{ "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 Koyeb's 46.6 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "koyeb", "name": "Koyeb", "vendor": "Koyeb", "vendorUrl": "https://www.koyeb.com", "kind": "platform", "category": "gpu-compute", "summary": "Serverless platform for deploying applications and containers on CPU or GPU instances, with autoscaling and an API.", "url": "https://www.anchorterminal.com/tools/koyeb", "markdownUrl": "https://www.anchorterminal.com/tools/koyeb.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/koyeb.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/koyeb.json", "dns": "koyeb.grade.anchorterminal.com", "repo": "https://github.com/koyeb/koyeb-cli", "license": "Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://app.koyeb.com/v1", "packages": [], "auth": "pat", "authNotes": "Personal access token created in the control panel (app.koyeb.com/user/settings/api) and sent as `Authorization: Bearer` to app.koyeb.com/v1. The CLI stores it from `koyeb login` and hides it in debug output. Organisation-scoped tokens can be created for teams.", "pricing": "freemium", "pricingNotes": "Pro is $29 a month with $10 of usage included, Scale $299 with $100, Enterprise custom from $1,000 a month. The Starter plan closed to new sign-ups after the Mistral AI agreement and no longer appears on the pricing page. Everything bills per second. GPUs an hour are RTX 4000 SFF Ada $0.50, L4 $0.70, RTX A6000 $0.75, L40S $1.20, A100 $1.60, A100 SXM $2.15, RTX PRO 6000 $2.20, H100 $2.50, H200 $3.00, 2x A100 $3.20, 2x H100 $5.00, B200 $5.50, 4x A100 $6.40, 8x H100 $20.00, 8x H200 $24.00. CPU services start at $0.000006 a second (https://www.koyeb.com/pricing, https://www.koyeb.com/blog/koyeb-is-joining-mistral-ai-to-build-the-future-of-ai-infrastructure).", "priceSummary": "$29 / mo", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 72, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://www.koyeb.com/docs", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.containers" ], "tags": [ "hosted", "freemium", "eu", "enterprise" ], "lastRelease": "2026-10-20", "graded": true, "anchor": { "graded": true, "score": 46.6, "grade": "D", "agentReady": false, "rank": 1155, "ranked": true, "rankOf": 1486, "categoryRank": 19, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 51, "maintenance": 73, "payments": 20, "reliability": 50, "schema": 31, "security": 50, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-05" }, "negative": 0, "verdict": "Koyeb publishes per-second GPU prices without a login, from $0.50 an hour for an RTX 4000 SFF Ada to $2.50 for an H100, with an SLA document from the Scale plan. It has no downloadable OpenAPI file, documented rate limits or error codes, and no free compute plan, and its public changelog has been silent since 27 February 2026.", "bestFor": "Teams that want low-cost H100, H200 or B200 containers with scale to zero and an SLA, deployed from Git or an image.", "strengths": [ "H100 at $2.50, H200 at $3.00 and B200 at $5.50 an hour, billed per second", "Scale to zero after 5 idle minutes by default, configurable up to 12 hours on higher plans", "SLA document with service credits; Scale lists 99.9 per cent uptime and Enterprise 99.99", "Five tagged CLI and Python SDK releases between 27 August and 20 October 2026", "List endpoints filter by name, type, status and region with `limit` and `offset`, and create and update take `dry_run`" ], "weaknesses": [ "Public changelog silent since 27 February 2026, so API changes surface only through CLI and SDK releases", "No free compute plan; Pro at $29 a month is the entry point", "No llms.txt, no downloadable OpenAPI file, no documented rate limits or error codes", "Audit logs and RBAC only on Enterprise, and tokens have no scopes", "Platform due to fold into Mistral Compute with no dated migration plan" ], "agentNotes": [ "Pass `dry_run` on service create or update to validate the definition before anything deploys", "Page service lists with `limit` and `offset` and filter by `statuses` instead of fetching everything", "Expect the first request after deep sleep to take 1 to 5 seconds and retry once with a timeout", "Set `--min-scale 0` on GPU services so idle instances stop billing", "Read the CLI's CHANGES.md and the Python SDK tags for API changes, since the web changelog stopped in February 2026" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 46.6 } ], "editorialScores": { "ergonomics": 51, "maintenance": 73, "payments": 20, "reliability": 50, "schema": 31, "security": 50, "transparency": 50 }, "provenanceScore": 78, "checked": { "categories": { "ergonomics": "2026-11-05", "maintenance": "2026-11-05", "payments": "2026-11-05", "reliability": "2026-11-05", "schema": "2026-11-05", "security": "2026-11-05", "transparency": "2026-11-05" }, "last": "2026-11-05", "lastMoved": "2026-11-05", "oldest": "2026-11-05", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "brew install koyeb/tap/koyeb \u0026\u0026 koyeb login # or go install github.com/koyeb/koyeb-cli/cmd/koyeb", "http": "curl \"https://app.koyeb.com/v1/services\" -H \"Authorization: Bearer $KOYEB_TOKEN\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/koyeb" }, "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 2.5 }, { "item": "H200 141 GB", "unit": "gpu-hour", "usd": 3 }, { "item": "B200", "unit": "gpu-hour", "usd": 5.5 }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 1.6 }, { "item": "RTX PRO 6000", "unit": "gpu-hour", "usd": 2.2 }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 1.2 }, { "item": "L4 24 GB", "unit": "gpu-hour", "usd": 0.7 }, { "item": "Pro plan", "unit": "month", "usd": 29, "note": "$10 of usage included" }, { "item": "Scale plan", "unit": "month", "usd": 299, "note": "$100 of usage included" } ], "provenance": { "legalEntity": "Koyeb SAS", "domain": "koyeb.com", "domainRegistered": "2019-03-11", "endpointOnVendorDomain": true, "terms": "https://www.koyeb.com/docs/legal/terms", "privacy": "https://www.koyeb.com/docs/legal/data-processing-agreement", "statusPage": "https://status.koyeb.com", "changelog": "https://www.koyeb.com/changelog", "securityTxt": "none", "checked": "2026-11-05", "notes": [ "The Master Services Agreement of 28 June 2024 names Koyeb, a simplified joint-stock company registered in Nanterre under 850 183 948, at 9 rue des Longs Prés, Boulogne-Billancourt, under French law. Its Bots clause covers workloads run on the platform, not reading the website.", "The site footer's privacy link points at the data processing agreement rather than a separate privacy policy.", "www.koyeb.com/.well-known/security.txt returns 404 and there's no llms.txt at www.koyeb.com or under /docs (5 November 2026).", "Koyeb announced on 17 February 2026 that it is joining Mistral AI." ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/koyeb.json", "live": { "slug": "koyeb", "probe": { "target": "https://app.koyeb.com/v1", "method": "get", "lastAt": "2026-11-07T18:20:34.082438382Z", "lastOk": true, "lastStatus": 200, "lastMs": 135, "authRequired": false, "uptime24h": 100, "uptime30d": 99.99, "p50ms24h": 66, "p95ms24h": 159, "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": 251 }, { "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": 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://status.koyeb.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:58.832052518Z" }, "versions": [ { "registry": "github", "name": "koyeb/koyeb-cli", "version": "v5.12.0", "released": "2026-09-16", "seenAt": "2026-11-06T23:37:43.85754248Z" } ], "githubStars": 77, "securityTxt": { "url": "https://koyeb.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:16.209310212Z" }, "domain": { "domain": "koyeb.com", "registered": "2019-03-11", "source": "https://rdap.verisign.com/com/v1/domain/koyeb.com", "checkedAt": "2026-11-01T14:17:08.497490753Z" }, "pages": [ { "url": "https://www.koyeb.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:30:36.311116627Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7e4e89b36b63" }, { "url": "https://www.koyeb.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-11-07T14:30:42.420198952Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9d7cf517fa78" }, { "url": "https://www.koyeb.com/docs/legal/data-processing-agreement", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:30:38.426689944Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6e08cc6e8919" }, { "url": "https://www.koyeb.com/docs/legal/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:30:40.460441331Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "089f524cdbd6" } ], "github": { "repo": "koyeb/koyeb-cli", "checkedAt": "2026-11-02T08:59:14.60153217Z", "stars": 75, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-29T16:05:59Z", "openIssues": 23, "openPRs": 9, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 26, "ci": { "branch": "master", "runs": 45, "success": 44, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-14T07:00:43Z" }, "replies": { "sampled": 25, "unanswered": 9, "medianDays": 0.2 } }, "updatedAt": "2026-11-07T18:20:34.082438382Z" } }, "edges": [ { "by": 50, "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": "No downloadable OpenAPI file. The API reference at koyeb.com/docs/reference/api renders only by script, and the generated docs in the Go and Python client repositories aren't a published contract (0, was 10). No llms.txt (www.koyeb.com/llms.txt and /docs/llms.txt both 404) and no Markdown twins (0). Guides on scale to zero and autoscaling say when to use each setting (10, held). Typed parameters with required bodies in the Go client's docs, but service types and statuses are free strings with no listed values (8, held). CLI examples throughout; no documented error responses found (5, held). /v1 paths, but the public changelog stopped on 27 February 2026 (8, held). 0 + 0 + 10 + 8 + 5 + 8 = 31." }, "scores": { "a": 81, "b": 31 } }, { "by": 28, "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": "Personal access tokens and organisation tokens sent as Bearer; no scopes found (20). RBAC only on Enterprise; no read-only token (5). Runs your own containers and returns their output (10). Audit logs only on Enterprise (10). ISO 27001 and SOC 2 listed on the pricing page for Enterprise; www.koyeb.com/.well-known/security.txt is 404 and no disclosure policy, SECURITY.md or bug bounty found, so a bare certification claim (5). 20 + 5 + 10 + 10 + 5 = 50." }, "scores": { "a": 78, "b": 50 } }, { "by": 20, "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": "Graded on the hosted lines for its platform API. Instatus page at status.koyeb.com with components (API, Control Panel, Build / Provisioning and one per region) and history back to 2022 in its feed (20). Since 7 August the feed holds nine incidents and one maintenance. The eight in September each name one region, one GPU type or some customers, or ran 6 to 52 minutes (8, 11, 15, 21, 22 and 23 September and two on 29 September). On 16 October Koyeb posted a separate incident, \"The ongoing maintenance is causing API to fail with 500\", on the API, Control Panel and Build components for 24 minutes, inside a maintenance window announced the day before for 07:00 to 08:00 UTC with \"max 10m unavailability\". The status page labels it an incident and the outage ran past the unavailability announced, so it counts as an incident, and the API failing with 500 is errors across the board, one major outage (10). No API rate limits found in the docs we could read (0). No 429 or backoff guidance found (0). The Scale plan lists a 99.9 per cent uptime SLA and Enterprise 99.99, with an SLA document at /docs/legal/sla setting service credits (10). Services and GPUs are generally available; light sleep is a preview (10). 20 + 10 + 0 + 0 + 10 + 10 = 50." }, "scores": { "a": 70, "b": 50 } }, { "by": 20, "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": "The editorial half. Closed service under the French-law Master Services Agreement of 28 June 2024; the CLI and Go client are Apache-2.0 (20). An MSA and a DPA are published, the MSA deletes customer data at the end of the reversibility period, but the footer's privacy link points at the DPA and we found no separate privacy policy or retention periods (15). The Mistral agreement was announced on 17 February 2026, with Starter closed to new sign-ups, and no dated migration or end-of-life notice since (5, held). Regions are named on the status page (North America, Europe, Asia-Pacific); subprocessors not checked (10). 20 + 15 + 5 + 10 = 50." }, "scores": { "a": 84, "b": 64 } }, { "by": 15, "category": "ergonomics", "leads": "cloud-run-gpus", "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": "List endpoints take `limit` and `offset` plus filters on name, type, status, region and ID, per the Go client's docs (15). The same filters give pagination and output-size control (20). No error codes or messages documented that we could find (0, was 5 with nothing behind it). `dry_run` on create and update validates a service before anything deploys; no idempotency keys (8, held as partial). Sensible scale-to-zero defaults (5 minutes idle) and official clients in Go and Python, but required parameters weren't readable in the script-drawn reference (8, held as partial). 15 + 20 + 0 + 8 + 8 = 51." }, "scores": { "a": 66, "b": 51 } }, { "by": 7, "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": "The newest release is the Python SDK `koyeb-sdk` v1.5.6, tagged 20 October 2026, 16 days before this check (30). Five releases since 7 August carry code changes, CLI v5.11.0 (27 August) and v5.12.0 (10 September), and Python SDK v1.5.2 (27 August), v1.5.5 (29 September) and v1.5.6 (20 October) (20). The 1 October check read the CLI as ending at v5.10.2 and missed both. The public changelog still ends on 27 February 2026. A community forum and a stalled web changelog, and GitHub issues weren't readable (5 of 15, held). Current official SDKs in Go (client updated 10 October 2026) and Python (15, was 5). CI workflows exist in both repositories, but package health and CI results weren't readable (3, held). 30 + 20 + 5 + 15 + 3 = 73." }, "scores": { "a": 80, "b": 73 } } ], "facts": [ { "a": "Platform", "b": "Platform", "name": "Kind" }, { "a": "Google Cloud", "b": "Koyeb", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://app.koyeb.com/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "OAuth", "b": "Token", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "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": "no", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-20", "name": "Last release" }, { "a": "2026-09-02", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "no date given", "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": "yes", "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": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "72 stars", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Koyeb's 46.6 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Cloud Run GPUs or Koyeb?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 50", "Schema \u0026 documentation, 81 against 31", "Agent ergonomics, 66 against 51", "Security \u0026 auth, 78 against 50", "Maintenance \u0026 community, 80 against 73", "Transparency \u0026 trust, 84 against 64" ], "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": "Teams that want low-cost H100, H200 or B200 containers with scale to zero and an SLA, deployed from Git or an image.", "slug": "koyeb", "watchFor": "Public changelog silent since 27 February 2026, so API changes surface only through CLI and SDK releases" } ], "history": { "cloud-run-gpus": null, "koyeb": [ { "causes": [ "reliability", "correction" ], "date": "2026-11-05", "delta": 0, "from": 46.6, "fromGrade": "D", "to": 46.6, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 46.5, "fromGrade": "D", "to": 46.6, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.5, "from": 47, "fromGrade": "D", "to": 46.5, "toGrade": "D" } ] }, "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-koyeb.json", "title": "Baseten vs Koyeb", "url": "https://www.anchorterminal.com/compare/baseten-vs-koyeb" }, { "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-koyeb.json", "title": "Beam vs Koyeb", "url": "https://www.anchorterminal.com/compare/beam-vs-koyeb" }, { "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-koyeb.json", "title": "Cerebrium vs Koyeb", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-koyeb" }, { "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-koyeb.json", "title": "CoreWeave vs Koyeb", "url": "https://www.anchorterminal.com/compare/coreweave-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-koyeb.json", "title": "Crusoe Cloud vs Koyeb", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb.json", "title": "GPUsMarket vs Koyeb", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb.json", "title": "Hugging Face Inference Endpoints vs Koyeb", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb.json", "title": "Hyperbolic vs Koyeb", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb" }, { "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/koyeb-vs-massed-compute.json", "title": "Koyeb vs Massed Compute", "url": "https://www.anchorterminal.com/compare/koyeb-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-modal.json", "title": "Koyeb vs Modal", "url": "https://www.anchorterminal.com/compare/koyeb-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-nebius-ai-cloud.json", "title": "Koyeb vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/koyeb-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-northflank.json", "title": "Koyeb vs Northflank", "url": "https://www.anchorterminal.com/compare/koyeb-vs-northflank" }, { "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/koyeb-vs-runpod.json", "title": "Koyeb vs Runpod", "url": "https://www.anchorterminal.com/compare/koyeb-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-thunder-compute.json", "title": "Koyeb vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/koyeb-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.json", "title": "Koyeb vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.json", "title": "Koyeb vs Vast.ai", "url": "https://www.anchorterminal.com/compare/koyeb-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-verda.json", "title": "Koyeb vs Verda", "url": "https://www.anchorterminal.com/compare/koyeb-vs-verda" }, { "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": 20, "cloud-run-gpus": 70, "edge": "cloud-run-gpus", "key": "reliability", "koyeb": 50, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 50, "cloud-run-gpus": 81, "edge": "cloud-run-gpus", "key": "schema", "koyeb": 31, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 15, "cloud-run-gpus": 66, "edge": "cloud-run-gpus", "key": "ergonomics", "koyeb": 51, "name": "Agent ergonomics", "weight": 13 }, { "by": 28, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "key": "security", "koyeb": 50, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "cloud-run-gpus": 20, "edge": "", "key": "payments", "koyeb": 20, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "cloud-run-gpus": 80, "edge": "cloud-run-gpus", "key": "maintenance", "koyeb": 73, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 20, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "key": "transparency", "koyeb": 64, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Koyeb's 46.6 (D), and leads in 6 of 7 scored categories. 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.", "koyeb": "Koyeb publishes per-second GPU prices without a login, from $0.50 an hour for an RTX 4000 SFF Ada to $2.50 for an H100, with an SLA document from the Scale plan. It has no downloadable OpenAPI file, documented rate limits or error codes, and no free compute plan, and its public changelog has been silent since 27 February 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Koyeb's 46.6 (D), and leads in 6 of 7 scored categories. 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- Koyeb: grade D, 46.6/100, rank #1155 of 1486. Markdown https://www.anchorterminal.com/tools/koyeb.md · JSON https://www.anchorterminal.com/api/v1/tools/koyeb.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 50\n- Schema \u0026 documentation, 81 against 31\n- Agent ergonomics, 66 against 51\n- Security \u0026 auth, 78 against 50\n- Maintenance \u0026 community, 80 against 73\n- Transparency \u0026 trust, 84 against 64\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### Koyeb (D)\n\nGood for: Teams that want low-cost H100, H200 or B200 containers with scale to zero and an SLA, deployed from Git or an image.\n\nWatch for: Public changelog silent since 27 February 2026, so API changes surface only through CLI and SDK releases\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Cloud Run GPUs +50\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- Koyeb (31): No downloadable OpenAPI file. The API reference at koyeb.com/docs/reference/api renders only by script, and the generated docs in the Go and Python client repositories aren't a published contract (0, was 10). No llms.txt (www.koyeb.com/llms.txt and /docs/llms.txt both 404) and no Markdown twins (0). Guides on scale to zero and autoscaling say when to use each setting (10, held). Typed parameters with required bodies in the Go client's docs, but service types and statuses are free strings with no listed values (8, held). CLI examples throughout; no documented error responses found (5, held). /v1 paths, but the public changelog stopped on 27 February 2026 (8, held). 0 + 0 + 10 + 8 + 5 + 8 = 31.\n\n### Security \u0026 auth: Cloud Run GPUs +28\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- Koyeb (50): Personal access tokens and organisation tokens sent as Bearer; no scopes found (20). RBAC only on Enterprise; no read-only token (5). Runs your own containers and returns their output (10). Audit logs only on Enterprise (10). ISO 27001 and SOC 2 listed on the pricing page for Enterprise; www.koyeb.com/.well-known/security.txt is 404 and no disclosure policy, SECURITY.md or bug bounty found, so a bare certification claim (5). 20 + 5 + 10 + 10 + 5 = 50.\n\n### Reliability: Cloud Run GPUs +20\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- Koyeb (50): Graded on the hosted lines for its platform API. Instatus page at status.koyeb.com with components (API, Control Panel, Build / Provisioning and one per region) and history back to 2022 in its feed (20). Since 7 August the feed holds nine incidents and one maintenance. The eight in September each name one region, one GPU type or some customers, or ran 6 to 52 minutes (8, 11, 15, 21, 22 and 23 September and two on 29 September). On 16 October Koyeb posted a separate incident, \"The ongoing maintenance is causing API to fail with 500\", on the API, Control Panel and Build components for 24 minutes, inside a maintenance window announced the day before for 07:00 to 08:00 UTC with \"max 10m unavailability\". The status page labels it an incident and the outage ran past the unavailability announced, so it counts as an incident, and the API failing with 500 is errors across the board, one major outage (10). No API rate limits found in the docs we could read (0). No 429 or backoff guidance found (0). The Scale plan lists a 99.9 per cent uptime SLA and Enterprise 99.99, with an SLA document at /docs/legal/sla setting service credits (10). Services and GPUs are generally available; light sleep is a preview (10). 20 + 10 + 0 + 0 + 10 + 10 = 50.\n\n### Transparency \u0026 trust: Cloud Run GPUs +20\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- Koyeb (64): The editorial half. Closed service under the French-law Master Services Agreement of 28 June 2024; the CLI and Go client are Apache-2.0 (20). An MSA and a DPA are published, the MSA deletes customer data at the end of the reversibility period, but the footer's privacy link points at the DPA and we found no separate privacy policy or retention periods (15). The Mistral agreement was announced on 17 February 2026, with Starter closed to new sign-ups, and no dated migration or end-of-life notice since (5, held). Regions are named on the status page (North America, Europe, Asia-Pacific); subprocessors not checked (10). 20 + 15 + 5 + 10 = 50.\n\n### Agent ergonomics: Cloud Run GPUs +15\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- Koyeb (51): List endpoints take `limit` and `offset` plus filters on name, type, status, region and ID, per the Go client's docs (15). The same filters give pagination and output-size control (20). No error codes or messages documented that we could find (0, was 5 with nothing behind it). `dry_run` on create and update validates a service before anything deploys; no idempotency keys (8, held as partial). Sensible scale-to-zero defaults (5 minutes idle) and official clients in Go and Python, but required parameters weren't readable in the script-drawn reference (8, held as partial). 15 + 20 + 0 + 8 + 8 = 51.\n\n### Maintenance \u0026 community: Cloud Run GPUs +7\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- Koyeb (73): The newest release is the Python SDK `koyeb-sdk` v1.5.6, tagged 20 October 2026, 16 days before this check (30). Five releases since 7 August carry code changes, CLI v5.11.0 (27 August) and v5.12.0 (10 September), and Python SDK v1.5.2 (27 August), v1.5.5 (29 September) and v1.5.6 (20 October) (20). The 1 October check read the CLI as ending at v5.10.2 and missed both. The public changelog still ends on 27 February 2026. A community forum and a stalled web changelog, and GitHub issues weren't readable (5 of 15, held). Current official SDKs in Go (client updated 10 October 2026) and Python (15, was 5). CI workflows exist in both repositories, but package health and CI results weren't readable (3, held). 30 + 20 + 5 + 15 + 3 = 73.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Koyeb | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 50 | Cloud Run GPUs +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 31 | Cloud Run GPUs +50 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 51 | Cloud Run GPUs +15 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 50 | Cloud Run GPUs +28 |\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 | 73 | Cloud Run GPUs +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 64 | Cloud Run GPUs +20 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **68.4 · B** | **46.6 · D** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Koyeb |\n| --- | --- | --- |\n| Kind | Platform | Platform |\n| Vendor | Google Cloud | Koyeb |\n| Hosted endpoint | `https://run.googleapis.com` | `https://app.koyeb.com/v1` |\n| Transports | | HTTP |\n| Auth | OAuth | Token |\n| Pricing | Pay per use | Freemium |\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 | no |\n| Last release | 2026-10-30 | 2026-10-20 |\n| Terms last updated | 2026-09-02 | no date given |\n| Privacy policy last updated | 2026-09-28 | no date given |\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 | yes |\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 | not found in the text |\n| Popularity | none | 72 stars |\n| Agent reviews | none | 3.5/5 (2) |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Koyeb\n\n- no change on 5 November 2026: reliability, correction\n- +0.1 on 27 October 2026: checklist\n- -0.5 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**Koyeb.** Koyeb publishes per-second GPU prices without a login, from $0.50 an hour for an RTX 4000 SFF Ada to $2.50 for an H100, with an SLA document from the Scale plan. It has no downloadable OpenAPI file, documented rate limits or error codes, and no free compute plan, and its public changelog has been silent since 27 February 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### Koyeb\n\n1. Pass `dry_run` on service create or update to validate the definition before anything deploys\n2. Page service lists with `limit` and `offset` and filter by `statuses` instead of fetching everything\n3. Expect the first request after deep sleep to take 1 to 5 seconds and retry once with a timeout\n4. Set `--min-scale 0` on GPU services so idle instances stop billing\n5. Read the CLI's CHANGES.md and the Python SDK tags for API changes, since the web changelog stopped in February 2026\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Koyeb?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Koyeb's 46.6 (D), and leads in 6 of 7 scored categories.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"koyeb\"}`. From a terminal: `anchor compare cloud-run-gpus koyeb`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/koyeb.json\n\n## Other comparisons with Cloud Run GPUs or Koyeb\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Koyeb](https://www.anchorterminal.com/compare/baseten-vs-koyeb.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Koyeb](https://www.anchorterminal.com/compare/beam-vs-koyeb.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Koyeb](https://www.anchorterminal.com/compare/cerebrium-vs-koyeb.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 Koyeb](https://www.anchorterminal.com/compare/coreweave-vs-koyeb.md)\n- [Crusoe Cloud vs Koyeb](https://www.anchorterminal.com/compare/crusoe-cloud-vs-koyeb.md)\n- [GPUsMarket vs Koyeb](https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb.md)\n- [Hugging Face Inference Endpoints vs Koyeb](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb.md)\n- [Hyperbolic vs Koyeb](https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb.md)\n- [Koyeb vs Lambda Cloud](https://www.anchorterminal.com/compare/koyeb-vs-lambda.md)\n- [Koyeb vs Massed Compute](https://www.anchorterminal.com/compare/koyeb-vs-massed-compute.md)\n- [Koyeb vs Modal](https://www.anchorterminal.com/compare/koyeb-vs-modal.md)\n- [Koyeb vs Nebius AI Cloud](https://www.anchorterminal.com/compare/koyeb-vs-nebius-ai-cloud.md)\n- [Koyeb vs Northflank](https://www.anchorterminal.com/compare/koyeb-vs-northflank.md)\n- [Koyeb vs Replicate Deployments](https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy.md)\n- [Koyeb vs Runpod](https://www.anchorterminal.com/compare/koyeb-vs-runpod.md)\n- [Koyeb vs Thunder Compute](https://www.anchorterminal.com/compare/koyeb-vs-thunder-compute.md)\n- [Koyeb vs Together GPU Clusters](https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.md)\n- [Koyeb vs Vast.ai](https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.md)\n- [Koyeb vs Verda](https://www.anchorterminal.com/compare/koyeb-vs-verda.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 Koyeb", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Koyeb's 46.6 (D) for compute serverless. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Koyeb D 46.6", "scores" ], "h1": "Cloud Run GPUs vs Koyeb", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-koyeb", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Koyeb for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb" }, "tokens": { "markdown": 4800, "slim": 2730 }, "version": 1 }