For several days, I can’t use the model gemini-3.1-pro-preview via gemini-cli via my Google One AI Pro account.
It always returns the same error:
> gemini -m gemini-3.1-pro-preview -y -p “Say Hello” --output-format json
YOLO mode is enabled. All tool calls will be automatically approved.
Loaded cached credentials.
YOLO mode is enabled. All tool calls will be automatically approved.
Loading extension: atlassian-rovo-mcp-server
Loading extension: chrome-devtools-mcp
Loading extension: code-review
Loading extension: gemini-cli-jules
Loading extension: github
Loading extension: google-workspace
Loading extension: terraform
Scheduling MCP context refresh…
Executing MCP context refresh…
Found stored OAuth token for server ‘atlassian-rovo-mcp-server’
MCP context refresh complete.
Registering notification handlers for server ‘julesServer’. Capabilities: { tools: { listChanged: true } }
Server ‘julesServer’ supports tool updates. Listening for changes…
Registering notification handlers for server ‘terraform’. Capabilities: {
resources: { subscribe: true, listChanged: true },
tools: { listChanged: true }
}
Server ‘terraform’ supports tool updates. Listening for changes…
Server ‘terraform’ supports resource updates. Listening for changes…
Registering notification handlers for server ‘atlassian-rovo-mcp-server’. Capabilities: { logging: {}, resources: {}, tools: { listChanged: true } }
Server ‘atlassian-rovo-mcp-server’ supports tool updates. Listening for changes…
Server ‘atlassian-rovo-mcp-server’ has resources but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Registering notification handlers for server ‘google-workspace’. Capabilities: { tools: { listChanged: true } }
Server ‘google-workspace’ supports tool updates. Listening for changes…
Registering notification handlers for server ‘github’. Capabilities: { completions: {}, prompts: {}, resources: {}, tools: {} }
Server ‘github’ has tools but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘github’ has resources but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘github’ has prompts but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Registering notification handlers for server ‘chrome-devtools’. Capabilities: { logging: {}, tools: { listChanged: true } }
Server ‘chrome-devtools’ supports tool updates. Listening for changes…
Registering notification handlers for server ‘kubernetes’. Capabilities: { prompts: {}, resources: {}, tools: {} }
Server ‘kubernetes’ has tools but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘kubernetes’ has resources but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘kubernetes’ has prompts but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Registering notification handlers for server ‘memory’. Capabilities: {
experimental: {
hardware_info: {
architecture: ‘x86_64’,
accelerator: ‘cpu’,
memory_gb: 31.05,
cpu_count: 8
}
},
prompts: { listChanged: false },
resources: { subscribe: false, listChanged: false },
tools: { listChanged: false }
}
Server ‘memory’ has tools but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘memory’ has resources but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Server ‘memory’ has prompts but did not declare ‘listChanged’ capability. Listening anyway for robustness…
Scheduling MCP context refresh…
Executing MCP context refresh…
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh already in progress, queuing trailing execution.
MCP context refresh complete.
Coalescing burst refresh requests (300ms delay)…
Executing MCP context refresh…
MCP context refresh complete.
Attempt 1 failed with status 429. Retrying with backoff… GaxiosError: [{
“error”: {
“code”: 429,
“message”: “No capacity available for model gemini-3.1-pro-preview on the server”,
“errors”: [
{
“message”: “No capacity available for model gemini-3.1-pro-preview on the server”,
“domain”: “global”,
“reason”: “rateLimitExceeded”
}
],
“status”: “RESOURCE_EXHAUSTED”,
“details”: [
{
“@type”: “type.googleapis.com/google.rpc.ErrorInfo”,
“reason”: “MODEL_CAPACITY_EXHAUSTED”,
“domain”: “cloudcode-pa.googleapis.com”,
“metadata”: {
“model”: “gemini-3.1-pro-preview”
}
}
]
}
}
]
Is it possible to investigate if there is a regional capacity constraint?
Or is there a rate-limiting issue on my account?
Furthermore, I would like to verify if my Google One AI Pro entitlement is prioritizing traffic correctly.
Thanks for your help.