether the OpenCode Go subscription is worth it still. DeepSeek Platform (1h 30m 42s): • Cache hit: 99.8% • Uncached input: 91,329 tok • Cached input: 43,253,376 tok • Output: 265,159 tok • Speed: 213 tok/s avg OpenCode Go (1h 18m 31s): • Cache hit: 98% • Uncached input: 182,546 tok • Cached input: 8,274,688 tok • Output: 77,621 tok • Speed: 143 tok/s avg What do you think did better?
This post quotes another post: “DeepSeek V4.1 Flash: DeepSeek Platform vs OpenCode Go on the same prompt”