Skip to content

Spark allowance shows 100% remaining but prolite account receives model-not-supported HTTP 400 #46052

Open
Open
Spark allowance shows 100% remaining but prolite account receives model-not-supported HTTP 400#46052
Labels
CLIIssues related to the Codex CLIbugSomething isn't workingrate-limitsIssues related to rate limits, quotas, and token usage reportingwindows-osIssues related to Codex on Windows systems

Description

@J-dev2
J-dev2
opened on Sep 16, 2026

Summary

My account reports a GPT-5.3-Codex-Spark allowance with 100% remaining in both the five-hour and weekly windows, but Spark is missing from the desktop model picker and an explicit CLI request returns HTTP 400.

Environment

  • Windows 11, OS build 26200, PowerShell
  • Codex CLI: 0.154.0-alpha.6.2 (desktop-bundled binary)
  • Authentication: ChatGPT account
  • Account plan identifier returned by usage reporting: prolite
  • Model requested: gpt-5.3-codex-spark
  • Reproduced: September 16, 2026

Steps to reproduce

  1. Check account usage. A separate limit named GPT-5.3-Codex-Spark reports usedPercent: 0 for both the 300-minute and 10080-minute windows.
  2. Open the desktop model picker. It offers 5.6 Sol, 6 Astra, 5.6 Terra, 5.6 Luna, and 5.5, but no Spark.
  3. Run:
codex exec --model gpt-5.3-codex-spark --sandbox read-only --skip-git-repo-check --ephemeral --color never 'Reply with exactly: Spark connection works. Do not use tools or read or edit files.'

Actual result

The CLI exits with code 1. It first warns:

Model metadata for `gpt-5.3-codex-spark` not found. Defaulting to fallback metadata; this can degrade performance and cause issues.

The server then returns:

{"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.3-codex-spark' model is not supported when using Codex with a ChatGPT account."}}

This is an explicit model-access rejection, despite the unused allowance. I have not established the underlying cause or tested a separate stable CLI installation.

Expected result

If the account is eligible, Spark should be selectable and direct requests should work. If it is ineligible, the usage interface should explain why it shows a Spark allowance that cannot be used. Please clarify Spark eligibility for the prolite plan and investigate the mismatch between usage reporting and model access.

Related reports

This report adds a reproduction using the desktop-bundled CLI version above and the plan identifier returned by usage reporting. Account IDs, credentials, local personal paths, and unrelated logs are omitted.

Update after reviewing related reports (September 16, 2026)

I reviewed #45594, #45972, #45857, #45613, and #45728 after the duplicate notice. They describe the same basic problem across Windows and macOS: Spark quota is visible, but the model is missing or direct requests are rejected. Reports using stable CLI 0.154.0 also reproduce it, and users in #45594 and #45613 say signing in again did not help. All five issues were still open when checked, with no maintainer explanation or confirmed fix in their comments. The author of #45857 reports a support escalation, but no diagnosis yet.

I understand why these reports are flagged as possible duplicates. What feels unfair is being shown an available allowance without being able to use it or getting a clear explanation. The duplicate notice points to other people with the same problem, but it does not answer why access is being rejected.

Can someone from OpenAI clarify whether Spark is currently supposed to work for these accounts? If it is, is there a known incident or a supported fix? If it is no longer available, why does the usage page still show an unused Spark allowance? Please identify the main issue to follow and provide a clear status update. I do not know the cause and am asking for an explanation rather than assuming one.

Activity

  1. github-actions
    added
    bugSomething isn't working
    CLIIssues related to the Codex CLI
    windows-osIssues related to Codex on Windows systems
    rate-limitsIssues related to rate limits, quotas, and token usage reporting
    on Sep 16, 2026

  2. github-actions commented on Sep 16, 2026

    @github-actions
    github-actionsBot
    on Sep 16, 2026 – with GitHub Actions
    Contributor

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

    Powered by Codex Action

  3. J-dev2 commented on Sep 16, 2026

    @J-dev2
    J-dev2
    on Sep 16, 2026
    Author

    @etraut-openai, you previously helped clarify Spark subscription access in #17642. Could you help route this current report to the right team?

    I reproduced a Spark access failure on Windows: my account shows 100% remaining in both Spark usage windows, but Spark is missing from the desktop picker and a direct CLI request returns HTTP 400 saying it is not supported with a ChatGPT account. The account's usage response reports prolite; the exact command and error are in the issue above.

    I also reviewed #45594, #45972, #45857, #45613, and #45728. They report the same mismatch across Windows and macOS, including stable CLI 0.154.0. None had a maintainer explanation or confirmed fix when I checked.

    Could someone clarify current Spark eligibility and why an unusable allowance is still displayed? If this is being tracked elsewhere, please point us to the main issue and current status. I understand consolidating duplicates, but we still need an explanation or a supported next step.

  4. brianjlacy commented on Sep 16, 2026

    @brianjlacy
    brianjlacy
    on Sep 16, 2026

    Additional likely-related (or identical) reported issues:

    #37308
    #38199
    #39429
    #45566
    #45590
    #45655
    #45666

    This has clearly been an ongoing issue for some time...

  5. matttiii13 commented on Sep 17, 2026

    @matttiii13
    matttiii13
    on Sep 17, 2026

    I can reproduce this on macOS with a ChatGPT Pro account. Both Spark limits show 100% remaining, but Spark is absent from the Codex desktop model picker. After restarting the app and signing in again, a direct CLI request for gpt-5.3-codex-spark returns HTTP 400: “The 'gpt-5.3-codex-spark' model is not supported when using Codex with a ChatGPT account.”

    Codex desktop version: 26.908.40834. Could OpenAI clarify whether Spark is currently available to Pro accounts and how affected users can regain access?

  6. fdefilippo commented on Sep 20, 2026

    @fdefilippo
    fdefilippo
    on Sep 20, 2026

    I can reproduce this on Codex CLI v0.155.1 with a ChatGPT Pro Lite account.

    Spark was available earlier today. After upgrading Codex to v0.155.1, Spark disappeared from the model selection/status UI.

    I then tested explicit model selection:

    codex exec \
  --model gpt-5.3-codex-spark \
  --sandbox read-only \
  --skip-git-repo-check \
  --ephemeral \
  'Reply only OK. Do not use tools.'

    The CLI reported:

    warning: Model metadata for `gpt-5.3-codex-spark` not found.
Defaulting to fallback metadata; this can degrade performance and cause issues.

ERROR: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.3-codex-spark' model is not supported when using Codex with a ChatGPT account."}}

    This confirms that Spark is not merely hidden from the model selector: explicit requests are rejected by the backend.

    Environment: Codex CLI 0.155.1, ChatGPT Pro Lite, Linux.

    I cannot yet determine whether the CLI upgrade caused the change or whether model entitlement changed server-side during the same period. Could you confirm whether Spark access for Pro Lite accounts has been intentionally changed?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    CLIIssues related to the Codex CLIbugSomething isn't workingrate-limitsIssues related to rate limits, quotas, and token usage reportingwindows-osIssues related to Codex on Windows systems

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions