gpt-5.5 capacity errors and recovered session returns with only ~60-70% context left

Open 💬 3 comments Opened Jun 9, 2026 by AnaisHeaney

💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex CLI is running?

codex-cli 0.137.0

What subscription do you have?

Not sure

Which model were you using?

gpt-5.5

What platform is your computer?

Darwin x86_64 (macOS)

What issue are you seeing?

I am repeatedly seeing:

Selected model is at capacity. Please try a different model.

After switching models to recover the session, it often comes back showing only around 60-70% context left instead of what appears to be a fresh/full context window.

What steps can reproduce the bug?

Use Codex CLI on macOS
Run an active coding session with tool use
Hit the capacity error on gpt-5.5
Switch to another model such as gpt-5.4
Observe that the recovered session often shows only about 60-70% context left

What is the expected behavior?

The session should continue without capacity interruptions, or
if recovery is required, the recovered session should not come back with unexpectedly reduced available context

Additional information

Switching to gpt-5.4 allowed the session to continue
I also noticed another similar report shortly before posting, so this does not look isolated

View original on GitHub ↗

3 Comments

github-actions[bot] contributor · 2 months ago

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

#26290
#26783

Powered by Codex Action

martinmclee · 2 months ago

I?m seeing this issue right now and wanted to add a direct data point.

Timestamp: 2026-06-16T17:10:07.3757326+08:00
Model: gpt-5.5 xhigh
Exact error: "Selected model is at capacity. Please try a different model."
Environment: Not running cloud / not using a hosted/custom cloud stack.

I can reproduce this repeatedly during normal usage with that model. Fallback to another model is required to continue.

Could this be tied to backend regional model-capacity routing even for non-cloud/local sessions?

martinmclee · 2 months ago

I?m seeing this issue right now and wanted to add a direct data point.

Timestamp: 2026-06-16T17:10:07.3757326+08:00
Model: gpt-5.5 xhigh
Exact error: "Selected model is at capacity. Please try a different model."
Environment: Not running cloud / not using a hosted/custom cloud stack.

I can reproduce this repeatedly during normal usage with that model. Fallback to another model is required to continue.

Could this be tied to backend regional model-capacity routing even for non-cloud/local sessions?