Downgraded to Flash with paid Gemini Code Assist Standard

[medproapp]

Billing account
My Billing Account
Subscription ID
3fe51ab7-2040-4a6b-82f9-94c2d1c142d3
Subscription period
Monthly
Subscription edition
Standard
Subscription start date
Jul 02, 2025
Subscription auto renew date
Aug 02, 2025
Number of licenses
1
Cost per license
$22.80
Cost per month
$22.80

➜ version3 echo $GOOGLE_CLOUD_PROJECT
gen-lang-client-0601086194

➜ version3 gcloud projects list
PROJECT_ID NAME PROJECT_NUMBER
gen-lang-client-0601086194 Gemini API 1093876296519

│ - medprofront/dev-server.js │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
Flushing log events to Clearcut.
Attempt 1 failed with status 429. Retrying with backoff... GaxiosError: [{
"error": {
"code": 429,
"message": "Quota exceeded for quota metric 'Gemini 2.5 Pro Requests' and limit 'Gemini 2.5 Pro Requests per day per user per tier' of service 'cloudcode-pa.googleapis.com' for consumer 'project_number:681255809395'.",
"errors": [
{
"message": "Quota exceeded for quota metric 'Gemini 2.5 Pro Requests' and limit 'Gemini 2.5 Pro Requests per day per user per tier' of service 'cloudcode-pa.googleapis.com' for consumer 'project_number:681255809395'.",
"domain": "global",
"reason": "rateLimitExceeded"
}
],
"status": "RESOURCE_EXHAUSTED"
}
}
]
at Gaxios._request (/home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/gaxios/build/src/gaxios.js:142:23)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async OAuth2Client.requestAsync (/home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/google-auth-library/build/src/auth/oauth2client.js:429:18)
at async CodeAssistServer.requestStreamingPost (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/code_assist/server.js:81:21)
at async CodeAssistServer.generateContentStream (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/code_assist/server.js:23:23)
at async retryWithBackoff (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/utils/retry.js:61:20)
at async GeminiChat.sendMessageStream (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/geminiChat.js:283:36)
at async Turn.run (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/turn.js:33:36)
at async GeminiClient.sendMessageStream (file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/node_modules/@google/gemini-cli-core/dist/src/core/client.js:175:26)
at async file:///home/adminuser/.nvm/versions/node/v22.16.0/lib/node_modules/@google/gemini-cli/dist/src/ui/hooks/useGeminiStream.js:275:26 {
config: {
url: 'https://cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse',
method: 'POST',
params: { alt: 'sse' },
headers: {
'Content-Type': 'application/json',
'User-Agent': 'GeminiCLI/v22.16.0 (linux; x64) google-api-nodejs-client/9.15.1',
Authorization: '< - See errorRedactor option in gaxios for configuration>.',
'x-goog-api-client': 'gl-node/22.16.0'
},
responseType: 'stream',
body: '< - See errorRedactor option in gaxios for configuration>.',
signal: AbortSignal { aborted: false },
paramsSerializer: [Function: paramsSerializer],
validateStatus: [Function: validateStatus],
errorRedactor: [Function: defaultErrorRedactor]
},
response: {
config: {
url: 'https://cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse',
method: 'POST',
params: [Object],
headers: [Object],
responseType: 'stream',
body: '< - See errorRedactor option in gaxios for configuration>.',
signal: [AbortSignal],
paramsSerializer: [Function: paramsSerializer],
validateStatus: [Function: validateStatus],
errorRedactor: [Function: defaultErrorRedactor]
},
data: '[{\n' +
' "error": {\n' +
' "code": 429,\n' +
"message": "Quota exceeded for quota metric 'Gemini 2.5 Pro Requests' and limit 'Gemini 2.5 Pro Requests per day per user per tier' of service 'cloudcode-pa.googleapis.com' for consumer 'project_number:681255809395'.",\n +
' "errors": [\n' +
' {\n' +
"message": "Quota exceeded for quota metric 'Gemini 2.5 Pro Requests' and limit 'Gemini 2.5 Pro Requests per day per user per tier' of service 'cloudcode-pa.googleapis.com' for consumer 'project_number:681255809395'.",\n +
' "domain": "global",\n' +
' "reason": "rateLimitExceeded"\n' +
' }\n' +
' ],\n' +
' "status": "RESOURCE_EXHAUSTED"\n' +
' }\n' +
'}\n' +
']',
headers: {
'alt-svc': 'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000',
'content-length': '630',
'content-type': 'application/json; charset=UTF-8',
date: 'Thu, 03 Jul 2025 15:13:07 GMT',
server: 'ESF',
'server-timing': 'gfet4t7; dur=470',
vary: 'Origin, X-Origin, Referer',
'x-content-type-options': 'nosniff',
'x-frame-options': 'SAMEORIGIN',
'x-xss-protection': '0'
},
status: 429,
statusText: 'Too Many Requests',
request: {
responseURL: 'https://cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse'
}
},
error: undefined,
status: 429,
[Symbol(gaxios-gaxios-error)]: '6.7.1'
}

ℹ ⚡ Slow response times detected. Automatically switching from gemini-2.5-pro to gemini-2.5-flash for faster responses for the remainder of this session.
⚡ To avoid this you can either upgrade to Standard tier. See: https://goo.gle/set-up-gemini-code-assist
⚡ Or you can utilize a Gemini API Key. See: https://goo.gle/gemini-cli-docs-auth#gemini-api-key
⚡ You can switch authentication methods by typing /auth
✦ I see you've provided the dev-server.js file. This file sets up a development server for your frontend.

It looks like it is not using the right GCloud project number...

I hava a paid Standard subscription and I cannot use the pro model. The flash simply does not work.

[medproapp]

I give up on Gemini CLI for now ... I have canceled my subscription ... Too many problems and errors. I will stay with Claude Code at least for now ... Much better, precise, stable and just works!

[ryanjsalva]

Thanks for giving it a try. Come back anytime. 🤗

[AgarwalPragy]

So is this the expected behavior? I'm encountering the same issue.

I've Google Code Assist and Cloud Assist enabled on my account. I've setup the licenses. I've setup the GOOGLE_CLOUD_PROJECT env variable. I'm using /auth to login via Google.

And it still keeps switching to gemini-2.5-flash.

Is there any way to find out how CLI is authenticating, or what it sees after authentication?

[medproapp]

This was closed without a proper answers ... !?!? Is this really Google's position? Do not care about answering????