Project ID: (PII Removed by Staff)
Project number: (PII Removed by Staff)
Billing account: (PII Removed by Staff)
Contact: (PII Removed by Staff)
Issue
Anthropic Claude shared-lineage quotas on Agent Platform / Vertex AI are locked at 0. Cloud Quotas preferences return grantedValue=0. QuotaIncreaseEligibility shows NOT_ENOUGH_USAGE_HISTORY. Live call to claude-sonnet-5 returns HTTP 429 RESOURCE_EXHAUSTED on global_online_prediction_requests_per_base_model for base_model anthropic-claude-sonnet.
Models needed ASAP (1M context)
- claude-sonnet-5 (lineage anthropic-claude-sonnet)
- claude-opus-5 (lineage anthropic-claude-opus)
- claude-fable-5 (lineage anthropic-claude-fable)
Requested limits (Global + US multi-region), per lineage
- QPM: 1000
- Input TPM: 1,000,000
- Output TPM: 1,000,000
Quota preferences already filed via Cloud Quotas API for those three lineages (Global + US).
Usage history
We generated Vertex usage with Gemini 2.5 Flash/Pro generateContent + countTokens on the global endpoint. Please manually review Anthropic partner model-access eligibility and grant the preferred quotas.
Use case
Non-production evaluation. Production inference remains on Claude Platform on AWS.
Please route for manual model-access / capacity review.