Errors & Fixes — CodexHow
A catalogue of specific mistakes developers actually hit, each with the cause and a one-line fix — not a general troubleshooting essay. If a request silently repriced, a cache silently didn't hit, or a config flag silently stopped working the way it used to, the specific answer is almost certainly here, sourced from the exact OpenAI page that documents the real behaviour.
Every entry follows the same shape on purpose: what the mistake looks like, why it actually happens, and the smallest fix that resolves it — searchable and skimmable rather than something you have to read start to finish, and worth bookmarking as a group.
Codex CLI Defaults to Sol, Not the Codex Model
The 272K Cliff Reprices the Whole Request
Workspace-write Turns Off Network Access
Git Directory Stays Protected as a gitdir File
A Non-Version-Controlled Folder Starts Read-Only
The --full-auto Flag Is Deprecated
prompt_cache_key Is Required on GPT-5.6 and Later
Cache Writes Cost More, Not Less, on GPT-5.6
More Than 4 Cache Breakpoints in One Request
Cache Breakpoint Lookback Exceeds 20 Blocks
Tier 2 to Tier 3 Does Not Raise Your RPM
Batch Completion Window Can't Go Below 24 Hours
Batch API Not Available on Bedrock or Vertex
Flex and Batch Cost the Same but Aren't Identical
Fast Mode Is Not Offered on Every Model
GPT-5.4 Cyber Pricing Is Not Published
A Destructive MCP Tool Call Still Needs Approval
Web Search Defaults to Cached Results, Not Live
The Data-Residency Uplift on Regional Endpoints
Bedrock Pricing Does Not Match OpenAI Direct
Unsuffixed GPT-5.6 Is Just an Alias for Sol
Only gpt-5.3-codex Publishes Reasoning Effort
GPT-5.4 Pro's Context Window vs Tier 1 TPM