Codex CLI cannot use Luna Reserve after standard usage limit is exhausted

[kubrick06010]

Summary

Codex CLI appears unable to use the Luna Reserve entitlement after the standard usage limit is exhausted, even though the same ChatGPT account has Luna Reserve available in Codex App.

Reproduction

1. Use the same ChatGPT Plus account in Codex App and Codex CLI.
2. In Codex CLI 0.149.1, select model gpt-5.6-luna.
3. Exhaust the standard 5-hour limit.
4. Run /status.
5. Send a minimal prompt such as: Reply only with: OK.

Observed behavior

Codex CLI reports:

5h limit: 0% left
Weekly limit: 73% left

The minimal prompt fails with:

You've hit your usage limit.

At the same time, Codex App, using the same account, shows:

Luna Reserve: 100% remaining

Expected behavior

If Luna Reserve is intended to be available across Codex clients, the CLI should automatically use the reserve after the standard allowance is exhausted, or clearly explain that the entitlement is App-only.

Environment

• Codex CLI: 0.149.1
• Plan: ChatGPT Plus
• Model: gpt-5.6-luna
• Authentication: ChatGPT account

The CLI already appears to support multiple rate-limit snapshots generically, so this may be an entitlement/request-context parity issue rather than only a /status display issue.

Could you clarify whether Luna Reserve is intentionally limited to Codex App, or whether ChatGPT-authenticated Codex CLI sessions should be able to use the same reserve entitlement?

[github-actions]

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

• luna reserve on goals #40744

Powered by Codex Action

[kubrick06010]

Thanks. I reviewed #40744, and I don't believe this is a duplicate.

#40744 is about Codex App Goals: after pausing/resuming a Goal, model/effort switching does not work, which prevents the Goal from continuing in Luna Reserve mode.

This issue is specifically about Codex CLI. There are no Goals involved. With the same ChatGPT Plus account, Codex App shows Luna Reserve: 100% remaining, while Codex CLI 0.149.1 running gpt-5.6-luna has the standard 5h bucket exhausted and rejects even Reply only with: OK with You've hit your usage limit.

So the execution paths are different:

• luna reserve on goals #40744: Codex App → Goals → resume/model-switch behavior → Luna Reserve
• Codex CLI cannot use Luna Reserve after standard usage limit is exhausted #40939: Codex CLI → standard allowance exhausted → gpt-5.6-luna → no access to Luna Reserve

They may share an underlying Luna Reserve entitlement/routing problem, but #40744 does not cover CLI behavior or CLI/App entitlement parity. I'll keep this open unless maintainers confirm that Luna Reserve is intentionally App-only or that both issues have the same underlying fix.

[scooter-lacroix]

Any updates on this issue? Can confirm on codex v0.151.0 I am experiencing the same.

[StdCarrot]

I did some additional testing and was able to narrow this down further.

After exhausting my regular Codex usage allowance, I found that Luna Reserve appears to use a separate model ID:

gpt-reserve

rather than:

gpt-5.6-luna

I confirmed that gpt-reserve can be invoked directly from Codex CLI and successfully uses the Luna Reserve allowance even after the regular usage limit has been reached.

For example:

codex -m gpt-reserve -c model_reasoning_effort='"xhigh"'

works after the regular usage allowance is exhausted.

In contrast, explicitly selecting:

codex -m gpt-5.6-luna

still hits the regular usage limit.

I also observed that the Luna Reserve model supports reasoning efforts up to:

low, medium, high, xhigh

max does not appear to be supported for gpt-reserve.

However, gpt-reserve does not appear to be exposed through the normal Codex model catalog / model/list, even though the CLI can execute it when the model ID is specified manually.

So the behavior appears to be:

• gpt-5.6-luna → exposed normally, uses the regular Codex allowance
• gpt-reserve → uses the Luna Reserve allowance and is executable when specified manually
• gpt-reserve → not exposed in the normal model list/catalog
• gpt-reserve → supports reasoning effort up to xhigh

This suggests that the issue may not be that Codex CLI cannot use Luna Reserve, but rather that the reserve model is not being exposed/discovered by the CLI.

It may be worth exposing gpt-reserve in the model catalog when Luna Reserve is available for the authenticated account, so users can select it normally without having to know and manually specify the internal model ID.

[crisdosaygo]

Is this the fix? @StdCarrot

[StdCarrot]

This is from OpenAI's model API, so, it can not fix by this projects.
Anyway, you can use the model using commandline or customize model_cache.json.