review error eats up 5hr limit
What version of Codex CLI is running?
v0.121.0
What subscription do you have?
plus
Which model were you using?
gpt-5.1mini
What platform is your computer?
macos
What terminal emulator and version are you using (if applicable)?
Ghostty
What issue are you seeing?
if i review code using gpt-5.1-codex-mini, it eats up around 25% of my 5hr right away even without processing. It was the first command after the 5h reset.
Review the current code changes (staged, unstaged, and untracked files) and provide prioritized findings.
■ {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.1-codex-mini' model is not supported when using Codex with a ChatGPT account."}}
<< Code review finished >>
• Review was interrupted. Please re-run /review and wait for it to complete.
• Fast mode set to off
> Code review started: current changes <<
⚠ MCP client for codex_apps failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport [rmcp::transport::worker::WorkerTransport<rmcp::t
ransport::streamable_http_client::StreamableHttpClientWorker<codex_rmcp_client::rmcp_client::StreamableHttpResponseClient>>] error: Client error: error sending request for url
(https://chatgpt.com/backend-api/wham/apps), when send initialize request
⚠ MCP startup incomplete (failed: codex_apps)
■ {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.1-codex-mini' model is not supported when using Codex with a ChatGPT account."}}
<< Code review finished >>
What steps can reproduce the bug?
set model to gpt-5.1-codex-mini, do a /review uncommited changes against base, it will show error, try again.
Do a /status and see 5h limit go down significantly.
What is the expected behavior?
5h shouldn't go down at all from a server error.
Additional information
_No response_
10 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
5.1 is not uspported.
switch to 5.4mini , it will work
That’s not the bug Sent from my iPhoneOn Apr 16, 2026, at 4:22 PM, Mahkhmood9 @.***> wrote:Mahkhmood9 left a comment (openai/codex#18194)
5.1 is not uspported.
switch to 5.4mini , it will work
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>
WHAT YOU DONT UNDERSTAND
The 'gpt-5.1-codex-mini' model is not supported
happens because you are on the "FREE" plan
oh my god
my hero, @etraut-openai please close this
I’m on plus plan. The bug is that if someone accidentally has the model selected as such, it will eat up the tokens, and this should be fixed. Did you actually read what the bug is?Sent from my iPhoneOn Apr 19, 2026, at 3:06 PM, Mahkhmood9 @.***> wrote:Mahkhmood9 left a comment (openai/codex#18194)
That’s not the bug Sent from my iPhoneOn Apr 16, 2026, at 4:22 PM, Mahkhmood9 @.*> wrote:Mahkhmood9 left a comment (openai/codex#18194)
5.1 is not uspported.
switch to 5.4mini , it will work
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.*>
WHAT YOU DONT UNDERSTAND
The 'gpt-5.1-codex-mini' model is not supported
happens because you are on the "FREE" plan
oh my god
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>
you edited your message
How are you supporting codex while you can’t decipher a bug report? Let me rephrase: if I accidentally set it to 5.1mini codex and then I accidentally start a /review, it will eat up around 50% of my tokens after giving me an error. How is this not a big?Sent from my iPhoneOn Apr 20, 2026, at 7:35 AM, Mahkhmood9 @.***> wrote:Mahkhmood9 left a comment (openai/codex#18194)
That’s not the bug Sent from my iPhoneOn Apr 16, 2026, at 4:22 PM, Mahkhmood9 @.*> wrote:Mahkhmood9 left a comment (openai/codex#18194)
5.1 is not uspported.
switch to 5.4mini , it will work
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.*>
you edited your message
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>
openai employes please dont come after me , im from somaliland and 20$ is a lot of money for me ,
but I really enjoy the product , see it as a little agent to train your dataset :)
Just abuse the free trial dude
<img width="731" height="940" alt="Image" src="https://github.com/user-attachments/assets/87e29c9a-22ad-4c04-8744-39c412cfe021" />
I’m on the plus plan Sent from my iPhoneOn Apr 20, 2026, at 12:12 PM, Mahkhmood9 @.***> wrote:Mahkhmood9 left a comment (openai/codex#18194)
How are you supporting codex while you can’t decipher a bug report
Just abuse the free trial dude
image.png (view on web)
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>