Expired60% confidenceFactExact time
The /fast command in Codex CLI switches the session to speed-priority mode and consumes roughly twice the tokens compared to standard mode.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
The Complete Guide to All 42 Codex CLI Commands: From Beginner to Precision AI Programming
bilibili下班学AI5/29/2026
Related Claims
UnverifiedOpenAI按TPM（Tokens Per Minute）和RPM（Requests Per Minute）双重限制进行速率控制60% similarUnverifiedAfter enabling MTP, inference speed fluctuates significantly, sometimes exceeding 40 tokens/second and sometimes dropping to 25 tokens/second.59% similarUnverifiedLocal model inference speed is approximately 1–10 tokens/second, while cloud-based APIs can reach 50–150 tokens/second.57% similarUnverifiedFor general users, it is recommended to disable Ultra and Fast by default, enabling Fast only when tokens are plentiful and Ultra only when tasks are very complex.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49521API
curl https://kongchang.com/api/v1/knowledge/claims/49521MCP
get_claim(id=49521)