Repository navigation
Repeated "Selected model is at capacity" errors make Codex unusable #44382
Description
What version of Codex CLI is running?
v0.154.0
What subscription do you have?
ChatGPT Pro 20x
Which model were you using?
gpt-6-astra ultra fast
What platform is your computer?
Linux 6.8.0-107-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
No response
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1789007014s since unix epoch",
"overallStatus": "warning",
"codexVersion": "0.154.0",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "/home/ia_user/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/home/ia_user/.codex/app-server-daemon",
"mode": "ephemeral",
"pid file": "/home/ia_user/.codex/app-server-daemon/app-server.pid (missing)",
"settings": "/home/ia_user/.codex/app-server-daemon/settings.json (missing)",
"status": "not running",
"update-loop pid file": "/home/ia_user/.codex/app-server-daemon/app-server-updater.pid (missing)"
},
"remediation": null,
"durationMs": 0
},
"auth.credentials": {
"id": "auth.credentials",
"category": "auth",
"status": "ok",
"summary": "auth is configured",
"details": {
"auth file": "/home/ia_user/.codex/auth.json",
"auth storage mode": "File",
"stored API key": "false",
"stored ChatGPT tokens": "true",
"stored agent identity": "false",
"stored auth mode": "chatgpt"
},
"remediation": null,
"durationMs": 0
},
"config.load": {
"id": "config.load",
"category": "config",
"status": "ok",
"summary": "config loaded",
"details": {
"CODEX_HOME": "/home/ia_user/.codex",
"active thread overrides": "not inspected",
"config.toml": "/home/ia_user/.codex/config.toml",
"config.toml parse": "ok",
"configuration load ms": "30",
"configuration scope": "invocation config, including cloud-managed policy",
"cwd": "/home/ia_user",
"enabled feature flags": "shell_tool, view_image, sleep_tool, unified_exec, unified_exec_tty, unified_exec_zsh_fork, shell_snapshot, content_item_kinds, code_mode_host, terminal_resize_reflow, sqlite, memories, hooks, enable_request_compression, unbounded_connection_retries, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, in_app_chat, in_app_dictation, in_app_local_automation, in_app_updates, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, item_ids, skill_mcp_dependency_install, skill_search, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, compaction_image_budget, workspace_dependencies",
"feature flag overrides": "memories=true",
"feature flags enabled": "49",
"log dir": "/home/ia_user/.codex/log",
"mcp servers": "2",
"model": "gpt-6-astra",
"model provider": "openai",
"sqlite home": "/home/ia_user/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git executable found; execution not verified",
"details": {
"PATH git #1": "/usr/bin/git",
"PATH git #2": "/bin/git",
"PATH git entries": "2",
"git execution": "not inspected (PATH helpers are not executed)",
"repo detected": "false",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 0
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/usr/bin/codex",
"PATH codex #2": "/bin/codex",
"PATH codex entries": "2",
"current executable": "/usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install context": "npm (package /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"managed by Vite+": "false",
"managed by bun": "false",
"managed by npm": "true",
"managed by pnpm": "false",
"managed package root": "/usr/lib/node_modules/@openai/codex",
"npm update target": "not inspected (PATH helpers are not executed)"
},
"remediation": null,
"durationMs": 0
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "MCP configuration is locally consistent",
"details": {
"configured servers": "2",
"disabled servers": "0",
"stdio servers": "1",
"streamable_http servers": "1"
},
"remediation": null,
"durationMs": 74
},
"network.env": {
"id": "network.env",
"category": "network",
"status": "ok",
"summary": "network-related environment looks readable",
"details": {
"managed proxy": "not configured",
"proxy env vars": "none",
"respect system proxy": "disabled"
},
"remediation": null,
"durationMs": 0
},
"network.provider_reachability": {
"id": "network.provider_reachability",
"category": "reachability",
"status": "ok",
"summary": "active provider endpoints are reachable over HTTP",
"details": {
"ChatGPT inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 144
},
"network.websocket_reachability": {
"id": "network.websocket_reachability",
"category": "websocket",
"status": "ok",
"summary": "Responses WebSocket handshake succeeded",
"details": {
"DNS": "2 IPv4, 2 IPv6, first IPv4",
"auth mode": "chatgpt",
"connect timeout": "15000 ms",
"endpoint": "wss://chatgpt.com/backend-api/<redacted>",
"handshake result": "HTTP 101 Switching Protocols",
"model provider": "openai",
"provider name": "OpenAI",
"proxy env vars": "none",
"reasoning header": "false",
"server model present": "false",
"supports websockets": "true",
"wire API": "responses"
},
"remediation": null,
"durationMs": 778
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running npm on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "/usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install method": "npm (package /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-x86_64",
"version": "0.154.0"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search command found (bundled); execution not verified",
"details": {
"search command": "/usr/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path/rg",
"search command readiness": "file exists",
"search provider": "bundled"
},
"remediation": null,
"durationMs": 0
},
"sandbox.helpers": {
"id": "sandbox.helpers",
"category": "sandbox",
"status": "ok",
"summary": "sandbox configuration is readable",
"details": {
"approval policy": "OnRequest",
"codex-linux-sandbox helper": "/home/ia_user/.codex/tmp/arg0/codex-arg0g2d725/codex-linux-sandbox",
"denied-read glob rules": "0",
"denied-read rules": "0",
"execve wrapper helper": "/home/ia_user/.codex/tmp/arg0/codex-arg0g2d725/codex-execve-wrapper",
"filesystem sandbox": "restricted",
"glob scan max depth": "unbounded",
"managed filesystem source": "none",
"network sandbox": "restricted"
},
"remediation": null,
"durationMs": 0
},
"security.endpoint": {
"id": "security.endpoint",
"category": "security",
"status": "ok",
"summary": "endpoint protection is not inspected on this platform",
"details": {
"endpoint products": "not inspected on this platform"
},
"remediation": null,
"durationMs": 0
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "/home/ia_user/.codex (dir)",
"active rollout files": "5960 files, 580576085147 total bytes, 97412094 average bytes",
"archived rollout files": "4 files, 493469737 total bytes, 123367434 average bytes",
"goals DB": "/home/ia_user/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/home/ia_user/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/home/ia_user/.codex/log (dir)",
"memories DB": "/home/ia_user/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"queue DB": "/home/ia_user/.codex/queue_1.sqlite (file)",
"queue DB integrity": "ok",
"sqlite home": "/home/ia_user/.codex (dir)",
"state DB": "/home/ia_user/.codex/state_5.sqlite (file)",
"state DB integrity": "ok",
"thread history DB": "/home/ia_user/.codex/thread_history_1.sqlite (file)",
"thread history DB integrity": "ok"
},
"remediation": null,
"durationMs": 101609
},
"state.rollout_db_parity": {
"id": "state.rollout_db_parity",
"category": "threads",
"status": "warning",
"summary": "rollout files and state DB thread inventory differ",
"details": {
"default model provider": "openai",
"rollout DB active files": "5960",
"rollout DB active rows": "5959",
"rollout DB archive mismatches": "0",
"rollout DB archived files": "4",
"rollout DB archived rows": "4",
"rollout DB duplicate DB paths": "0",
"rollout DB duplicate rollout thread ids": "0",
"rollout DB malformed file names": "0",
"rollout DB missing active rows": "1",
"rollout DB missing active sample": "/home/ia_user/.codex/sessions/2026/08/31/rollout-2026-08-31T00-02-00-01a05368-03b6-7582-8db3-b4bef63d6e0d.jsonl",
"rollout DB missing archived rows": "0",
"rollout DB model providers": "openai=5963",
"rollout DB rows": "5963",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "subagent:thread_spawn=4922, exec=989, cli=49, subagent:review=3",
"rollout DB stale rows": "0"
},
"issues": [
{
"severity": "warning",
"cause": "rollout files are missing from the state DB",
"measured": "1 active, 0 archived",
"expected": "every rollout file has a matching threads row",
"remedy": null,
"fields": []
}
],
"remediation": null,
"durationMs": 1703
},
"system.disk": {
"id": "system.disk",
"category": "disk",
"status": "ok",
"summary": "sufficient free disk space (103.0 GiB)",
"details": {
"CODEX_HOME available": "103.0 GiB",
"failure threshold": "1.0 GiB",
"warning threshold": "5.0 GiB",
"worktree available": "103.0 GiB"
},
"remediation": null,
"durationMs": 0
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language en-US",
"details": {
"EDITOR": "not set",
"LANG": "en_US.UTF-8",
"VISUAL": "not set",
"os": "Ubuntu 24.4.0 (noble) [64-bit]",
"os language": "en-US",
"os type": "Ubuntu",
"os version": "24.4.0"
},
"remediation": null,
"durationMs": 10
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"SSH_CLIENT": "present",
"SSH_CONNECTION": "present",
"SSH_TTY": "present",
"TERM": "xterm",
"color output": "enabled",
"effective locale": "en_US.UTF-8",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout is terminal": "true",
"terminal": "unknown",
"terminal size": "208x40"
},
"remediation": null,
"durationMs": 0
},
"terminal.title": {
"id": "terminal.title",
"category": "title",
"status": "ok",
"summary": "terminal title default",
"details": {
"terminal title activity": "true",
"terminal title items": "activity, project-name",
"terminal title project source": "cwd",
"terminal title project value": "ia_user",
"terminal title source": "default"
},
"remediation": null,
"durationMs": 0
},
"updates.status": {
"id": "updates.status",
"category": "updates",
"status": "ok",
"summary": "update configuration is locally consistent",
"details": {
"cached latest version": "0.154.0",
"check for update on startup": "true",
"last checked at": "2026-09-10T00:48:55.887118995Z",
"latest version": "0.154.0",
"latest version status": "current version is not older",
"npm update target": "not inspected (PATH helpers are not executed)",
"update action": "npm install -g @openai/codex",
"version cache": "/home/ia_user/.codex/version.json"
},
"remediation": null,
"durationMs": 2448
}
}
}What issue are you seeing?
I frequently encounter the following error while using Codex:
"Selected model is at capacity. Please try a different model."
This is a recurring issue rather than an isolated interruption. Codex is currently unusable for my development work, and the repeated failures are blocking progress on my projects.
The error message does not provide enough information to identify the cause or a reliable way to resume working. I cannot determine whether this is a temporary model-capacity issue or another problem affecting my access to Codex.
Please investigate the affected thread referenced in the reproduction steps below and advise on a reliable workaround.
What steps can reproduce the bug?
Uploaded thread: 019e162f-ee7d-7d21-af2b-f08b8d4a317a
What is the expected behavior?
Codex should process requests normally when the selected model is available and my account is eligible to use it.
If the model is temporarily unavailable, Codex should provide actionable guidance, such as when to retry or which alternative model is available.
I should be able to resume the affected task once access is restored, without losing the conversation state or work already completed.
Additional information
Impact:
Codex is currently unusable for my development workflow, and this issue is blocking project progress.
Frequency:
Frequent / recurring.
Approximate timestamp of a recent failure, including time zone:
[Enter an actual failure date, time, and time zone]
Troubleshooting already attempted and results:
None yet
Questions for the team:
- Is this a known incident affecting Codex or the selected model?
- Can the uploaded thread help identify why these requests are failing?
- Is there a reliable workaround or a recommended alternative model to restore access?
- If more diagnostic information is needed, please specify what to collect and how to share it safely.
Activity
github-actions commentedon Sep 10, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
alexandrawallace commentedon Sep 10, 2026
same：019fd17f-95a1-7060-a853-f6dcd7cd558d
jeremyzhang866 commentedon Sep 10, 2026
the same issue
YoungTreeTree commentedon Sep 10, 2026
01a084fc-b976-7bb3-a13b-a4d367c21ea5
alexandrawallace commentedon Sep 10, 2026
have been four day ago，why？？？？ thats so crazy
FawziLinggo commentedon Sep 10, 2026
I’m seeing the same capacity failure today (Sep 10, 2026) on GPT-5.6 Sol on Windows.
What I observed:
test/tesrepeatedly fails with:Selected model is at capacity. Please try a different model.503 Service Unavailable/Our servers are currently overloaded. Please try again later.127.0.0.1:20128, TCP succeeds) and its/v1/modelsendpoint responds normally.Selected model is at capacity.This makes the issue look service/model-capacity related rather than project-specific, MCP-related, or caused by the local router configuration. The failure is reproducible even with a fresh/minimal prompt and no meaningful tool workload.
Affected model in my case: gpt-5.6-sol.
mingx2915-lab commentedon Sep 10, 2026
There’s barely any visible movement from OpenAI.
RostislavBlatman commentedon Sep 10, 2026
As far as I can tell, they have no intention of doing anything about this. I don't understand why I bought the Pro X20 subscription...
I’ve practically got PTSD from the yellow text in the terminal...
mingx2915-lab commentedon Sep 10, 2026
1ef7yy commentedon Sep 10, 2026
same for me on codex CLI (01a08ab9-8ae6-7362-9438-e5d722c90ef1) but not on ChatGPT desktop
have gotten temporary access to the models (for 1h30min or so) and then hit model capacity again
reinstalling codex cli and clearing the config files did not help, problem persists for all models and all reasoning effort levels
RostislavBlatman commentedon Sep 10, 2026
Well, that’s it—there will be no more Pro X20 subscriptions. They couldn't pull it off...
FawziLinggo commentedon Sep 11, 2026
Update (Sep 11, 2026): this is still reproducible for me on GPT-5.6 Sol on Windows.
Minimal prompts continue to fail after repeated reconnect/retry attempts with:
Selected model is at capacity. Please try a different model.When routed through my local Responses-compatible setup, the upstream failure is exposed as:
503 Service UnavailableOur servers are currently overloaded. Please try again later.The local router itself is healthy (
/v1/modelsresponds normally), and I can reproduce the same capacity failure through a clean/direct OpenAI path as well. That makes this look much more like a service/model capacity issue than a project-specific, MCP-related, or local-router problem.The repeated reconnects also make each failed request take much longer before Codex finally gives up, so the issue is not only availability but also severe latency/usability impact.
Could someone from the Codex/OpenAI team confirm whether GPT-5.6 Sol is currently experiencing an ongoing capacity degradation? The public status page does not appear to reflect the severity that users are reporting here.