Testing DeepSeek-V4-Flash: 37 API Calls in Codex CLI Cost Only $0.04

cedric_chee · x · 2026-07-31

A developer tested the newly released DeepSeek-V4-Flash within Codex CLI, comparing the differences between 'max' and 'high' reasoning modes.

The task involved 37 API requests, took 17 minutes, consumed roughly 3.79 million tokens, and cost only $0.04 in total. The author noted that the 'max' mode generated around 130k voxels, significantly more than the 76k in 'high' mode, suggesting the model might be heavily optimized for benchmarks.

Related event: DeepSeek-V4-Flash Agent Capabilities Tested at Ultra-Low Cost(3 posts)→

Original post →

More from coding & agent

coding & agent channel →