{ "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": "2026-11-07T18:20:17.664716666Z", "lastOk": true, "lastStatus": 404, "lastMs": 159, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 35, "p95ms24h": 120, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "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": "2026-11-07T18:20:17.664716666Z" } }, "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Replicate Deployments's 65.2 (B), and leads in 3 of 7 scored categories. Replicate Deployments leads on reliability, agent ergonomics and payments \u0026 pricing.", "b": { "slug": "replicate-deploy", "name": "Replicate Deployments", "vendor": "Replicate", "vendorUrl": "https://replicate.com", "kind": "http-api", "category": "gpu-compute", "summary": "Replicate's service for deploying and running custom models.", "url": "https://www.anchorterminal.com/tools/replicate-deploy", "markdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json", "dns": "replicate-deploy.grade.anchorterminal.com", "repo": "https://github.com/replicate/cog", "license": "Apache-2.0", "transports": [ "http", "sse", "stdio" ], "remoteUrl": "https://api.replicate.com/v1", "packages": [ { "registry": "npm", "name": "replicate" }, { "registry": "pypi", "name": "replicate" }, { "registry": "npm", "name": "replicate-mcp" } ], "auth": "api-key", "authNotes": "Bearer API token on every call to api.replicate.com. `cog push` uses the same token to upload a model image. The hosted MCP at https://mcp.replicate.com/sse asks for the token in a browser flow and holds it for the client; the local `replicate-mcp` package reads `REPLICATE_API_TOKEN`.", "pricing": "usage", "pricingNotes": "Private models and deployments bill per second for the whole time an instance is up, set-up and idle included, from prepaid credit or monthly in arrears. CPU (Small) $0.000025 a second ($0.09 an hour), CPU $0.000100 ($0.36), T4 $0.000225 ($0.81), L40S $0.000975 ($3.51), A100 80 GB $0.001400 ($5.04), H100 $0.001525 ($5.49), 2x L40S $0.001950 ($7.02), 2x A100 $0.002800 ($10.08). 2x H100 ($10.98), H200 ($5.49) and 2x to 8x H200, and 4x and 8x L40S, A100 and H100 up to $43.92 an hour need a committed-spend contract. Fast-booting fine-tunes bill only while active. Public models bill only active time and not failures (https://replicate.com/pricing, https://replicate.com/docs/topics/billing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 9500, "npmWeekly": 634116, "pypiWeekly": 386704, "asOf": "2026-09-30" }, "docsUrl": "https://replicate.com/docs/topics/deployments", "llmsTxt": "https://replicate.com/docs/llms.txt", "openapi": "https://api.replicate.com/openapi.json", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.serverless", "compute.containers" ], "tags": [ "hosted", "usage-priced", "mcp", "llms-txt", "openapi", "python", "typescript", "async-jobs", "webhooks", "open-source" ], "lastRelease": "2026-10-19", "graded": true, "anchor": { "graded": true, "score": 65.2, "grade": "B", "agentReady": false, "rank": 430, "ranked": true, "rankOf": 1486, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 78, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": 0, "verdict": "OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026.", "bestFor": "Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.", "strengths": [ "OpenAPI file, llms.txt and an MCP server with a two-tool code mode", "Deployment min and max instances settable over the API, 0 allowed", "API prediction data deleted after one hour by default", "Published limits, 600 prediction creates and 3,000 other calls a minute", "Cog released 0.22.0, 0.23.0 and 0.23.1 between 13 August and 19 October 2026" ], "weaknesses": [ "Private instances bill set-up and idle time, H100 at $5.49 an hour", "API tokens have no scopes, expiry or audit log", "Changelog silent since 21 April 2026, and no stable Python client release since May 2025", "More than 2 GPUs, and any H200, needs a committed-spend contract", "Two September 2026 incidents ran 15 and 20 hours, both partial" ], "agentNotes": [ "List `GET /v1/hardware` first and use the returned `sku` in the deployment body", "Set `min_instances` to 0 for bursty work; a warm H100 bills $5.49 an hour whether called or not", "Send `Prefer: wait` on deployment predictions to block instead of polling", "Copy outputs within an hour; API prediction data is deleted after that", "Wait for the reset time in the 429 body before retrying; prediction creates cap at 600 a minute" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.2 } ], "editorialScores": { "ergonomics": 73, "maintenance": 78, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 69 }, "provenanceScore": 89, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install cog replicate", "http": "curl -X POST \"https://api.replicate.com/v1/deployments/$REPLICATE_OWNER/my-deployment/predictions\" \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" -H \"Content-Type: application/json\" -H \"Prefer: wait\" \\\n -d '{\"input\":{\"prompt\":\"hello\"}}'", "claudeCode": "claude mcp add replicate https://mcp.replicate.com/sse --transport sse --scope user", "config": { "mcpServers": { "replicate": { "args": [ "-y", "replicate-mcp" ], "command": "npx", "env": { "REPLICATE_API_TOKEN": "${REPLICATE_API_TOKEN}" } } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/replicate-deploy" }, "sameCompany": [ "replicate-image", "replicate-video", "replicate-musicgen" ], "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 5.49, "note": "$0.001525 a second, including set-up and idle" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 5.04, "note": "$0.001400 a second" }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 3.51, "note": "$0.000975 a second" }, { "item": "T4 16 GB", "unit": "gpu-hour", "usd": 0.81, "note": "$0.000225 a second" } ], "provenance": { "legalEntity": "Replicate, LLC", "domain": "replicate.com", "domainRegistered": "1998-05-26", "domainNote": "replicate.com was registered in 1998, long before Replicate the company existed.", "endpointOnVendorDomain": true, "terms": "https://replicate.com/terms", "privacy": "https://replicate.com/privacy", "statusPage": "https://replicatestatus.com", "changelog": "https://replicate.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms last updated 2026-04-01 name Replicate, LLC as the contracting party.", "replicatestatus.com redirects to Cloudflare's status page filtered to Replicate.", "Replicate's hosted image and music models are listed separately under image generation and music generation." ], "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/replicate-deploy.json", "live": { "slug": "replicate-deploy", "probe": { "target": "https://api.replicate.com/v1", "method": "get", "lastAt": "2026-11-07T18:20:50.760402766Z", "lastOk": true, "lastStatus": 401, "lastMs": 346, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 131, "p95ms24h": 271, "samples24h": 239, "samples30d": 7910, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "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": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "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": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://replicatestatus.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:40.399907591Z" }, "versions": [ { "registry": "github", "name": "replicate/cog", "version": "v0.23.1", "released": "2026-10-20", "seenAt": "2026-11-07T00:01:09.866719484Z" }, { "registry": "npm", "name": "replicate", "version": "1.4.0", "seenAt": "2026-11-07T00:01:07.5708322Z" }, { "registry": "npm", "name": "replicate-mcp", "version": "0.9.0", "seenAt": "2026-11-07T00:01:08.011276677Z" }, { "registry": "pypi", "name": "replicate", "version": "1.0.7", "released": "2025-05-27", "seenAt": "2026-11-07T00:01:07.782674478Z" } ], "githubStars": 9494, "npmWeekly": 805275, "pypiWeekly": 396497, "securityTxt": { "url": "https://replicate.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:02.105557027Z" }, "llmsTxt": { "url": "https://replicate.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:45.131385958Z" }, "domain": { "domain": "replicate.com", "registered": "1998-05-26", "source": "https://rdap.verisign.com/com/v1/domain/replicate.com", "checkedAt": "2026-11-01T14:20:16.006565471Z" }, "pages": [ { "url": "https://replicate.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:18:19.719079825Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "490f4836aca3" }, { "url": "https://replicate.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:18:22.053284085Z", "changedAt": "2026-11-04T08:31:26.382456818Z", "fingerprint": "246042e35580" }, { "url": "https://replicate.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:18:24.363010933Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8e299fbc64eb" }, { "url": "https://replicate.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:18:25.932917726Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ea48efe3382b" } ], "github": { "repo": "replicate/cog", "checkedAt": "2026-11-02T09:21:13.080161119Z", "stars": 9494, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-31T23:09:21Z", "openIssues": 30, "openPRs": 70, "issuesOpened90d": 5, "issuesClosed90d": 10, "prsMerged90d": 25, "ci": { "branch": "main", "runs": 50, "success": 49, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-27T20:48:06Z" }, "replies": { "sampled": 25, "unanswered": 2, "medianDays": 1.3 } }, "updatedAt": "2026-11-07T18:20:50.760402766Z" } }, "edges": [ { "by": 38, "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": "Bearer tokens starting `r8_`, several per account, each can be disabled; no scopes or expiry, re-read on 2 November (20). No read-only or per-model token; every token can create, update and delete deployments (0). Returns your own model's output (10). No audit log or per-token usage view found; predictions are listed per account (5). Replicate scans public GitHub for leaked tokens, disables them and emails the owner. replicate.com/.well-known/security.txt answers 404, and no bug bounty or certification was found in the docs we read. OSV lists no advisory for the `replicate` packages, `replicate-mcp` or Cog (5). 20 + 0 + 10 + 5 + 5 = 40." }, "scores": { "a": 78, "b": 40 } }, { "by": 10, "category": "payments", "leads": "replicate-deploy", "name": "Payments \u0026 pricing", "reasons": { "a": "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.", "b": "No machine payment protocol (0). Per-second prices for each hardware SKU published without a login, re-read on 2 November, now with a small CPU tier at $0.09 an hour and H200 SKUs on committed-spend contracts (20). Accounts without a card can run predictions at up to 6 a minute; private deployments still bill set-up and idle time (10 of 20). Signup is a browser flow (0). 0 + 20 + 10 + 0 = 30." }, "scores": { "a": 20, "b": 30 } }, { "by": 7, "category": "ergonomics", "leads": "replicate-deploy", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "The MCP server exposes one tool per HTTP operation and has an experimental code mode that collapses them into two tools (search the SDK docs, run TypeScript) (20). List responses page with `next` and `previous` cursor URLs, the predictions list filters by `created_after`, `created_before` and `source`, and the models list sorts, but there is no page size or field selection (15 of 20; was 10, pagination not verified on 1 October). Coded errors with suggested fixes, `detail` messages on HTTP errors (15). No idempotency keys; `Prefer: wait`, a `Cancel-After` header, webhooks and cancel cut polling, and a failed run still bills its active time (8). Sensible defaults (`min_instances` 0 allowed) and official Python and JavaScript clients plus Cog (15). 20 + 15 + 15 + 8 + 15 = 73." }, "scores": { "a": 66, "b": 73 } }, { "by": 5, "category": "reliability", "leads": "replicate-deploy", "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": "Replicate incidents post under a Replicate component on cloudflarestatus.com, and replicatestatus.com redirects to that page filtered to Replicate (20). The component's 90-day bars, read on 2 November, show 5 days with incidents, all in September 2026, and none since 28 September. Some third-party models couldn't scale out for 15 hours 41 minutes on 14 and 15 September, a Pruna-specific issue ran 20 hours on 17 September, backend services returned intermittent 500s for 1 hour 54 minutes on 24 September, and hot-swapped Flux models stuck for 17 minutes on 28 September. Each names a subset of models or intermittent errors, so each reads as partial, minor only (20). 600 prediction creates a minute, 3,000 a minute on other endpoints, and 6 a minute without a card, re-read on 2 November (15). A 429 body says when the limit resets ('resets in ~30s') and the error-code page gives retry advice per code, but there's no Retry-After header or idempotency guidance (10 of 15). No SLA found (0). Deployments are GA (10). 20 + 20 + 15 + 10 + 0 + 10 = 75." }, "scores": { "a": 70, "b": 75 } }, { "by": 5, "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; Cog is Apache-2.0 (20). API prediction inputs, outputs, files and logs are deleted after one hour by default, web predictions are kept until deleted, and a subprocessor page is published, per the 1 October check, not re-read on 2 November (22). Dated deprecations in the changelog (streaming default in July 2024, spend limits in July 2025) but no written policy (12). Subprocessors listed; data locations not stated in what we read (15). 20 + 22 + 12 + 15 = 69." }, "scores": { "a": 84, "b": 79 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Replicate", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://api.replicate.com/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, SSE (legacy), stdio", "name": "Transports" }, { "a": "OAuth", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-19", "name": "Last release" }, { "a": "2026-09-02", "b": "2026-04-01", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "2026-04-01", "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": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "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": "9.5k stars, 634k npm/wk, 387k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Replicate Deployments's 65.2 (B), and leads in 3 of 7 scored categories. Replicate Deployments leads on reliability, agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, Cloud Run GPUs or Replicate Deployments?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Replicate Deployments at https://api.replicate.com/v1.", "question": "Can an agent call Cloud Run GPUs and Replicate Deployments without installing anything?" }, { "answer": "No open-source release is listed for Cloud Run GPUs. Replicate Deployments is open source (Apache-2.0).", "question": "Are Cloud Run GPUs and Replicate Deployments open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 78 against 40", "Transparency \u0026 trust, 84 against 79" ], "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": [ "Reliability, 75 against 70", "Agent ergonomics, 73 against 66", "Payments \u0026 pricing, 30 against 20" ], "also": [ "Runs on your own machine", "Open source" ], "goodFor": "Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.", "slug": "replicate-deploy", "watchFor": "Private instances bill set-up and idle time, H100 at $5.49 an hour" } ], "history": { "cloud-run-gpus": null, "replicate-deploy": [ { "causes": [ "product", "evidence" ], "date": "2026-11-02", "delta": 1.5, "from": 63.7, "fromGrade": "B", "to": 65.2, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 63.6, "fromGrade": "B", "to": 63.7, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 63.7, "fromGrade": "B", "to": 63.6, "toGrade": "B" } ] }, "job": { "capability": "compute.serverless", "name": "Compute serverless" }, "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-replicate-deploy.json", "title": "Baseten vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Beam vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/beam-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Cerebrium vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy" }, { "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-lambda.json", "title": "Cloud Run GPUs vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda" }, { "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-replicate-deploy.json", "title": "CoreWeave vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.json", "title": "Crusoe Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.json", "title": "GPUsMarket vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.json", "title": "Hugging Face Inference Endpoints vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.json", "title": "Hyperbolic vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy.json", "title": "Koyeb vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy" }, { "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/massed-compute-vs-replicate-deploy.json", "title": "Massed Compute vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-replicate-deploy.json", "title": "Modal vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/modal-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy.json", "title": "Nebius AI Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy.json", "title": "Northflank vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod.json", "title": "Replicate Deployments vs Runpod", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute.json", "title": "Replicate Deployments vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.json", "title": "Replicate Deployments vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.json", "title": "Replicate Deployments vs Vast.ai", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-verda.json", "title": "Replicate Deployments vs Verda", "url": "https://www.anchorterminal.com/compare/replicate-deploy-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-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": 5, "cloud-run-gpus": 70, "edge": "replicate-deploy", "key": "reliability", "name": "Reliability", "replicate-deploy": 75, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "cloud-run-gpus": 81, "edge": "replicate-deploy", "key": "schema", "name": "Schema \u0026 documentation", "replicate-deploy": 85, "weight": 13 }, { "by": 7, "cloud-run-gpus": 66, "edge": "replicate-deploy", "key": "ergonomics", "name": "Agent ergonomics", "replicate-deploy": 73, "weight": 13 }, { "by": 38, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "key": "security", "name": "Security \u0026 auth", "replicate-deploy": 40, "weight": 14 }, { "by": 10, "cloud-run-gpus": 20, "edge": "replicate-deploy", "key": "payments", "name": "Payments \u0026 pricing", "replicate-deploy": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "cloud-run-gpus": 80, "edge": "cloud-run-gpus", "key": "maintenance", "name": "Maintenance \u0026 community", "replicate-deploy": 78, "weight": 7 }, { "by": 5, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "key": "transparency", "name": "Transparency \u0026 trust", "replicate-deploy": 79, "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Replicate Deployments's 65.2 (B), and leads in 3 of 7 scored categories. Replicate Deployments leads on reliability, agent ergonomics and payments \u0026 pricing. Both do compute serverless.", "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.", "replicate-deploy": "OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Replicate Deployments's 65.2 (B), and leads in 3 of 7 scored categories. Replicate Deployments leads on reliability, agent ergonomics and payments \u0026 pricing. Both do compute serverless.\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- Replicate Deployments: grade B, 65.2/100, rank #430 of 1486. Markdown https://www.anchorterminal.com/tools/replicate-deploy.md · JSON https://www.anchorterminal.com/api/v1/tools/replicate-deploy.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- Security \u0026 auth, 78 against 40\n- Transparency \u0026 trust, 84 against 79\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### Replicate Deployments (B)\n\nGood for: Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.\n\nAhead on:\n- Reliability, 75 against 70\n- Agent ergonomics, 73 against 66\n- Payments \u0026 pricing, 30 against 20\n\nAlso in its favour:\n- Runs on your own machine\n- Open source\n\nWatch for: Private instances bill set-up and idle time, H100 at $5.49 an hour\n\n\n## Why the edge\n\n### Security \u0026 auth: Cloud Run GPUs +38\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- Replicate Deployments (40): Bearer tokens starting `r8_`, several per account, each can be disabled; no scopes or expiry, re-read on 2 November (20). No read-only or per-model token; every token can create, update and delete deployments (0). Returns your own model's output (10). No audit log or per-token usage view found; predictions are listed per account (5). Replicate scans public GitHub for leaked tokens, disables them and emails the owner. replicate.com/.well-known/security.txt answers 404, and no bug bounty or certification was found in the docs we read. OSV lists no advisory for the `replicate` packages, `replicate-mcp` or Cog (5). 20 + 0 + 10 + 5 + 5 = 40.\n\n### Payments \u0026 pricing: Replicate Deployments +10\n\n- Cloud Run GPUs (20): 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- Replicate Deployments (30): No machine payment protocol (0). Per-second prices for each hardware SKU published without a login, re-read on 2 November, now with a small CPU tier at $0.09 an hour and H200 SKUs on committed-spend contracts (20). Accounts without a card can run predictions at up to 6 a minute; private deployments still bill set-up and idle time (10 of 20). Signup is a browser flow (0). 0 + 20 + 10 + 0 = 30.\n\n### Agent ergonomics: Replicate Deployments +7\n\n- Cloud Run GPUs (66): Platform reading. One `gcloud run deploy` with `--gpu` and `--gpu-type` adds a GPU to a container, and responses carry the service object with `fieldMask` on updates (15). List calls page with `pageSize` and `pageToken` (15). Google's status codes and messages, with quota errors that name the limit (12). Revisions are immutable, traffic can be moved back, and etags guard updates, but no idempotency key on create (12). Client libraries in many languages and gcloud, though a GPU deploy needs instance-based billing, minimum CPU and memory and, past 3 GPUs, a quota request (12). 15+15+12+12+12 = 66.\n- Replicate Deployments (73): The MCP server exposes one tool per HTTP operation and has an experimental code mode that collapses them into two tools (search the SDK docs, run TypeScript) (20). List responses page with `next` and `previous` cursor URLs, the predictions list filters by `created_after`, `created_before` and `source`, and the models list sorts, but there is no page size or field selection (15 of 20; was 10, pagination not verified on 1 October). Coded errors with suggested fixes, `detail` messages on HTTP errors (15). No idempotency keys; `Prefer: wait`, a `Cancel-After` header, webhooks and cancel cut polling, and a failed run still bills its active time (8). Sensible defaults (`min_instances` 0 allowed) and official Python and JavaScript clients plus Cog (15). 20 + 15 + 15 + 8 + 15 = 73.\n\n### Reliability: Replicate Deployments +5\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- Replicate Deployments (75): Replicate incidents post under a Replicate component on cloudflarestatus.com, and replicatestatus.com redirects to that page filtered to Replicate (20). The component's 90-day bars, read on 2 November, show 5 days with incidents, all in September 2026, and none since 28 September. Some third-party models couldn't scale out for 15 hours 41 minutes on 14 and 15 September, a Pruna-specific issue ran 20 hours on 17 September, backend services returned intermittent 500s for 1 hour 54 minutes on 24 September, and hot-swapped Flux models stuck for 17 minutes on 28 September. Each names a subset of models or intermittent errors, so each reads as partial, minor only (20). 600 prediction creates a minute, 3,000 a minute on other endpoints, and 6 a minute without a card, re-read on 2 November (15). A 429 body says when the limit resets ('resets in ~30s') and the error-code page gives retry advice per code, but there's no Retry-After header or idempotency guidance (10 of 15). No SLA found (0). Deployments are GA (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.\n\n### Transparency \u0026 trust: Cloud Run GPUs +5\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- Replicate Deployments (79): Closed service; Cog is Apache-2.0 (20). API prediction inputs, outputs, files and logs are deleted after one hour by default, web predictions are kept until deleted, and a subprocessor page is published, per the 1 October check, not re-read on 2 November (22). Dated deprecations in the changelog (streaming default in July 2024, spend limits in July 2025) but no written policy (12). Subprocessors listed; data locations not stated in what we read (15). 20 + 22 + 12 + 15 = 69.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Replicate Deployments | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 75 | Replicate Deployments +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 85 | Replicate Deployments +4 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 73 | Replicate Deployments +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 40 | Cloud Run GPUs +38 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 30 | Replicate Deployments +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 78 | Cloud Run GPUs +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 79 | Cloud Run GPUs +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **68.4 · B** | **65.2 · B** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Replicate Deployments |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Replicate |\n| Hosted endpoint | `https://run.googleapis.com` | `https://api.replicate.com/v1` |\n| Transports | | HTTP, SSE (legacy), stdio |\n| Auth | OAuth | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-30 | 2026-10-19 |\n| Terms last updated | 2026-09-02 | 2026-04-01 |\n| Privacy policy last updated | 2026-09-28 | 2026-04-01 |\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 | not found in the text |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | none | 9.5k stars, 634k npm/wk, 387k PyPI/wk |\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### Replicate Deployments\n\n- +1.5 on 2 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**Replicate Deployments.** OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026.\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### Replicate Deployments\n\n1. List `GET /v1/hardware` first and use the returned `sku` in the deployment body\n2. Set `min_instances` to 0 for bursty work; a warm H100 bills $5.49 an hour whether called or not\n3. Send `Prefer: wait` on deployment predictions to block instead of polling\n4. Copy outputs within an hour; API prediction data is deleted after that\n5. Wait for the reset time in the 429 body before retrying; prediction creates cap at 600 a minute\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Replicate Deployments?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Replicate Deployments's 65.2 (B), and leads in 3 of 7 scored categories. Replicate Deployments leads on reliability, agent ergonomics and payments \u0026 pricing.\n\n### Can an agent call Cloud Run GPUs and Replicate Deployments without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Replicate Deployments at https://api.replicate.com/v1.\n\n### Are Cloud Run GPUs and Replicate Deployments open source?\n\nNo open-source release is listed for Cloud Run GPUs. Replicate Deployments is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"replicate-deploy\"}`. From a terminal: `anchor compare cloud-run-gpus replicate-deploy`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json\n\n## Other comparisons with Cloud Run GPUs or Replicate Deployments\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Replicate Deployments](https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Replicate Deployments](https://www.anchorterminal.com/compare/beam-vs-replicate-deploy.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Replicate Deployments](https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy.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 Lambda Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.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 Replicate Deployments](https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.md)\n- [Crusoe Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.md)\n- [GPUsMarket vs Replicate Deployments](https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.md)\n- [Hugging Face Inference Endpoints vs Replicate Deployments](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.md)\n- [Hyperbolic vs Replicate Deployments](https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.md)\n- [Koyeb vs Replicate Deployments](https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy.md)\n- [Lambda Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy.md)\n- [Massed Compute vs Replicate Deployments](https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy.md)\n- [Modal vs Replicate Deployments](https://www.anchorterminal.com/compare/modal-vs-replicate-deploy.md)\n- [Nebius AI Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy.md)\n- [Northflank vs Replicate Deployments](https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy.md)\n- [Replicate Deployments vs Runpod](https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod.md)\n- [Replicate Deployments vs Thunder Compute](https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute.md)\n- [Replicate Deployments vs Together GPU Clusters](https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.md)\n- [Replicate Deployments vs Vast.ai](https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.md)\n- [Replicate Deployments vs Verda](https://www.anchorterminal.com/compare/replicate-deploy-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 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 Replicate Deployments", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Replicate Deployments's 65.2 (B) for compute serverless. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Replicate Deployments B 65.2", "scores" ], "h1": "Cloud Run GPUs vs Replicate Deployments", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-replicate-deploy", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Replicate Deployments for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy" }, "tokens": { "markdown": 4650, "slim": 2330 }, "version": 1 }