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.
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Dev workflow: Astra for tedious tasks, Claude for ideas not implementation — menhguin · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16