Cloud Run GPUs vs CoreWeave

Cloud Run GPUs 70

Hosted reading. Google Cloud's status page with a JSON incident feed (20). In the 90 days from 8 August 2026 the feed names Cloud Run in three multi-product incidents, a service outage on 20 August (15:40 to 19:20 UTC, 27 products, global and us-west1), a network degradation in us-central1-b on 1 September and a europe-west2 disruption on 20 October. One major (10). Resource limits and GPU quota are published with numbers (3 GPUs a region by default), but no request rate for the Admin API was found on the quotas page (10). Google's client libraries retry with backoff and the Admin API takes etags, while no GPU-specific retry guidance was found (10). An SLA for GPU services, 99.95% with zonal redundancy and 99.5% without (10). GPU services generally available since 7 April 2025 (10). 20+10+10+10+10+10 = 70.

CoreWeave 45

Graded as a hosted service on the CKS and platform APIs. Status.io page at status.coreweave.com with components per data centre and email, webhook, Teams, Slack and RSS subscriptions (20). The page's robots.txt now disallows /pages/*, where the history, incident pages and the RSS feed sit, so the 8 October reading of the feed (25 September to 8 October) is struck and the 90-day window is unread. The root page, which is allowed, shows one open incident, a facility power loss in US-EAST-15A from 22 October 2026 marked Partial Service Disruption, still in monitoring on 26 October. The same page counts 5 incidents in the last 30 days without listing them. That is one zone of about 40 and reads as partial, but the rest of the window can't be read, so it isn't credited (5). No request rate limits found for api.coreweave.com, only gateway size limits of about 50 KB and 100 MB, and quotas are set per customer through support (0). No 429 or backoff guidance and no idempotency keys found. Kubernetes resources are declarative, so re-applying a manifest is safe (5 of 15). The terms set an objective of 99.9 per cent across multiple regions and 99 per cent in one, with financial credits (10). CKS is sold as a general service but its cluster API is still v1beta1 and the Node Pool resource v1alpha1 (5 of 10). 20 + 5 + 0 + 5 + 10 + 5 = 45.

Cloud Run GPUs 66

Platform reading. One gcloud run deploy with --gpu and --gpu-type adds a GPU to a container, and responses carry the service object with fieldMask on updates (15). List calls page with pageSize and pageToken (15). Google's status codes and messages, with quota errors that name the limit (12). Revisions are immutable, traffic can be moved back, and etags guard updates, but no idempotency key on create (12). Client libraries in many languages and gcloud, though a GPU deploy needs instance-based billing, minimum CPU and memory and, past 3 GPUs, a quota request (12). 15+15+12+12+12 = 66.

CoreWeave 58

Graded on the platform API, the Kubernetes API and the Mission Control MCP server together. The MCP server documents 38 tools, most of them small read-only queries with limits, and every tool also takes an optional user_prompt (12 of 25). The Dedicated Inference API pages with maxPageSize and pageToken. The cluster list returns everything, with returnPartialSuccess for unreachable zones (14). Errors follow the google.rpc shape with a numeric code and a message, and support articles explain common failures (12). No idempotency keys, no MCP read-only or destructive annotations documented, and coreweave_kubectl_apply ignores dry_run and plan_token and applies the manifest (8). Generated clients on Buf for Go, Python, TypeScript, Java and others, plus a Terraform provider. Creating a cluster needs a zone, version and VPC (12).

Cloud Run GPUs 84

Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15). The Cloud Data Processing Addendum and the privacy notice cover customer data, per the Document AI listing's 1 November reading; no Cloud Run statement on GPU instance data after shutdown was found (22). The Cloud terms promise 12 months' notice before a backwards-incompatible API change, and driver versions are announced in the release notes (16). Regions per GPU type listed, with Google's subprocessor list and data-location terms (16). 15+22+16+16 = 69.

CoreWeave 78

Closed service with published terms. They were last modified on 30 June 2022 and say they may be amended without notice (15). The terms commit to deleting customer data after account closure within a 30-day recovery period and at most 180 days, there is a data processing agreement, and the privacy policy of 24 February 2026 gives no fixed retention period for personal data (22). The changelog gives dated deprecations, for example Kubernetes v1.34 for new clusters from 16 September 2026 and operating system and driver versions from 29 July 2026, and the maintenance policy promises 24 hours' notice for critical work, though it can change without notice (14). Two sub-processors are named for CoreWeave Infrastructure with their country (Backblaze and Microsoft, both United States) and 30 days' notice of additions, and regions and availability zones are documented (20).