Codex throughput still lags H100, but is already usable
TheZachMueller · x · 2026-07-20
Update on Codex throughput:
- It still falls far short of a dedicated H100 node, which is expected because the node only has 10GbE Ethernet.
- Even so, the speed is described as very usable overall.
- The author adds that H100 is around 200–300 tokens/sec per user depending on concurrency.
- A follow-up note says Codex ended the night at roughly doubling tokens/sec per user.
Related event: Codex Doubles Per-User Throughput(2 posts)→
More from coding & agent
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Agile co-author Ron Jeffries publishes 'Resist AI', urging developers to push back — mborch · 2026-09-11