{ "data": { "similar": [ { "grade": "B", "json": "https://www.anchorterminal.com/tools/modal.json", "name": "Modal", "score": 62.7, "shared": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "modal" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/beam.json", "name": "Beam", "score": 56.2, "shared": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "beam" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/runpod.json", "name": "Runpod", "score": 55.6, "shared": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "runpod" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/verda.json", "name": "Verda", "score": 53.3, "shared": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "verda" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/cerebrium.json", "name": "Cerebrium", "score": 52.5, "shared": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "cerebrium" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/nebius-ai-cloud.json", "name": "Nebius AI Cloud", "score": 71.2, "shared": [ "compute.gpu", "compute.endpoints", "compute.batch", "compute.containers" ], "slug": "nebius-ai-cloud" } ], "tool": { "slug": "cloud-run-gpus", "name": "Cloud Run GPUs", "vendor": "Google Cloud", "vendorUrl": "https://cloud.google.com/run", "kind": "platform", "category": "gpu-compute", "summary": "Cloud Run GPUs attach one NVIDIA L4 or RTX PRO 6000 Blackwell GPU to a Cloud Run service, job or worker pool, so a container serves models serverlessly, billed per second and able to scale to zero.", "url": "https://www.anchorterminal.com/tools/cloud-run-gpus", "markdownUrl": "https://www.anchorterminal.com/tools/cloud-run-gpus.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloud-run-gpus.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json", "dns": "cloud-run-gpus.grade.anchorterminal.com", "license": "Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0", "transports": [], "remoteUrl": "https://run.googleapis.com", "packages": [ { "registry": "pypi", "name": "google-cloud-run" }, { "registry": "npm", "name": "@google-cloud/run" } ], "auth": "oauth", "authNotes": "Deploys go through the Cloud Run Admin API with OAuth 2.0 bearer tokens from a service account or Application Default Credentials, under IAM roles such as roles/run.developer and roles/run.invoker. A deployed service can require IAM authentication or allow public calls. A project with billing enabled is set up in the console first.", "pricing": "usage", "pricingNotes": "Per second, instance-based billing only. L4 $0.0001867 a second (about $0.67 an hour) without zonal redundancy, $0.0002909 with; RTX PRO 6000 $0.00036522 (about $1.31 an hour) and $0.00056913. CPU and memory extra, with a minimum of 4 vCPU and 16 GiB (L4) or 20 vCPU and 80 GiB (RTX PRO 6000).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the Cloud Run pricing, GPU or quotas pages (checked 2026-11-06). Billing runs through a Google Cloud billing account.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.cloud.google.com/run/docs/configuring/services/gpu", "openapi": "https://run.googleapis.com/$discovery/rest?version=v2", "capabilities": [ "compute.serverless", "compute.gpu", "compute.endpoints", "compute.containers", "compute.batch" ], "tags": [ "hosted", "official", "usage", "per-second", "scale-to-zero", "sla", "status-page", "discovery-doc", "l4", "rtx-pro-6000" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 68.4, "grade": "B", "agentReady": false, "rank": 288, "ranked": true, "rankOf": 1486, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 80, "payments": 20, "reliability": 70, "schema": 81, "security": 78, "transparency": 84 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 70, "points": 14, "reason": "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.", "checked": "2026-11-06" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 81, "points": 13.16, "reason": "API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.", "checked": "2026-11-06" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 66, "points": 10.73, "reason": "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.", "checked": "2026-11-06" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 78, "points": 13.65, "reason": "OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.", "checked": "2026-11-06" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 20, "points": 2.5, "reason": "No x402, MPP or L402 (0). Per-second GPU, CPU and memory prices published without a login (20). The Cloud Run free tier covers CPU and memory, not GPUs, and the $300 trial credit needs a payment method (0). A person creates the project and billing account in a browser (0). 0+20+0+0 = 20.", "checked": "2026-11-06" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 80, "points": 7, "reason": "Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.", "checked": "2026-11-06" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 84, "points": 7.35, "note": "editorial 69, provenance 99", "reason": "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.", "checked": "2026-11-06" } ], "assessment": { "date": "2026-11-06", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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.", "maintenance": "Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.", "payments": "No x402, MPP or L402 (0). Per-second GPU, CPU and memory prices published without a login (20). The Cloud Run free tier covers CPU and memory, not GPUs, and the $300 trial credit needs a payment method (0). A person creates the project and billing account in a browser (0). 0+20+0+0 = 20.", "reliability": "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.", "schema": "API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.", "security": "OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.", "transparency": "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." }, "sources": [ { "what": "GPU support for services", "url": "https://docs.cloud.google.com/run/docs/configuring/services/gpu", "seen": "2026-11-06" }, { "what": "GPU support for jobs", "url": "https://docs.cloud.google.com/run/docs/configuring/jobs/gpu", "seen": "2026-11-06" }, { "what": "GPU best practices", "url": "https://docs.cloud.google.com/run/docs/configuring/services/gpu-best-practices", "seen": "2026-11-06" }, { "what": "quotas and limits", "url": "https://docs.cloud.google.com/run/quotas", "seen": "2026-11-06" }, { "what": "release notes", "url": "https://docs.cloud.google.com/run/docs/release-notes", "seen": "2026-11-06" }, { "what": "pricing", "url": "https://cloud.google.com/run/pricing", "seen": "2026-11-06" }, { "what": "SLA", "url": "https://cloud.google.com/run/sla", "seen": "2026-11-06" }, { "what": "Google Cloud incident feed", "url": "https://status.cloud.google.com/incidents.json", "seen": "2026-11-06" }, { "what": "20 August 2026 incident", "url": "https://status.cloud.google.com/incidents/utF3FMFdQfwBzJcGG6vf", "seen": "2026-11-06" } ], "openQuestions": [ "unchecked: rate limits on the Cloud Run Admin API, which the quotas page read doesn't give", "The Google Cloud terms, privacy notice and security.txt were not re-read for this listing; the provenance follows the Document AI check of 1 November 2026", "The status feed doesn't break incidents down by GPU, so how the three Cloud Run incidents affected GPU instances is not known" ] }, "negative": 0, "verdict": "Serverless GPUs on Cloud Run, an L4 or RTX PRO 6000 per instance, billed per second, scaling to zero and starting in about 5 seconds before the model loads, with a published SLA and IAM. One GPU per instance, 3 GPUs of default quota a region and instance-based billing limit it to small and mid-size models.", "bestFor": "Serving small and mid-size open models, or batch jobs, from a container that should scale to zero.", "strengths": [ "Scales to zero, bills per second, and instances with drivers start in about 5 seconds", "SLA of 99.95% with zonal redundancy and 99.5% without, plus Google's status feed", "IAM roles for deploying and invoking, Cloud Audit Logs and services that can require authentication", "Per-second prices public, L4 from about $0.67 a GPU-hour without zonal redundancy", "The same GPU option on services, jobs (up to 12 hours) and worker pools" ], "weaknesses": [ "One GPU per instance, L4 (24 GB) or RTX PRO 6000 (96 GB) only, so large models don't fit", "Default quota is 3 GPUs a region; more needs a quota request", "Model load time comes on top of the 5-second start, and minimum instances bill while idle", "No free GPU tier, and the trial credit needs a payment method", "Google's APIs accept OAuth tokens in a URL query parameter" ], "agentNotes": [ "Pass `--gpu 1 --gpu-type nvidia-l4` (or nvidia-rtx-pro-6000) with at least 4 vCPU and 16 GiB, and `--no-cpu-throttling` for instance-based billing", "Load model weights from Cloud Storage at startup in parallel; bake them into the image only below about 10 GB", "Turn zonal redundancy off for cheaper, more readily granted quota when failover isn't required", "Set minimum instances to 0 unless cold starts matter, since minimum instances bill at the full rate", "Send OAuth tokens in the `Authorization` header, never as `access_token` in the URL" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68.4 } ], "editorialScores": { "ergonomics": 66, "maintenance": 80, "payments": 20, "reliability": 70, "schema": 81, "security": 78, "transparency": 69 }, "provenanceScore": 99, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-06", "grade": "B", "kind": "listed", "method": "0.7", "score": 68.4 } ] }, "connect": { "headless": { "command": "gcloud run deploy SERVICE --image IMAGE --gpu 1 --gpu-type nvidia-l4 --cpu 4 --memory 16Gi --no-cpu-throttling --region europe-west1" } }, "letme": { "capability": "https://letme.dev/compute.serverless", "tool": "https://letme.dev/cloud-run-gpus" }, "sameCompany": [ "gemini-api", "vertex-ai", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-cloud-tts", "gemini-live", "google-adk", "google-memory-bank", "google-secret-manager", "google-cloud-document-ai", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api" ], "notable": [ "Instances with an L4 or RTX PRO 6000 GPU and drivers pre-installed start in about 5 seconds, before the container loads its model, per the GPU page (https://docs.cloud.google.com/run/docs/configuring/services/gpu)", "GPU services became generally available on 7 April 2025 and RTX PRO 6000 Blackwell support on 13 April 2026; jobs with GPUs can run up to 12 hours since 30 October 2026, per the release notes (https://docs.cloud.google.com/run/docs/release-notes)", "A project gets 3 GPUs of quota per region (zonal redundancy off) on its first GPU deployment, and more needs a quota request; quota without zonal redundancy is granted more readily (https://docs.cloud.google.com/run/docs/configuring/services/gpu)", "The SLA gives GPU services 99.95% monthly uptime with zonal redundancy and 99.5% without (https://cloud.google.com/run/sla)", "The Google Cloud incident feed names Cloud Run in three multi-product incidents from 8 August to 6 November 2026, among them a service outage on 20 August (15:40 to 19:20 UTC) (https://status.cloud.google.com/incidents/utF3FMFdQfwBzJcGG6vf)" ], "area": "models", "details": [ { "label": "Surface listed", "value": "GPUs on Cloud Run services, jobs and worker pools, configured through gcloud, YAML, Terraform or the Cloud Run Admin API, read from docs.cloud.google.com (GPU pages for services and jobs, GPU best practices, quotas, release notes), the pricing page, the SLA and status.cloud.google.com on 6 November 2026. Nothing was deployed" }, { "label": "Scope", "value": "The GPU option of Cloud Run. Google Cloud's other model and compute products are separate, and no Anchor Terminal listing covers Cloud Run itself" }, { "label": "GPUs", "value": "One GPU per instance, NVIDIA L4 (24 GB) or RTX PRO 6000 Blackwell (96 GB), attached to one container" }, { "label": "Regions", "value": "L4 in regions including europe-west1, europe-west4, asia-southeast1 and asia-south1 (by invitation); RTX PRO 6000 in us-central1, europe-west4, asia-southeast1 and asia-south2, among others listed on the GPU page" }, { "label": "Zonal redundancy", "value": "On by default for new services, reserving GPU capacity across zones for failover at a higher price; off is cheaper and fails over on a best-effort basis" }, { "label": "Billing", "value": "Instance-based billing only, for the whole instance lifecycle. Minimum instances bill at the full rate while idle. No per-request fees" }, { "label": "Model loading", "value": "The best-practices page recommends downloading models from Cloud Storage at startup in parallel, and keeping models in the image only below about 10 GB" } ], "unitPrices": [ { "item": "NVIDIA L4, no zonal redundancy", "unit": "gpu-hour", "usd": 0.67, "note": "$0.0001867 a second, tier 1 regions; CPU and memory extra" }, { "item": "NVIDIA L4, zonal redundancy", "unit": "gpu-hour", "usd": 1.05, "note": "$0.0002909 a second" }, { "item": "NVIDIA RTX PRO 6000, no zonal redundancy", "unit": "gpu-hour", "usd": 1.31, "note": "$0.00036522 a second" }, { "item": "NVIDIA RTX PRO 6000, zonal redundancy", "unit": "gpu-hour", "usd": 2.05, "note": "$0.00056913 a second" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoints are on googleapis.com, Google's API domain. Docs are on docs.cloud.google.com.", "endpointOnVendorDomain": true, "terms": "https://cloud.google.com/terms", "privacy": "https://cloud.google.com/terms/cloud-privacy-notice", "statusPage": "https://status.cloud.google.com", "changelog": "https://docs.cloud.google.com/run/docs/release-notes", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Legal entity, terms, privacy notice and security.txt as on the Google Cloud Document AI listing, checked 1 November 2026, and not re-read for this listing.", "docs.cloud.google.com/robots.txt and cloud.google.com/robots.txt allow the Cloud Run pages read; status.cloud.google.com/robots.txt allows everything.", "The Cloud Run SLA lists GPU services separately, 99.95% with zonal redundancy and 99.5% without (https://cloud.google.com/run/sla)." ], "score": 99, "checks": [ { "check": "Legal entity named", "value": "Google LLC", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "google.com, registered 1997-09-15 (29 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "run.googleapis.com", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 7 of the 7 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "read, states 7 of the 8 things a reader expects", "points": 9.3, "max": 10, "state": "part" }, { "check": "Status page", "value": "status.cloud.google.com", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" }, { "check": "People named", "value": "5 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://cloud.google.com/terms", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-09-02", "words": 13806, "points": 10, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "(Last modified September 2, 2026)", "says": "Last updated 2026-09-02" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "federal government entity, then the following applies: ALL CLAIMS ARISING OUT OF OR RELATING TO THIS AGREEMENT OR THE SERVICES WILL BE GOVERNED BY THE LAWS OF THE UNITED STATES OF AMERICA, EXCLUDING ITS CONFLICT OF LAWS RULES.", "says": "The law of the United States of America" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "…GWS Services, SecOps Services, Looker (original) Services, or Cloud Identity Services, as applicable, is limited to the Fees Customer paid for such Services during the 12 month period before the event giving rise to Liability, except Google’s total aggregate Liability for damages arising out of or related to Services…", "says": "Capped at the fees paid in the 12 months before the claim or $5,000" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "Customer may also terminate this Agreement for convenience under Section 8.5 (Termination for Convenience)." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "(i) With respect to GCP Services and their corresponding TSS, unless otherwise noted by Google, material updates to this Agreement will become effective 30 days after they are posted.", "says": "Gives 30 days of notice before a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "For clarity, Customer may not integrate the Google Workspace Services, SecOps Services, or Cloud Identity Services into Customer Applications or create or host Customer Applications using the Google Workspace Services, SecOps Services, or Cloud Identity Services under this Agreement, and Customer may only integrate Lo…" }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": true, "quote": "Cloud-native relational database with unlimited scale and 99.999% availability.", "says": "Names 99.999% availability" } ], "toKnow": [ { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "For purposes of GCP Services and TSS only, Google may terminate this Agreement or any applicable Order Form for its convenience at any time with 30 days' prior written notice to Customer." } ], "notes": [ { "date": "2026-10-08", "text": "Google may change its fees at any time unless an addendum or order form expressly says otherwise.", "quote": "Google may change the Fees at any time unless otherwise expressly agreed in an addendum or Order Form." }, { "date": "2026-10-08", "text": "Google's total liability for services or software supplied free of charge is limited to 5,000 US dollars.", "quote": "except Google’s total aggregate Liability for damages arising out of or related to Services or Software provided free of charge is limited to $5,000." }, { "date": "2026-10-08", "text": "When automated safety tools detect potential abuse of Generative AI Services, Google may log customer prompts to review whether a violation occurred.", "quote": "Google may log Customer prompts solely for the purpose of reviewing and determining whether a violation has occurred." } ] }, { "kind": "privacy", "url": "https://cloud.google.com/terms/cloud-privacy-notice", "state": "read", "readAt": "2026-10-09", "statedDate": "2026-09-28", "words": 11342, "points": 9.3, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "(Last modified September 28, 2026)", "says": "Last updated 2026-09-28" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "This Google Cloud Privacy Notice describes how we collect" }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "retention periods (which can be over a year) for Service" }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "trusted third party providers to process it for us as we" }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": false }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "authority if you have concerns regarding your rights under" }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "Service Data we process in accordance with this Privacy" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "Economic Area, the UK or Switzerland, we comply with" } ], "notes": [ { "date": "2026-10-08", "text": "This notice covers Service Data only and does not cover Customer Data or Partner Data, which the Cloud Data Processing Addendum governs.", "quote": "applies solely to Service Data and does" } ] } ] }, "humans": { "slug": "cloud-run-gpus", "checked": "2026-11-06", "company": "Google Cloud", "people": [ { "name": "Larry Page", "role": "Co-founder, Google, left executive roles in December 2019 and sits on Alphabet's board", "founder": true, "bio": "Larry Page co-founded Google with Sergey Brin, whom he met at Stanford University in 1995, and co-created the PageRank search ranking algorithm. He was Google's chief executive from 1997 to 2001 and from 2011 to 2015, then led its parent Alphabet until December 2019. He remains on Alphabet's board.", "bioSources": [ "https://about.google/intl/ALL_en/our-story/", "https://en.wikipedia.org/wiki/Larry_Page" ], "page": "/people/larry-page/" }, { "name": "Sergey Brin", "role": "Co-founder, Google, left executive roles in 2019 and sits on Alphabet's board", "founder": true, "bio": "Sergey Brin co-founded Google with Larry Page, whom he met at Stanford University in 1995, and together they built the search engine that became Google. He was president of Alphabet, Google's parent company, until stepping down in 2019, and remains an Alphabet co-founder and board member.", "bioSources": [ "https://about.google/intl/ALL_en/our-story/", "https://en.wikipedia.org/wiki/Sergey_Brin" ], "page": "/people/sergey-brin/" }, { "name": "Sundar Pichai", "role": "CEO, Google and Alphabet", "bio": "Sundar Pichai has been chief executive of Google since 2015 and of its parent Alphabet since 2019. He joined Google in 2004 and led product management for its client software, including Chrome and ChromeOS, then took on Drive, Gmail, Maps and Android before being named product chief.", "bioSources": [ "https://en.wikipedia.org/wiki/Sundar_Pichai", "https://about.google/company-info/" ], "page": "/people/sundar-pichai/" }, { "name": "Thomas Kurian", "role": "CEO, Google Cloud", "bio": "Thomas Kurian has led Google Cloud as chief executive since 2019, after joining Google's cloud organisation in November 2018. Before that he spent more than twenty years at Oracle, rising to president of product development, in charge of Oracle Database, Fusion Middleware and its business applications.", "bioSources": [ "https://en.wikipedia.org/wiki/Thomas_Kurian", "https://en.wikipedia.org/wiki/Google_Cloud" ], "page": "/people/thomas-kurian/" }, { "name": "Demis Hassabis", "role": "Co-founder and CEO, Google DeepMind", "bio": "Demis Hassabis co-founded DeepMind, which started in 2010, and leads Google DeepMind, formed by bringing Google Brain and DeepMind together. He is also chief executive and co-founder of Isomorphic Labs, and shared the 2024 Nobel Prize in Chemistry with John Jumper for AI research on protein structure prediction.", "bioSources": [ "https://deepmind.google/about/", "https://en.wikipedia.org/wiki/Demis_Hassabis" ], "page": "/people/demis-hassabis/" } ], "peopleNote": "Google Cloud is Google's cloud business, so the company-level people are the same as for Google (out/top/antigravity-cli.json), with Thomas Kurian added as CEO of Google Cloud from Wikipedia's Google Cloud article (infobox owner Google, CEO Thomas Kurian) and his own article, read 28 October 2026. Copied from the Google Cloud Document AI listing for Cloud Run GPUs on 6 November 2026; no Cloud Run product people were looked for.", "companySocial": { "linkedin": "https://www.linkedin.com/company/google", "x": "https://x.com/Google" }, "support": { "urls": [ "https://cloud.google.com/support-hub", "https://support.google.com/" ], "contactUrls": [ "https://cloud.google.com/contact" ] }, "sources": [ "https://about.google/intl/ALL_en/our-story/", "https://www.linkedin.com/company/google", "https://x.com/Google", "https://cloud.google.com/contact", "https://cloud.google.com/support-hub" ], "ownership": { "status": "subsidiary", "parent": "Alphabet Inc.", "checked": "2026-10-28", "sources": [ "https://en.wikipedia.org/wiki/Google", "https://about.google/company-info/", "https://en.wikipedia.org/wiki/Google_Cloud" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloud-run-gpus.json", "live": { "slug": "cloud-run-gpus", "probe": { "target": "https://run.googleapis.com", "method": "get", "lastAt": "2026-11-07T17:49:34.946235459Z", "lastOk": true, "lastStatus": 404, "lastMs": 33, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 35, "p95ms24h": 110, "samples24h": 195, "samples30d": 195, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 182, "ok": 182 } ] }, "vendorStatus": { "page": "https://status.cloud.google.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:16.629467571Z" }, "versions": [ { "registry": "npm", "name": "@google-cloud/run", "version": "4.2.0", "seenAt": "2026-11-06T23:15:29.275446701Z" }, { "registry": "pypi", "name": "google-cloud-run", "version": "0.16.2", "released": "2026-10-01", "seenAt": "2026-11-06T23:15:27.277547645Z" } ], "npmWeekly": 1706675, "pypiWeekly": 3039289, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-07T16:01:22.068349931Z" }, "pages": [ { "url": "https://docs.cloud.google.com/run/docs/release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:05:47.69894113Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "924ee0205e11" }, { "url": "https://cloud.google.com/terms/cloud-privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:01:29.495526727Z", "changedAt": "2026-11-03T07:43:24.319773868Z", "fingerprint": "b62369d64ac6" }, { "url": "https://cloud.google.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:01:27.593286996Z", "changedAt": "2026-11-03T07:43:22.480965239Z", "fingerprint": "b9ec671a2caf" } ], "updatedAt": "2026-11-07T17:49:34.946235459Z" } }, "verify": { "accepts": "a page on google.com or one of its subdomains", "badgeUrl": "https://www.anchorterminal.com/badges/cloud-run-gpus.svg", "body": { "slug": "cloud-run-gpus", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/cloud-run-gpus", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/cloud-run-gpus\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/cloud-run-gpus.svg\" alt=\"Cloud Run GPUs on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Cloud Run GPUs on Anchor Terminal](https://www.anchorterminal.com/badges/cloud-run-gpus.svg)](https://www.anchorterminal.com/tools/cloud-run-gpus)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/cloud-run-gpus\"\u003eCloud Run GPUs on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/cloud-run-gpus", "json": "https://www.anchorterminal.com/tools/cloud-run-gpus.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/cloud-run-gpus.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/cloud-run-gpus#pricing", "reviews": "https://www.anchorterminal.com/tools/cloud-run-gpus#reviews", "slim": "https://www.anchorterminal.com/tools/cloud-run-gpus.min.md" }, "markdown": "## Overview\n\n**Grade B · 68.4/100 · rank #288 of 1486 · #2 in GPU \u0026 serverless compute · not agent-ready · confidence medium**\n\n\nMore from Google Cloud, listed separately because each is its own product: [Gemini Developer API](https://www.anchorterminal.com/tools/gemini-api.md) (Model APIs \u0026 inference), [Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/tools/vertex-ai.md) (Model APIs \u0026 inference), [Gemini Embedding](https://www.anchorterminal.com/tools/gemini-embedding.md) (Embeddings \u0026 rerankers), [Vertex AI Gemini tuning](https://www.anchorterminal.com/tools/vertex-ai-tuning.md) (Fine-tuning), [Google Cloud Model Armor](https://www.anchorterminal.com/tools/google-model-armor.md) (Guardrails \u0026 safety filters), [Google Imagen](https://www.anchorterminal.com/tools/google-imagen.md) (Image generation), [Google Veo](https://www.anchorterminal.com/tools/google-veo.md) (Video generation), [Google Lyria](https://www.anchorterminal.com/tools/google-lyria.md) (Music generation), [Google Cloud Speech-to-Text](https://www.anchorterminal.com/tools/google-speech-to-text.md) (Speech-to-text), [Google Cloud Text-to-Speech](https://www.anchorterminal.com/tools/google-cloud-tts.md) (Text-to-speech), [Gemini Live API](https://www.anchorterminal.com/tools/gemini-live.md) (Conversational voice agents), [Agent Development Kit (ADK)](https://www.anchorterminal.com/tools/google-adk.md) (Agent frameworks \u0026 SDKs), [Agent Platform Memory Bank](https://www.anchorterminal.com/tools/google-memory-bank.md) (Agent memory), [Google Cloud Secret Manager](https://www.anchorterminal.com/tools/google-secret-manager.md) (Secrets \u0026 credential vaults), [Google Cloud Document AI](https://www.anchorterminal.com/tools/google-cloud-document-ai.md) (Document parsing \u0026 extraction), [Google Weather API (Maps Platform)](https://www.anchorterminal.com/tools/google-weather-api.md) (Weather \u0026 climate data), [Chrome DevTools MCP](https://www.anchorterminal.com/tools/chrome-devtools-mcp.md) (Browser automation), [Google Maps Platform + Grounding Lite MCP](https://www.anchorterminal.com/tools/google-maps-platform.md) (Maps, geocoding \u0026 places), [Google Cloud Translation](https://www.anchorterminal.com/tools/google-cloud-translation.md) (Translation), [Google Calendar API](https://www.anchorterminal.com/tools/google-calendar-api.md) (Calendars \u0026 scheduling), [Firebase Cloud Messaging](https://www.anchorterminal.com/tools/firebase-cloud-messaging.md) (Notifications), [Google Cloud Storage](https://www.anchorterminal.com/tools/google-cloud-storage.md) (File storage \u0026 sharing), [Google Drive API + MCP](https://www.anchorterminal.com/tools/google-drive-api.md) (File storage \u0026 sharing), [Gemini Enterprise](https://www.anchorterminal.com/tools/gemini-enterprise.md) (Company knowledge \u0026 data catalogues), [Gemini CLI](https://www.anchorterminal.com/tools/gemini-cli.md) (Agent harnesses), [Google Search Console API](https://www.anchorterminal.com/tools/google-search-console.md) (SEO \u0026 search visibility), [Google Ads API](https://www.anchorterminal.com/tools/google-ads-api.md) (Advertising \u0026 campaign operations), [Google Forms API](https://www.anchorterminal.com/tools/google-forms.md) (Forms, surveys \u0026 structured intake), [Google Sheets API](https://www.anchorterminal.com/tools/google-sheets-api.md) (Spreadsheets \u0026 operational tables), [Gmail API](https://www.anchorterminal.com/tools/gmail-api.md) (Mailbox access), [Google People API](https://www.anchorterminal.com/tools/google-people-api.md) (Contacts \u0026 address books).\n\n## Assessment\n\nServerless GPUs on Cloud Run, an L4 or RTX PRO 6000 per instance, billed per second, scaling to zero and starting in about 5 seconds before the model loads, with a published SLA and IAM. One GPU per instance, 3 GPUs of default quota a region and instance-based billing limit it to small and mid-size models.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Google Cloud (https://cloud.google.com/run) |\n| Kind | Platform |\n| Category | GPU \u0026 serverless compute (https://www.anchorterminal.com/categories/gpu-compute) |\n| Endpoint | `https://run.googleapis.com` |\n| Auth | OAuth · Deploys go through the Cloud Run Admin API with OAuth 2.0 bearer tokens from a service account or Application Default Credentials, under IAM roles such as roles/run.developer and roles/run.invoker. A deployed service can require IAM authentication or allow public calls. A project with billing enabled is set up in the console first. |\n| Pricing | Pay per use (Pay per use) · Per second, instance-based billing only. L4 $0.0001867 a second (about $0.67 an hour) without zonal redundancy, $0.0002909 with; RTX PRO 6000 $0.00036522 (about $1.31 an hour) and $0.00056913. CPU and memory extra, with a minimum of 4 vCPU and 16 GiB (L4) or 20 vCPU and 80 GiB (RTX PRO 6000). |\n| x402 | No · No x402, MPP or L402 on the Cloud Run pricing, GPU or quotas pages (checked 2026-11-06). Billing runs through a Google Cloud billing account. |\n| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 |\n| Packages | pypi: `google-cloud-run`; npm: `@google-cloud/run` |\n| Docs | https://docs.cloud.google.com/run/docs/configuring/services/gpu |\n| llms.txt | not found |\n| Last release | 2026-10-30 |\n| Surface listed | GPUs on Cloud Run services, jobs and worker pools, configured through gcloud, YAML, Terraform or the Cloud Run Admin API, read from docs.cloud.google.com (GPU pages for services and jobs, GPU best practices, quotas, release notes), the pricing page, the SLA and status.cloud.google.com on 6 November 2026. Nothing was deployed |\n| Scope | The GPU option of Cloud Run. Google Cloud's other model and compute products are separate, and no Anchor Terminal listing covers Cloud Run itself |\n| GPUs | One GPU per instance, NVIDIA L4 (24 GB) or RTX PRO 6000 Blackwell (96 GB), attached to one container |\n| Regions | L4 in regions including europe-west1, europe-west4, asia-southeast1 and asia-south1 (by invitation); RTX PRO 6000 in us-central1, europe-west4, asia-southeast1 and asia-south2, among others listed on the GPU page |\n| Zonal redundancy | On by default for new services, reserving GPU capacity across zones for failover at a higher price; off is cheaper and fails over on a best-effort basis |\n| Billing | Instance-based billing only, for the whole instance lifecycle. Minimum instances bill at the full rate while idle. No per-request fees |\n| Model loading | The best-practices page recommends downloading models from Cloud Storage at startup in parallel, and keeping models in the image only below about 10 GB |\n| Capabilities | compute.serverless, compute.gpu, compute.endpoints, compute.containers, compute.batch |\n| Tags | hosted, official, usage, per-second, scale-to-zero, sla, status-page, discovery-doc, l4, rtx-pro-6000 |\n| JSON | https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 70 | 14.0 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 81 | 13.2 |\n| Agent ergonomics | 13% | 16.2 | 66 | 10.7 |\n| Security \u0026 auth | 14% | 17.5 | 78 | 13.7 |\n| Payments \u0026 pricing | 10% | 12.5 | 20 | 2.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 80 | 7.0 |\n| Transparency \u0026 trust (editorial 69, provenance 99) | 7% | 8.8 | 84 | 7.3 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **68.4 → B** |\n\n### Why each score\n\n- Reliability 70 (checked 2026-11-06): 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.\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 81 (checked 2026-11-06): API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.\n- Agent ergonomics 66 (checked 2026-11-06): 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.\n- Security \u0026 auth 78 (checked 2026-11-06): OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.\n- Payments \u0026 pricing 20 (checked 2026-11-06): No x402, MPP or L402 (0). Per-second GPU, CPU and memory prices published without a login (20). The Cloud Run free tier covers CPU and memory, not GPUs, and the $300 trial credit needs a payment method (0). A person creates the project and billing account in a browser (0). 0+20+0+0 = 20.\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 80 (checked 2026-11-06): Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.\n- Transparency \u0026 trust 84 (checked 2026-11-06): 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.\n\nFix list, everything this grade says the listing lacks, the biggest gain first (12 items). What it covers is at https://www.anchorterminal.com/fixes/cloud-run-gpus.md (JSON https://www.anchorterminal.com/fixes/cloud-run-gpus.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{\"listing\": \"cloud-run-gpus\", \"plan\": \"read\"}`, free while the beta runs\n\n### What we couldn't check\n\n- unchecked: rate limits on the Cloud Run Admin API, which the quotas page read doesn't give\n- The Google Cloud terms, privacy notice and security.txt were not re-read for this listing; the provenance follows the Document AI check of 1 November 2026\n- The status feed doesn't break incidents down by GPU, so how the three Cloud Run incidents affected GPU instances is not known\n\n### Sources\n\n- GPU support for services: \u003chttps://docs.cloud.google.com/run/docs/configuring/services/gpu\u003e (seen 2026-11-06)\n- GPU support for jobs: \u003chttps://docs.cloud.google.com/run/docs/configuring/jobs/gpu\u003e (seen 2026-11-06)\n- GPU best practices: \u003chttps://docs.cloud.google.com/run/docs/configuring/services/gpu-best-practices\u003e (seen 2026-11-06)\n- quotas and limits: \u003chttps://docs.cloud.google.com/run/quotas\u003e (seen 2026-11-06)\n- release notes: \u003chttps://docs.cloud.google.com/run/docs/release-notes\u003e (seen 2026-11-06)\n- pricing: \u003chttps://cloud.google.com/run/pricing\u003e (seen 2026-11-06)\n- SLA: \u003chttps://cloud.google.com/run/sla\u003e (seen 2026-11-06)\n- Google Cloud incident feed: \u003chttps://status.cloud.google.com/incidents.json\u003e (seen 2026-11-06)\n- 20 August 2026 incident: \u003chttps://status.cloud.google.com/incidents/utF3FMFdQfwBzJcGG6vf\u003e (seen 2026-11-06)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus/history.json\n\n- 2026-11-06: graded 68.4 B (methodology 0.7)\n\n## Who's behind it (provenance 99/100, checked 2026-11-06)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Google LLC | 20/20 |\n| Domain age | google.com, registered 1997-09-15 (29 years) | 15/15 |\n| Endpoint on the vendor's domain | run.googleapis.com | 15/15 |\n| Terms of service | read, states 7 of the 7 things a reader expects | 10/10 |\n| Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 |\n| Status page | status.cloud.google.com | 10/10 |\n| Changelog | published | 10/10 |\n| security.txt | valid | 10/10 |\n| People named | 5 named with their role, none with a public profile | 7/10 |\n| Support route | help pages | 5/5 |\n\nThe endpoints are on googleapis.com, Google's API domain. Docs are on docs.cloud.google.com.\n\nLegal entity, terms, privacy notice and security.txt as on the Google Cloud Document AI listing, checked 1 November 2026, and not re-read for this listing.\n\ndocs.cloud.google.com/robots.txt and cloud.google.com/robots.txt allow the Cloud Run pages read; status.cloud.google.com/robots.txt allows everything.\n\nThe Cloud Run SLA lists GPU services separately, 99.95% with zonal redundancy and 99.5% without (https://cloud.google.com/run/sla).\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://cloud.google.com/terms), read 2026-10-08, dated 2026-09-02, states 7 of the 7 things a reader expects.\n\n- To know. Says access can be ended without notice or for any reason. \"For purposes of GCP Services and TSS only, Google may terminate this Agreement or any applicable Order Form for its convenience at any time with 30 days' prior written notice to Customer.\"\n- Gives the date it was last updated. Last updated 2026-09-02.\n- Names the governing law or courts. The law of the United States of America.\n- States a limit on its liability. Capped at the fees paid in the 12 months before the claim or $5,000.\n- Says how changes to the terms are announced. Gives 30 days of notice before a change.\n- Refers to a service level or uptime commitment. Names 99.999% availability.\n- Also in the text (2026-10-08). Google may change its fees at any time unless an addendum or order form expressly says otherwise. \"Google may change the Fees at any time unless otherwise expressly agreed in an addendum or Order Form.\"\n- Also in the text (2026-10-08). Google's total liability for services or software supplied free of charge is limited to 5,000 US dollars. \"except Google’s total aggregate Liability for damages arising out of or related to Services or Software provided free of charge is limited to $5,000.\"\n- Also in the text (2026-10-08). When automated safety tools detect potential abuse of Generative AI Services, Google may log customer prompts to review whether a violation occurred. \"Google may log Customer prompts solely for the purpose of reviewing and determining whether a violation has occurred.\"\n\n**Privacy policy** (https://cloud.google.com/terms/cloud-privacy-notice), read 2026-10-09, dated 2026-09-28, states 7 of the 8 things a reader expects.\n\n- Gives the date it was last updated. Last updated 2026-09-28.\n- Not found in the text. Says whether personal data is sold or shared for advertising.\n- Also in the text (2026-10-08). This notice covers Service Data only and does not cover Customer Data or Partner Data, which the Cloud Data Processing Addendum governs. \"applies solely to Service Data and does\"\n\n## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade)\n\n### Key people\n\n- Larry Page, Co-founder, Google, left executive roles in December 2019 and sits on Alphabet's board\n- Sergey Brin, Co-founder, Google, left executive roles in 2019 and sits on Alphabet's board\n- Sundar Pichai, CEO, Google and Alphabet\n- Thomas Kurian, CEO, Google Cloud\n- Demis Hassabis, Co-founder and CEO, Google DeepMind\n- Note: Google Cloud is Google's cloud business, so the company-level people are the same as for Google (out/top/antigravity-cli.json), with Thomas Kurian added as CEO of Google Cloud from Wikipedia's Google Cloud article (infobox owner Google, CEO Thomas Kurian) and his own article, read 28 October 2026. Copied from the Google Cloud Document AI listing for Cloud Run GPUs on 6 November 2026; no Cloud Run product people were looked for.\n- Google Cloud: LinkedIn https://www.linkedin.com/company/google X https://x.com/Google\n\n### Ownership and investors\n\n- Ownership: Part of Alphabet Inc.\n\n### Getting support\n\n- Help: https://cloud.google.com/support-hub\n- Help: https://support.google.com/\n- Sources: https://about.google/intl/ALL_en/our-story/, https://www.linkedin.com/company/google, https://x.com/Google, https://cloud.google.com/contact, https://cloud.google.com/support-hub\n\n## Live (updated 2026-11-07 17:49 UTC)\n\n- Right now: up, HTTP 404, 33 ms, checked 2026-11-07 17:49 UTC (get on `https://run.googleapis.com`)\n- Uptime 24h 100.0% (195 probes) · 30 days 100.0% (195 probes) · p50 35 ms · p95 110 ms\n- Vendor status page: not read, no machine-readable status found\n- npm `@google-cloud/run` 4.2.0\n- pypi `google-cloud-run` 0.16.2, released 2026-10-01\n- security.txt: valid, expires 2030-04-01T00:00:00z\n- Watching changelog \u003chttps://docs.cloud.google.com/run/docs/release-notes\u003e\n- Watching privacy \u003chttps://cloud.google.com/terms/cloud-privacy-notice\u003e, last changed 2026-11-03 07:43 UTC\n- Watching terms \u003chttps://cloud.google.com/terms\u003e, last changed 2026-11-03 07:43 UTC\n- Always current: https://www.anchorterminal.com/api/v1/live/cloud-run-gpus.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| NVIDIA L4, no zonal redundancy | $0.67 | per GPU-hour | $0.0001867 a second, tier 1 regions; CPU and memory extra |\n| NVIDIA L4, zonal redundancy | $1.05 | per GPU-hour | $0.0002909 a second |\n| NVIDIA RTX PRO 6000, no zonal redundancy | $1.31 | per GPU-hour | $0.00036522 a second |\n| NVIDIA RTX PRO 6000, zonal redundancy | $2.05 | per GPU-hour | $0.00056913 a second |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Scales to zero, bills per second, and instances with drivers start in about 5 seconds\n- SLA of 99.95% with zonal redundancy and 99.5% without, plus Google's status feed\n- IAM roles for deploying and invoking, Cloud Audit Logs and services that can require authentication\n- Per-second prices public, L4 from about $0.67 a GPU-hour without zonal redundancy\n- The same GPU option on services, jobs (up to 12 hours) and worker pools\n\n## Weaknesses\n\n- One GPU per instance, L4 (24 GB) or RTX PRO 6000 (96 GB) only, so large models don't fit\n- Default quota is 3 GPUs a region; more needs a quota request\n- Model load time comes on top of the 5-second start, and minimum instances bill while idle\n- No free GPU tier, and the trial credit needs a payment method\n- Google's APIs accept OAuth tokens in a URL query parameter\n\n\n\n## Before you call it (notes for agents)\n\n1. Pass `--gpu 1 --gpu-type nvidia-l4` (or nvidia-rtx-pro-6000) with at least 4 vCPU and 16 GiB, and `--no-cpu-throttling` for instance-based billing\n2. Load model weights from Cloud Storage at startup in parallel; bake them into the image only below about 10 GB\n3. Turn zonal redundancy off for cheaper, more readily granted quota when failover isn't required\n4. Set minimum instances to 0 unless cold starts matter, since minimum instances bill at the full rate\n5. Send OAuth tokens in the `Authorization` header, never as `access_token` in the URL\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Modal | B | 62.7 | 543 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/modal.md |\n| Beam | C | 56.2 | 835 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/beam.md |\n| Runpod | C | 55.6 | 859 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/runpod.md |\n| Verda | D | 53.3 | 946 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/verda.md |\n| Cerebrium | D | 52.5 | 983 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/cerebrium.md |\n| Nebius AI Cloud | BB | 71.2 | 167 | compute.gpu, compute.endpoints, compute.batch, compute.containers | no | https://www.anchorterminal.com/tools/nebius-ai-cloud.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Instances with an L4 or RTX PRO 6000 GPU and drivers pre-installed start in about 5 seconds, before the container loads its model, per the GPU page (source: \u003chttps://docs.cloud.google.com/run/docs/configuring/services/gpu\u003e)\n- GPU services became generally available on 7 April 2025 and RTX PRO 6000 Blackwell support on 13 April 2026; jobs with GPUs can run up to 12 hours since 30 October 2026, per the release notes (source: \u003chttps://docs.cloud.google.com/run/docs/release-notes\u003e)\n- A project gets 3 GPUs of quota per region (zonal redundancy off) on its first GPU deployment, and more needs a quota request; quota without zonal redundancy is granted more readily (source: \u003chttps://docs.cloud.google.com/run/docs/configuring/services/gpu\u003e)\n- The SLA gives GPU services 99.95% monthly uptime with zonal redundancy and 99.5% without (source: \u003chttps://cloud.google.com/run/sla\u003e)\n- The Google Cloud incident feed names Cloud Run in three multi-product incidents from 8 August to 6 November 2026, among them a service outage on 20 August (15:40 to 19:20 UTC) (source: \u003chttps://status.cloud.google.com/incidents/utF3FMFdQfwBzJcGG6vf\u003e)\n\n- #2 of 22 in Best GPU and serverless compute for AI workloads: https://www.anchorterminal.com/best/gpu-compute/index.md\n- All 231 gpu compute comparisons: https://www.anchorterminal.com/compare/gpu-compute/index.md\n\n## Compare\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md): B 62.7 vs B 68.4\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md): C 56.2 vs B 68.4\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md): D 52.5 vs B 68.4\n- [Cloud Run GPUs vs CoreWeave](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.md): B 68.4 vs C 60.5\n- [Cloud Run GPUs vs Crusoe Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.md): B 68.4 vs B 62.4\n- [Cloud Run GPUs vs GPUsMarket](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.md): B 68.4 vs E 39.6\n- [Cloud Run GPUs vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.md): B 68.4 vs B 66.7\n- [Cloud Run GPUs vs Hyperbolic](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.md): B 68.4 vs E 38.7\n- [Cloud Run GPUs vs Lambda Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.md): B 68.4 vs D 52.9\n- [Cloud Run GPUs vs Massed Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.md): B 68.4 vs E 42.6\n- [Cloud Run GPUs vs Nebius AI Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.md): B 68.4 vs BB 71.2\n- [Cloud Run GPUs vs Northflank](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.md): B 68.4 vs C 54\n- [Cloud Run GPUs vs Thunder Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.md): B 68.4 vs D 51.3\n- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md): B 68.4 vs C 58.1\n- [Cloud Run GPUs vs Koyeb](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md): B 68.4 vs D 46.6\n- [Cloud Run GPUs vs Modal](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.md): B 68.4 vs B 62.7\n- [Cloud Run GPUs vs Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md): B 68.4 vs B 65.2\n- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md): B 68.4 vs C 55.6\n- [Cloud Run GPUs vs Vast.ai](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.md): B 68.4 vs C 56.4\n- [Cloud Run GPUs vs Verda](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.md): B 68.4 vs D 53.3\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on google.com or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"cloud-run-gpus\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/cloud-run-gpus\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/cloud-run-gpus.svg\" alt=\"Cloud Run GPUs on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Cloud Run GPUs on Anchor Terminal](https://www.anchorterminal.com/badges/cloud-run-gpus.svg)](https://www.anchorterminal.com/tools/cloud-run-gpus)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/cloud-run-gpus\"\u003eCloud Run GPUs on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Cloud Run GPUs is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/cloud-run-gpus-dark.png\n- Light: https://www.anchorterminal.com/assets/share/cloud-run-gpus-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "GPU \u0026 serverless compute", "url": "https://www.anchorterminal.com/categories/gpu-compute" }, { "name": "Cloud Run GPUs", "url": "" } ], "description": "Cloud Run GPUs attach one NVIDIA L4 or RTX PRO 6000 Blackwell GPU to a Cloud Run service, job or worker pool, so a container serves models serverlessly, billed per second and able to scale to zero.", "facts": [ "rank #288 of 1486", "OAuth auth", "0 desk reviews" ], "h1": "Cloud Run GPUs", "image": "https://www.anchorterminal.com/assets/og/tools-cloud-run-gpus.png", "path": "/tools/cloud-run-gpus", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs review (2026): pricing, alternatives and grade B", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/tools/cloud-run-gpus" }, "tokens": { "markdown": 7600, "slim": 1480 }, "version": 1 }