{ "data": { "a": { "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" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "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 } }, "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" ], "area": "models", "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 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloud-run-gpus.json", "live": { "slug": "cloud-run-gpus", "probe": { "target": "https://run.googleapis.com", "method": "get", "lastAt": "2026-11-07T18:07:48.433280085Z", "lastOk": true, "lastStatus": 404, "lastMs": 93, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 35, "p95ms24h": 114, "samples24h": 198, "samples30d": 198, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 185, "ok": 185 } ] }, "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": "2026-11-07T18:07:48.433280085Z" } }, "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Lambda Cloud's 52.9 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "lambda", "name": "Lambda Cloud", "vendor": "Lambda", "vendorUrl": "https://lambda.ai", "kind": "http-api", "category": "gpu-compute", "summary": "On-demand GPU virtual machines and clusters, with an API for provisioning compute and persistent storage.", "url": "https://www.anchorterminal.com/tools/lambda", "markdownUrl": "https://www.anchorterminal.com/tools/lambda.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/lambda.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/lambda.json", "dns": "lambda.grade.anchorterminal.com", "transports": [ "http" ], "remoteUrl": "https://cloud.lambda.ai/api/v1", "packages": [], "auth": "api-key", "authNotes": "API key created at cloud.lambda.ai/api-keys and sent as `Authorization: Bearer`. HTTP Basic with the key as the username (`curl -u 'KEY:'`) still works as a legacy option. SSH keys registered in the account are injected into launched instances.", "pricing": "usage", "pricingNotes": "On-demand, per GPU an hour, Tesla V100 16 GB $0.79, A100 40 GB $1.99, A100 80 GB $2.79, H100 SXM 80 GB $3.99, B200 180 GB $6.69. 1-Click Clusters of HGX B200 are quoted per GPU-hour at $9.86 for 16 GPUs, $9.36 for 64 and $8.87 for 256 or more on two-week to one-year commitments. Instances bill in one-minute increments from the moment they pass health checks until you terminate them, invoiced weekly. Filesystems bill per GB used a month in one-hour increments. No free tier (https://lambda.ai/pricing, https://docs.lambda.ai/public-cloud/billing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.lambda.com/public-cloud/on-demand/", "openapi": "https://docs.lambda.com/api/cloud/spec.json", "capabilities": [ "compute.gpu", "compute.containers" ], "tags": [ "hosted", "usage-priced", "openapi", "enterprise" ], "graded": true, "anchor": { "graded": true, "score": 52.9, "grade": "D", "agentReady": false, "rank": 963, "ranked": true, "rankOf": 1486, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 5, "payments": 20, "reliability": 55, "schema": 69, "security": 70, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated.", "bestFor": "Agents or pipelines that need a whole GPU machine with SSH for hours, such as training or batch jobs, and will manage the lifecycle themselves.", "strengths": [ "H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing", "OpenAPI 3.1 spec with documented error codes, a `suggestion` field and cursor pagination", "Audit events endpoint filterable by time and resource type", "Published rate limits, one request a second and one launch every 12 seconds, with Retry-After on a 429", "Role-based access with service identities and a read-only role, and a trust portal with SOC 2 Type 2 and four ISO certifications" ], "weaknesses": [ "No scale to zero, autoscaling or endpoints; an idle VM bills until terminated", "Seven readable status incidents since August 2026, among them a two-day outage in one region", "No changelog, no llms.txt and no official SDK", "Launch has no idempotency key, and API keys have no documented rotation or expiry", "security.txt expired on 1 June 2026 and no free tier" ], "agentNotes": [ "Call `GET /instance-types` first and read `regions_with_capacity_available` before trying to launch", "Space launch calls 12 seconds apart; a sixth in a minute returns 429 with `global/rate-limited`, so wait for the Retry-After interval", "Branch on the error `code`, not the `message` or `suggestion`, which Lambda says may change", "List instances before retrying a failed launch, since there's no idempotency key and a retry can start a second machine", "Terminate the instance in a `finally` block; billing runs by the minute until you do", "Run under a service identity with only the workspace roles it needs, such as Instance Reader for monitoring" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.9 } ], "editorialScores": { "ergonomics": 63, "maintenance": 5, "payments": 20, "reliability": 55, "schema": 69, "security": 70, "transparency": 48 }, "provenanceScore": 71, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl \"https://cloud.lambda.ai/api/v1/instance-types\" -H \"Authorization: Bearer $LAMBDA_API_KEY\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/lambda" }, "area": "models", "unitPrices": [ { "item": "H100 SXM 80 GB", "unit": "gpu-hour", "usd": 3.99, "note": "Billed per minute" }, { "item": "B200 180 GB", "unit": "gpu-hour", "usd": 6.69 }, { "item": "A100 SXM 80 GB", "unit": "gpu-hour", "usd": 2.79 }, { "item": "A100 SXM 40 GB", "unit": "gpu-hour", "usd": 1.99 }, { "item": "Tesla V100 16 GB", "unit": "gpu-hour", "usd": 0.79 }, { "item": "HGX B200 1-Click Cluster, 16 GPUs", "unit": "gpu-hour", "usd": 9.86, "note": "Two-week to one-year commitment; $8.87 at 256 GPUs or more" } ], "provenance": { "legalEntity": "Lambda, Inc.", "domain": "lambda.ai", "domainRegistered": "", "domainNote": "Lambda moved from lambdalabs.com, registered 2008-05-29, to lambda.ai. The .ai registry's RDAP server rate-limited our lookup of the new domain.", "endpointOnVendorDomain": true, "terms": "https://lambda.ai/legal/terms-of-service", "privacy": "https://lambda.ai/legal/privacy-policy", "statusPage": "https://status.lambda.ai", "changelog": "", "securityTxt": "expired", "checked": "2026-11-04", "notes": [ "Terms dated August 2025 and the privacy policy of 1 January 2026 name Lambda, Inc., 2510 Zanker Road, San Jose, California (privacy policy per the 1 October 2026 check).", "The API runs on cloud.lambda.ai, a subdomain of the vendor domain. The docs moved from docs.lambda.ai to docs.lambda.com, which docs.lambda.ai now redirects to.", "security.txt expired 2026-06-01 and has no Policy field (read 4 November 2026).", "No public changelog found for the cloud. The OpenAPI spec reports version 1.10.0." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/lambda.json", "live": { "slug": "lambda", "probe": { "target": "https://cloud.lambda.ai/api/v1", "method": "get", "lastAt": "2026-11-07T18:08:02.235491675Z", "lastOk": true, "lastStatus": 403, "lastMs": 1299, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 99.8, "p50ms24h": 744, "p95ms24h": 1112, "samples24h": 239, "samples30d": 7908, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 271 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 236 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 185, "ok": 185 } ], "outages": [ { "start": "2026-10-31T04:40:34.538053708Z", "end": "2026-10-31T05:43:37.088836787Z", "note": "EOF" } ] }, "vendorStatus": { "page": "https://status.lambda.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:09:30.783638133Z" }, "securityTxt": { "url": "https://lambda.ai/.well-known/security.txt", "state": "expired", "expires": "2026-06-01T16:00:00Z", "checkedAt": "2026-11-07T16:01:42.94704571Z" }, "domain": { "domain": "lambda.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/lambda.ai", "checkedAt": "2026-11-01T14:13:00.056712497Z" }, "pages": [ { "url": "https://lambda.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:12:19.409114908Z", "changedAt": "2026-11-07T14:12:19.409114908Z", "fingerprint": "43d2243dd65b" }, { "url": "https://lambda.ai/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:12:14.343180344Z", "changedAt": "2026-11-07T14:12:14.343180344Z", "fingerprint": "d0e1f9cb081a" }, { "url": "https://lambda.ai/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:12:16.798534055Z", "changedAt": "2026-11-07T14:12:16.798534055Z", "fingerprint": "2d5b17c47588" } ], "updatedAt": "2026-11-07T18:09:30.783638133Z" } }, "edges": [ { "by": 75, "category": "maintenance", "leads": "cloud-run-gpus", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "No changelog or release notes found, and the docs pages carry no dates, so we couldn't date the last API change. The spec still reads 1.10.0 although it gained identity, group, role and workspace paths since 1 October (0). No dated changes in the last 90 days found (0). Closed service with a status page that posts updates and a support-ticket API, but no changelog (5 of 15). No official SDK (0). No packages to assess (0). 0 + 0 + 5 + 0 + 0 = 5." }, "scores": { "a": 80, "b": 5 } }, { "by": 24, "category": "transparency", "leads": "cloud-run-gpus", "name": "Transparency \u0026 trust", "reasons": { "a": "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.", "b": "Closed service under California terms dated August 2025 (15). A privacy policy dated 1 January 2026 exists, but we found no retention period for instance disks or filesystems after termination, and the trust portal says none either (10). One dated deprecation in the spec (`/file-systems` in favour of `/filesystems`, not scheduled for removal) and no deprecation policy (8). The trust portal names its subprocessors (Cloudflare, Oracle) and the docs name each region (15). 15 + 10 + 8 + 15 = 48." }, "scores": { "a": 84, "b": 60 } }, { "by": 15, "category": "reliability", "leads": "cloud-run-gpus", "name": "Reliability", "reasons": { "a": "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.", "b": "incident.io page at status.lambda.ai with components (Cloud API, Network, Virtual Machines, Storage and others) and an RSS feed (20). The feed holds only its ten latest items, back to updates of 17 August 2026, and the page lists only incidents linked to components, so 6 to 17 August is partly unread. What is readable since 6 August touches one region or one function each, so partial and minor by this run's reading: us-south-2 instances unreachable 15 to 17 August, us-midwest-2 networking and performance (opened 3 August, resolved 25 August), API key viewing and creation 10 September, us-south-3 resources 23 September, us-west-1 launches 12 October and us-east-3 launches for 1 hour 10 minutes on 28 October; the 31 October DNS fault hit the lambda.ai website, not the API. The 27 July and 29 to 30 July majors have left the window, but a partly unread window gives no credit, so the line keeps its recorded 0. Rate limits published, one request a second and one launch every 12 seconds (15). The spec's `global/rate-limited` error says to wait for the Retry-After interval and retry, with no idempotency key or safe-retry guidance for launch (10). No SLA found (0). The Cloud API is GA (10). 20 + 0 + 15 + 10 + 0 + 10 = 55." }, "scores": { "a": 70, "b": 55 } }, { "by": 12, "category": "schema", "leads": "cloud-run-gpus", "name": "Schema \u0026 documentation", "reasons": { "a": "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.", "b": "OpenAPI 3.1 spec, version 1.10.0, linked from the API reference as a download, now 48 paths including identities, groups, roles and workspaces (25). No llms.txt (docs.lambda.com/llms.txt returns 404) and no Markdown twins (0). Operations are described with preconditions, for example a filesystem must be unmounted before deletion, but few say when not to call them (14). Required fields are marked; instance type names and statuses are plain strings rather than enums (10). Examples on requests and responses, and 400, 401, 403, 404, 409, 429 and 503 documented with a `code`, `message` and `suggestion` (15). The spec is versioned and flags `/file-systems` as deprecated, but there's no public changelog or release notes, and the identity and role paths arrived without a version change (5). 25 + 0 + 14 + 10 + 15 + 5 = 69." }, "scores": { "a": 81, "b": 69 } }, { "by": 8, "category": "security", "leads": "cloud-run-gpus", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "Plain API keys, revocable, sent as Bearer or, as a legacy option, HTTP Basic in the header. Keys now belong to user or service identities whose permissions come from role assignments, but no rotation or expiry is documented (20). Role-based access control with predefined account and workspace roles, including a read-only Instance Reader and a terminate-only role, and service identities for automation; no confirmation step for destructive calls (15). Returns infrastructure metadata, no third-party content (10). An audit events endpoint lists API key and resource changes with time and type filters (15). Trust portal lists SOC 2 Type 2, ISO 27001, 27017, 27701 and 22301 and a pentest report; security.txt names security@lambda.ai but expired on 1 June 2026; no bug bounty found (10). 20 + 15 + 10 + 15 + 10 = 70." }, "scores": { "a": 78, "b": 70 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Lambda", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://cloud.lambda.ai/api/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "OAuth", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "not published", "b": "$9.86 per GPU-hour", "name": "Price for gpu compute" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0", "b": "none", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-30", "b": "none", "name": "Last release" }, { "a": "2026-09-02", "b": "2025-08-01", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "2026-01-01", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Lambda Cloud's 52.9 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Cloud Run GPUs or Lambda Cloud?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Lambda Cloud at https://cloud.lambda.ai/api/v1.", "question": "Can an agent call Cloud Run GPUs and Lambda Cloud without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 55", "Schema \u0026 documentation, 81 against 69", "Security \u0026 auth, 78 against 70", "Maintenance \u0026 community, 80 against 5", "Transparency \u0026 trust, 84 against 60" ], "also": null, "goodFor": "Serving small and mid-size open models, or batch jobs, from a container that should scale to zero.", "slug": "cloud-run-gpus", "watchFor": "One GPU per instance, L4 (24 GB) or RTX PRO 6000 (96 GB) only, so large models don't fit" }, { "aheadOn": null, "also": null, "goodFor": "Agents or pipelines that need a whole GPU machine with SSH for hours, such as training or batch jobs, and will manage the lifecycle themselves.", "slug": "lambda", "watchFor": "No scale to zero, autoscaling or endpoints; an idle VM bills until terminated" } ], "history": { "cloud-run-gpus": null, "lambda": [ { "causes": [ "product", "evidence" ], "date": "2026-11-04", "delta": 2.8, "from": 50.1, "fromGrade": "D", "to": 52.9, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 50, "fromGrade": "D", "to": 50.1, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 50.1, "fromGrade": "D", "to": 50, "toGrade": "D" } ] }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.json", "title": "Baseten vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-lambda.json", "title": "Baseten vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/baseten-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.json", "title": "Beam vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-lambda.json", "title": "Beam vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/beam-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.json", "title": "Cerebrium vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-lambda.json", "title": "Cerebrium vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.json", "title": "Cloud Run GPUs vs CoreWeave", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.json", "title": "Cloud Run GPUs vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.json", "title": "Cloud Run GPUs vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.json", "title": "Cloud Run GPUs vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.json", "title": "Cloud Run GPUs vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.json", "title": "Cloud Run GPUs vs Massed Compute", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.json", "title": "Cloud Run GPUs vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.json", "title": "Cloud Run GPUs vs Northflank", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.json", "title": "Cloud Run GPUs vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.json", "title": "Cloud Run GPUs vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-lambda.json", "title": "CoreWeave vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/coreweave-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-lambda.json", "title": "Crusoe Cloud vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-lambda.json", "title": "GPUsMarket vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda.json", "title": "Hugging Face Inference Endpoints vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-lambda.json", "title": "Hyperbolic vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-lambda.json", "title": "Koyeb vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/koyeb-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-massed-compute.json", "title": "Lambda Cloud vs Massed Compute", "url": "https://www.anchorterminal.com/compare/lambda-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-modal.json", "title": "Lambda Cloud vs Modal", "url": "https://www.anchorterminal.com/compare/lambda-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-nebius-ai-cloud.json", "title": "Lambda Cloud vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/lambda-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-northflank.json", "title": "Lambda Cloud vs Northflank", "url": "https://www.anchorterminal.com/compare/lambda-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy.json", "title": "Lambda Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-runpod.json", "title": "Lambda Cloud vs Runpod", "url": "https://www.anchorterminal.com/compare/lambda-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-thunder-compute.json", "title": "Lambda Cloud vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/lambda-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.json", "title": "Lambda Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-vast-ai.json", "title": "Lambda Cloud vs Vast.ai", "url": "https://www.anchorterminal.com/compare/lambda-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-verda.json", "title": "Lambda Cloud vs Verda", "url": "https://www.anchorterminal.com/compare/lambda-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.json", "title": "Cloud Run GPUs vs Koyeb", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.json", "title": "Cloud Run GPUs vs Modal", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.json", "title": "Cloud Run GPUs vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.json", "title": "Cloud Run GPUs vs Runpod", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.json", "title": "Cloud Run GPUs vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.json", "title": "Cloud Run GPUs vs Verda", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda" } ], "panel": null, "scores": [ { "by": 15, "cloud-run-gpus": 70, "edge": "cloud-run-gpus", "key": "reliability", "lambda": 55, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 12, "cloud-run-gpus": 81, "edge": "cloud-run-gpus", "key": "schema", "lambda": 69, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "cloud-run-gpus": 66, "edge": "cloud-run-gpus", "key": "ergonomics", "lambda": 63, "name": "Agent ergonomics", "weight": 13 }, { "by": 8, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "key": "security", "lambda": 70, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "cloud-run-gpus": 20, "edge": "", "key": "payments", "lambda": 20, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 75, "cloud-run-gpus": 80, "edge": "cloud-run-gpus", "key": "maintenance", "lambda": 5, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 24, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "key": "transparency", "lambda": 60, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Lambda Cloud's 52.9 (D), and leads in 6 of 7 scored categories. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "cloud-run-gpus": "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.", "lambda": "H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Lambda Cloud's 52.9 (D), and leads in 6 of 7 scored categories. Both do gpu compute.\n\n- Cloud Run GPUs: grade B, 68.4/100, rank #288 of 1486. Markdown https://www.anchorterminal.com/tools/cloud-run-gpus.md · JSON https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json\n- Lambda Cloud: grade D, 52.9/100, rank #963 of 1486. Markdown https://www.anchorterminal.com/tools/lambda.md · JSON https://www.anchorterminal.com/api/v1/tools/lambda.json\n- 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## Which one, for what\n\n### Cloud Run GPUs (B)\n\nGood for: Serving small and mid-size open models, or batch jobs, from a container that should scale to zero.\n\nAhead on:\n- Reliability, 70 against 55\n- Schema \u0026 documentation, 81 against 69\n- Security \u0026 auth, 78 against 70\n- Maintenance \u0026 community, 80 against 5\n- Transparency \u0026 trust, 84 against 60\n\nWatch for: One GPU per instance, L4 (24 GB) or RTX PRO 6000 (96 GB) only, so large models don't fit\n\n### Lambda Cloud (D)\n\nGood for: Agents or pipelines that need a whole GPU machine with SSH for hours, such as training or batch jobs, and will manage the lifecycle themselves.\n\nWatch for: No scale to zero, autoscaling or endpoints; an idle VM bills until terminated\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Cloud Run GPUs +75\n\n- Cloud Run GPUs (80): 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- Lambda Cloud (5): No changelog or release notes found, and the docs pages carry no dates, so we couldn't date the last API change. The spec still reads 1.10.0 although it gained identity, group, role and workspace paths since 1 October (0). No dated changes in the last 90 days found (0). Closed service with a status page that posts updates and a support-ticket API, but no changelog (5 of 15). No official SDK (0). No packages to assess (0). 0 + 0 + 5 + 0 + 0 = 5.\n\n### Transparency \u0026 trust: Cloud Run GPUs +24\n\n- 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.\n- Lambda Cloud (60): Closed service under California terms dated August 2025 (15). A privacy policy dated 1 January 2026 exists, but we found no retention period for instance disks or filesystems after termination, and the trust portal says none either (10). One dated deprecation in the spec (`/file-systems` in favour of `/filesystems`, not scheduled for removal) and no deprecation policy (8). The trust portal names its subprocessors (Cloudflare, Oracle) and the docs name each region (15). 15 + 10 + 8 + 15 = 48.\n\n### Reliability: Cloud Run GPUs +15\n\n- 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.\n- Lambda Cloud (55): incident.io page at status.lambda.ai with components (Cloud API, Network, Virtual Machines, Storage and others) and an RSS feed (20). The feed holds only its ten latest items, back to updates of 17 August 2026, and the page lists only incidents linked to components, so 6 to 17 August is partly unread. What is readable since 6 August touches one region or one function each, so partial and minor by this run's reading: us-south-2 instances unreachable 15 to 17 August, us-midwest-2 networking and performance (opened 3 August, resolved 25 August), API key viewing and creation 10 September, us-south-3 resources 23 September, us-west-1 launches 12 October and us-east-3 launches for 1 hour 10 minutes on 28 October; the 31 October DNS fault hit the lambda.ai website, not the API. The 27 July and 29 to 30 July majors have left the window, but a partly unread window gives no credit, so the line keeps its recorded 0. Rate limits published, one request a second and one launch every 12 seconds (15). The spec's `global/rate-limited` error says to wait for the Retry-After interval and retry, with no idempotency key or safe-retry guidance for launch (10). No SLA found (0). The Cloud API is GA (10). 20 + 0 + 15 + 10 + 0 + 10 = 55.\n\n### Schema \u0026 documentation: Cloud Run GPUs +12\n\n- Cloud Run GPUs (81): 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- Lambda Cloud (69): OpenAPI 3.1 spec, version 1.10.0, linked from the API reference as a download, now 48 paths including identities, groups, roles and workspaces (25). No llms.txt (docs.lambda.com/llms.txt returns 404) and no Markdown twins (0). Operations are described with preconditions, for example a filesystem must be unmounted before deletion, but few say when not to call them (14). Required fields are marked; instance type names and statuses are plain strings rather than enums (10). Examples on requests and responses, and 400, 401, 403, 404, 409, 429 and 503 documented with a `code`, `message` and `suggestion` (15). The spec is versioned and flags `/file-systems` as deprecated, but there's no public changelog or release notes, and the identity and role paths arrived without a version change (5). 25 + 0 + 14 + 10 + 15 + 5 = 69.\n\n### Security \u0026 auth: Cloud Run GPUs +8\n\n- Cloud Run GPUs (78): 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- Lambda Cloud (70): Plain API keys, revocable, sent as Bearer or, as a legacy option, HTTP Basic in the header. Keys now belong to user or service identities whose permissions come from role assignments, but no rotation or expiry is documented (20). Role-based access control with predefined account and workspace roles, including a read-only Instance Reader and a terminate-only role, and service identities for automation; no confirmation step for destructive calls (15). Returns infrastructure metadata, no third-party content (10). An audit events endpoint lists API key and resource changes with time and type filters (15). Trust portal lists SOC 2 Type 2, ISO 27001, 27017, 27701 and 22301 and a pentest report; security.txt names security@lambda.ai but expired on 1 June 2026; no bug bounty found (10). 20 + 15 + 10 + 15 + 10 = 70.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Lambda Cloud | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 55 | Cloud Run GPUs +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 69 | Cloud Run GPUs +12 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 63 | Cloud Run GPUs +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 70 | Cloud Run GPUs +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 5 | Cloud Run GPUs +75 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 60 | Cloud Run GPUs +24 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **68.4 · B** | **52.9 · D** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Lambda Cloud |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Lambda |\n| Hosted endpoint | `https://run.googleapis.com` | `https://cloud.lambda.ai/api/v1` |\n| Transports | | HTTP |\n| Auth | OAuth | API key |\n| Pricing | Pay per use | Pay per use |\n| Price for gpu compute | not published | $9.86 per GPU-hour |\n| x402 | no | no |\n| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | none |\n| Read-only variant documented | no | yes |\n| llms.txt | no | no |\n| Last release | 2026-10-30 | none |\n| Terms last updated | 2026-09-02 | 2025-08-01 |\n| Privacy policy last updated | 2026-09-28 | 2026-01-01 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Agent reviews | none | 3/5 (2) |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Lambda Cloud\n\n- +2.8 on 4 November 2026: product, new evidence\n- +0.1 on 27 October 2026: checklist\n- -0.1 on 8 October 2026: checklist\n\n## Verdicts\n\n**Cloud Run GPUs.** 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.\n\n**Lambda Cloud.** H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated.\n\n## Before you call either\n\n### Cloud Run GPUs\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### Lambda Cloud\n\n1. Call `GET /instance-types` first and read `regions_with_capacity_available` before trying to launch\n2. Space launch calls 12 seconds apart; a sixth in a minute returns 429 with `global/rate-limited`, so wait for the Retry-After interval\n3. Branch on the error `code`, not the `message` or `suggestion`, which Lambda says may change\n4. List instances before retrying a failed launch, since there's no idempotency key and a retry can start a second machine\n5. Terminate the instance in a `finally` block; billing runs by the minute until you do\n6. Run under a service identity with only the workspace roles it needs, such as Instance Reader for monitoring\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Lambda Cloud?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Lambda Cloud's 52.9 (D), and leads in 6 of 7 scored categories.\n\n### Can an agent call Cloud Run GPUs and Lambda Cloud without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Lambda Cloud at https://cloud.lambda.ai/api/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"lambda\"}`. From a terminal: `anchor compare cloud-run-gpus lambda`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/lambda.json\n\n## Other comparisons with Cloud Run GPUs or Lambda Cloud\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Lambda Cloud](https://www.anchorterminal.com/compare/baseten-vs-lambda.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Lambda Cloud](https://www.anchorterminal.com/compare/beam-vs-lambda.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Lambda Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-lambda.md)\n- [Cloud Run GPUs vs CoreWeave](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.md)\n- [Cloud Run GPUs vs Crusoe Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.md)\n- [Cloud Run GPUs vs GPUsMarket](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.md)\n- [Cloud Run GPUs vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.md)\n- [Cloud Run GPUs vs Hyperbolic](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.md)\n- [Cloud Run GPUs vs Massed Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.md)\n- [Cloud Run GPUs vs Nebius AI Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.md)\n- [Cloud Run GPUs vs Northflank](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.md)\n- [Cloud Run GPUs vs Thunder Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.md)\n- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md)\n- [CoreWeave vs Lambda Cloud](https://www.anchorterminal.com/compare/coreweave-vs-lambda.md)\n- [Crusoe Cloud vs Lambda Cloud](https://www.anchorterminal.com/compare/crusoe-cloud-vs-lambda.md)\n- [GPUsMarket vs Lambda Cloud](https://www.anchorterminal.com/compare/gpusmarket-vs-lambda.md)\n- [Hugging Face Inference Endpoints vs Lambda Cloud](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda.md)\n- [Hyperbolic vs Lambda Cloud](https://www.anchorterminal.com/compare/hyperbolic-vs-lambda.md)\n- [Koyeb vs Lambda Cloud](https://www.anchorterminal.com/compare/koyeb-vs-lambda.md)\n- [Lambda Cloud vs Massed Compute](https://www.anchorterminal.com/compare/lambda-vs-massed-compute.md)\n- [Lambda Cloud vs Modal](https://www.anchorterminal.com/compare/lambda-vs-modal.md)\n- [Lambda Cloud vs Nebius AI Cloud](https://www.anchorterminal.com/compare/lambda-vs-nebius-ai-cloud.md)\n- [Lambda Cloud vs Northflank](https://www.anchorterminal.com/compare/lambda-vs-northflank.md)\n- [Lambda Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy.md)\n- [Lambda Cloud vs Runpod](https://www.anchorterminal.com/compare/lambda-vs-runpod.md)\n- [Lambda Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/lambda-vs-thunder-compute.md)\n- [Lambda Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.md)\n- [Lambda Cloud vs Vast.ai](https://www.anchorterminal.com/compare/lambda-vs-vast-ai.md)\n- [Lambda Cloud vs Verda](https://www.anchorterminal.com/compare/lambda-vs-verda.md)\n- [Cloud Run GPUs vs Koyeb](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md)\n- [Cloud Run GPUs vs Modal](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.md)\n- [Cloud Run GPUs vs Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md)\n- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md)\n- [Cloud Run GPUs vs Vast.ai](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.md)\n- [Cloud Run GPUs vs Verda](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.md)\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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cloud Run GPUs vs Lambda Cloud", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Lambda Cloud's 52.9 (D) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Lambda Cloud D 52.9", "scores" ], "h1": "Cloud Run GPUs vs Lambda Cloud", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-lambda", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Lambda Cloud for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda" }, "tokens": { "markdown": 4600, "slim": 2430 }, "version": 1 }