{ "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 Vast.ai's 56.4 (C), and leads in 5 of 7 scored categories.", "b": { "slug": "vast-ai", "name": "Vast.ai", "vendor": "Vast.ai Inc.", "vendorUrl": "https://vast.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Vast.ai is a marketplace for renting GPUs by the second from independent hosts and data centres, as Docker instances, virtual machines or autoscaling serverless endpoints. Agents use the `vastai` CLI, a Python SDK or a REST API.", "url": "https://www.anchorterminal.com/tools/vast-ai", "markdownUrl": "https://www.anchorterminal.com/tools/vast-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vast-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vast-ai.json", "dns": "vast-ai.grade.anchorterminal.com", "repo": "https://github.com/vast-ai/vast-cli", "license": "Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT", "transports": [ "http" ], "remoteUrl": "https://console.vast.ai/api/v0", "packages": [ { "registry": "pypi", "name": "vastai" } ], "auth": "api-key", "authNotes": "API key from the console's Keys page, sent as `Authorization: Bearer` to https://console.vast.ai/api/v0, or stored once with `vastai set api-key`. Access is self-serve after a browser signup and email verification. A key has full account access by default. Scoped keys take any of 11 permission categories (`instance_read`, `instance_write`, `billing_write` and others) and constraints that narrow an endpoint to resource IDs. Keys are shown once, and can be reset or deleted with immediate effect. The rate-limit page names an `api_key` query parameter as part of a caller's identity, while the authentication page documents only the header.", "pricing": "usage", "pricingNotes": "Prepaid credit with a $5 minimum deposit and no free tier or trial found. Each host sets its own rate per listing, so there is no fixed price list. Live rates are public at vast.ai/pricing and through `vastai search offers`. GPU time bills per second while an instance runs, storage per second while it exists (stopped included) and bandwidth per byte. Interruptible rentals are bid-priced and reserved rentals are prepaid for 1, 3 or 6 months. Serverless adds no fee on top of instance rates. Spent credit is not refunded (https://docs.vast.ai/guides/reference/billing.md, https://docs.vast.ai/guides/instances/pricing.md, checked 2026-10-08).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, llms.txt, the agent pricing page or the OpenAPI file (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 223, "npmWeekly": null, "pypiWeekly": 32699, "asOf": "2026-10-08" }, "docsUrl": "https://docs.vast.ai", "llmsTxt": "https://docs.vast.ai/llms.txt", "openapi": "https://docs.vast.ai/api-reference/openapi.json", "capabilities": [ "compute.gpu", "compute.containers", "compute.serverless", "compute.endpoints" ], "tags": [ "hosted", "marketplace", "usage-priced", "prepaid", "api-key", "scoped-keys", "openapi", "llms-txt", "python", "cli", "agent-skill", "serverless", "spot", "status-page", "soc2" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 56.4, "grade": "C", "agentReady": false, "rank": 824, "ranked": true, "rankOf": 1486, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 81, "payments": 20, "reliability": 50, "schema": 78, "security": 70, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -3, "negativeNotes": [ "2026-10-30, -3. A published behaviour changed for existing callers with notice only on release day. vastai v1.10.0, a minor release with no changelog, makes `vastai search offers` request amd64 and arm64 machines by default, where the help text's default query had no architecture and the API documents amd64 as the default, so unchanged searches now return arm64 hosts. Read as people-data-labs' 20 October field change was. https://github.com/vast-ai/vast-cli/commit/a357b331fdebc4c137dd11be853e1290bdc27c9a" ], "verdict": "API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships about weekly with a skill file and editor plugins for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier.", "bestFor": "Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.", "strengths": [ "API keys take 11 permission categories and per-endpoint constraints on resource IDs, and can be reset or deleted at once", "Public OpenAPI 3.1 file with 89 operations, llms.txt and Markdown docs pages", "MIT CLI and Python SDK, v1.10.0 on 30 October 2026, with 13 tagged releases since 4 August 2026", "Per-second billing, with serverless workers charged at the same rates as rented instances", "Vulnerability disclosure policy with safe harbour and triage within 5 business days, and an account audit log from the CLI" ], "weaknesses": [ "No SLA. The terms say availability is not guaranteed and the service can change without notice", "Rate-limit thresholds are unpublished and 429 responses carry no `Retry-After` header", "No free tier. Credit is prepaid with a $5 minimum deposit after a browser signup and email verification", "Hosts are independent. The security FAQ says individual hosts may have less formal security than Secure Cloud data centres", "The terms of 1 September 2026 prohibit scripts and automated access to the services without a separate written agreement, which conflicts with the public API" ], "agentNotes": [ "Create a scoped key with `vastai create api-key --permissions` for the agent. A default key has full account access, billing and key management included", "Pass `--raw` on every CLI command for JSON output, and `-y` on `vastai destroy instance`, which otherwise waits for a confirmation prompt", "Register an SSH key with `vastai create ssh-key` before creating an instance, or the host is unreachable", "Destroy instances when finished. A stopped instance still bills storage, and a zero balance without a saved card leads to deletion", "Back off on HTTP 429 yourself when calling REST directly. The CLI retries 429, honouring a Retry-After header when one comes back, and stops on a daily search quota", "Filter searches with `verified=true` or the Secure Cloud option for sensitive data, set a `dph_total` price cap, and add `cpu_arch=amd64` for amd64-only images, since v1.10.0 searches arm64 machines too" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 56.4 } ], "editorialScores": { "ergonomics": 57, "maintenance": 81, "payments": 20, "reliability": 50, "schema": 78, "security": 70, "transparency": 45 }, "provenanceScore": 82, "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 vastai", "http": "curl -s -H \"Authorization: Bearer $VAST_API_KEY\" \\\n \"https://console.vast.ai/api/v0/users/current/\"", "claudeCode": "/plugin marketplace add vast-ai/vast-claude-plugin\n/plugin install vastai" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/vast-ai" }, "area": "models", "provenance": { "legalEntity": "Vast.ai Inc.", "domain": "vast.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://vast.ai/terms", "privacy": "https://vast.ai/privacy", "statusPage": "https://status.vast.ai", "changelog": "https://github.com/vast-ai/vast-cli/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Terms of Use Agreement, version date 1 September 2026, names Vast.ai Inc. and its affiliates, covers the website and the rental service, and is governed by California law with JAMS arbitration in the Los Angeles area.", "The privacy policy, version date 18 June 2025, names Vast.ai Inc. and a Privacy Officer at contact@vast.ai. It is written for users of the website and contains an unfilled `[INSERT HYPERLINK]` placeholder.", "A Data Processing Agreement at vast.ai/data-processing-agreement forms part of the terms, with standard contractual clauses and five named sub-processors (Stripe, Google, Meta, Twitter, Microsoft).", "The REST API answers at console.vast.ai and serverless routing at run.vast.ai, both on the vendor's domain. Rented machines belong to independent hosts.", "vast.ai/.well-known/security.txt returns 404. A vulnerability disclosure policy dated 23 July 2025 at vast.ai/vulnerability-disclosure-policy sends reports to security@vast.ai.", "No API changelog was found in the docs index. The changelog link is the CLI and SDK repository's release list, which has no CHANGELOG file.", "RDAP for vast.ai gives a registration date of 2017-12-16." ], "score": 82 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vast-ai.json", "live": { "slug": "vast-ai", "probe": { "target": "https://console.vast.ai/api/v0", "method": "get", "lastAt": "2026-11-07T18:21:03.28530026Z", "lastOk": true, "lastStatus": 404, "lastMs": 493, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 372, "p95ms24h": 487, "samples24h": 239, "samples30d": 7440, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "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://status.vast.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:55.408936389Z" }, "versions": [ { "registry": "github", "name": "vast-ai/vast-cli", "version": "v1.11.0", "released": "2026-11-04", "seenAt": "2026-11-07T00:14:43.765870402Z" }, { "registry": "pypi", "name": "vastai", "version": "1.11.0", "released": "2026-11-04", "seenAt": "2026-11-07T00:14:43.584449824Z" } ], "githubStars": 230, "pypiWeekly": 32921, "securityTxt": { "url": "https://vast.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:02:03.166474584Z" }, "llmsTxt": { "url": "https://docs.vast.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:15.796619863Z" }, "domain": { "domain": "vast.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/vast.ai", "checkedAt": "2026-11-01T14:16:46.621379816Z" }, "pages": [ { "url": "https://docs.vast.ai/guides/instances/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:08:35.441877987Z", "changedAt": "2026-10-24T02:16:55.781341869Z", "fingerprint": "93ae7e3a1e2d" }, { "url": "https://vast.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:23:10.681277893Z", "changedAt": "2026-11-05T13:07:32.192530933Z", "fingerprint": "e5d8e448f73f" }, { "url": "https://vast.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:23:12.932242476Z", "changedAt": "2026-11-05T13:07:34.915328452Z", "fingerprint": "bbee067d5cd1" } ], "github": { "repo": "vast-ai/vast-cli", "checkedAt": "2026-11-02T09:35:11.919319198Z", "stars": 227, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T20:55:21Z", "openIssues": 19, "openPRs": 41, "issuesOpened90d": 3, "issuesClosed90d": 5, "prsMerged90d": 29, "ci": { "branch": "master", "runs": 2, "success": 0, "failure": 2, "other": 0, "latest": "failure", "latestAt": "2026-07-09T19:43:00Z" }, "replies": { "sampled": 25, "unanswered": 11, "medianDays": 4.2 } }, "updatedAt": "2026-11-07T18:21:03.28530026Z" } }, "edges": [ { "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 as a hosted service. status.vast.ai is Vast.ai's own page with three components (vast, console, serverless) and 30-day bars built from roughly hourly checks, with no incident write-ups (20). The page draws its bars by script from check-log files on the same host. The 8 October count came from those files, the page's own data, which this run doesn't read (as the Docusign and SeaTable listings read their status pages' data feeds), so it's struck, and the window from 4 August to 2 November is unread (5). The page covers Vast.ai's control plane and not the independent hosts' machines. Rate limits are described as a minimum interval per endpoint and identity, re-read on 2 November, but thresholds are unpublished apart from an `x-rateLimit` value on 2 of 89 operations in the OpenAPI file (5 of 15). 429 is documented with backoff advice and the CLI retries it, but the docs say the API sets no `Retry-After` header, and there is no idempotency key for instance creation (10 of 15). No SLA found, and the terms say availability is not guaranteed (0). Instances, serverless and the REST API carry no beta label (10). 20 + 5 + 5 + 10 + 0 + 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": "A closed service with an MIT CLI and SDK. The Terms of Use Agreement of 1 September 2026, re-read on 2 November, prohibits scripts and automated access to the services without a separate written agreement, which conflicts with the public API and agent tooling (17 of 30). The compliance page says data is destroyed when an instance is deleted, and the DPA allows return or deletion on written notice within 30 days of termination. The privacy policy of 18 June 2025 is written for website users, gives no retention periods, allows targeted advertising and contains an unfilled `[INSERT HYPERLINK]` placeholder (15 of 30). No deprecation policy was found, and the terms allow changes or discontinuation without notice. v0 and v1 routes coexist (3 of 20). The DPA names five sub-processors without locations and gives new ones only on request. Host location is shown per listing and can be filtered (10 of 20). 17 + 15 + 3 + 10 = 45." }, "scores": { "a": 84, "b": 64 } }, { "by": 9, "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": "No MCP server for account actions. The CLI skill file is about 19 KB, `--raw` returns JSON on every command, and the v1 instances route supports column selection (18 of 25). Search takes filter operators, sort fields and a price cap, and v1 instances use keyset pagination with at most 25 a page (16 of 20). The usual error body has `success`, `error` and `msg`, but some endpoints omit fields and 429 is often plain text (10 of 20). No idempotency keys were found in the OpenAPI file. The CLI retries only 429, and `vastai destroy instance` asks for confirmation unless `-y` is passed (5 of 20). Templates supply launch defaults. The only official SDK is Python, and the docs send other languages to raw REST (8 of 15). 18 + 16 + 10 + 5 + 8 = 57." }, "scores": { "a": 66, "b": 57 } }, { "by": 8, "category": "security", "leads": "cloud-run-gpus", "name": "Security \u0026 auth", "reasons": { "a": "OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.", "b": "Keys can be scoped to 11 permission categories and narrowed by constraints to resource IDs, are shown once, and can be reset or deleted with immediate effect (30). The rate-limit page, re-read on 2 November, names an `api_key` query parameter as part of a caller's identity while the authentication page shows only the Bearer header. We took 5 of the checklist's 10 points for a key that can travel in a URL, a judgement call because the option is acknowledged but not taught (25 of 30). Read-only categories and per-instance constraints exist. The CLI confirms a destroy, and Vast.ai's auth.md asks agents to confirm paid or destructive actions, but nothing on the server enforces approval and default keys have full access (15 of 20). The service runs the customer's own containers and returns their logs (10). `vastai show audit-logs` returns account action history. Its retention and fields were not reviewed (10 of 15). A vulnerability disclosure policy dated 23 July 2025, re-read on 2 November, has safe harbour, triage within 5 business days and security@vast.ai. Its bounty is discretionary, which this checklist doesn't count. The compliance page states SOC 2 Type 2 and makes a SOC 3 report available on request. There is no security.txt (404 on 2 November) and no advisories for `vastai` in OSV, and the security FAQ says individual hosts may have less formal security. A reporting route and SOC 2 with no counted bounty take 10, as Sinch's messaging listing (10 of 20). 25 + 15 + 10 + 10 + 10 = 70." }, "scores": { "a": 78, "b": 70 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Vast.ai Inc.", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://console.vast.ai/api/v0", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "OAuth", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0", "b": "Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-30", "name": "Last release" }, { "a": "2026-09-02", "b": "2026-09-01", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "2025-06-18", "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": "yes", "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": "223 stars, 33k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Vast.ai's 56.4 (C), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Cloud Run GPUs or Vast.ai?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Vast.ai at https://console.vast.ai/api/v0.", "question": "Can an agent call Cloud Run GPUs and Vast.ai without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 50", "Agent ergonomics, 66 against 57", "Security \u0026 auth, 78 against 70", "Transparency \u0026 trust, 84 against 64" ], "also": [ "No incidents deducted, where Vast.ai loses 3 points for them" ], "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": "Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.", "slug": "vast-ai", "watchFor": "No SLA. The terms say availability is not guaranteed and the service can change without notice" } ], "history": { "cloud-run-gpus": null, "vast-ai": [ { "causes": [ "correction", "event" ], "date": "2026-11-02", "delta": -6.3, "from": 62.7, "fromGrade": "B", "to": 56.4, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 62.6, "fromGrade": "B", "to": 62.7, "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-vast-ai.json", "title": "Baseten vs Vast.ai", "url": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai" }, { "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-vast-ai.json", "title": "Beam vs Vast.ai", "url": "https://www.anchorterminal.com/compare/beam-vs-vast-ai" }, { "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-vast-ai.json", "title": "Cerebrium vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai" }, { "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-vast-ai.json", "title": "CoreWeave vs Vast.ai", "url": "https://www.anchorterminal.com/compare/coreweave-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-vast-ai.json", "title": "Crusoe Cloud vs Vast.ai", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-vast-ai.json", "title": "GPUsMarket vs Vast.ai", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai.json", "title": "Hugging Face Inference Endpoints vs Vast.ai", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-vast-ai.json", "title": "Hyperbolic vs Vast.ai", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-vast-ai" }, { "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/lambda-vs-vast-ai.json", "title": "Lambda Cloud vs Vast.ai", "url": "https://www.anchorterminal.com/compare/lambda-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/massed-compute-vs-vast-ai.json", "title": "Massed Compute vs Vast.ai", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-vast-ai.json", "title": "Modal vs Vast.ai", "url": "https://www.anchorterminal.com/compare/modal-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-vast-ai.json", "title": "Nebius AI Cloud vs Vast.ai", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-vast-ai.json", "title": "Northflank vs Vast.ai", "url": "https://www.anchorterminal.com/compare/northflank-vs-vast-ai" }, { "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/runpod-vs-vast-ai.json", "title": "Runpod vs Vast.ai", "url": "https://www.anchorterminal.com/compare/runpod-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai.json", "title": "Thunder Compute vs Vast.ai", "url": "https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.json", "title": "Together GPU Clusters vs Vast.ai", "url": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/vast-ai-vs-verda.json", "title": "Vast.ai vs Verda", "url": "https://www.anchorterminal.com/compare/vast-ai-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.json", "title": "Cloud Run GPUs vs Koyeb", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.json", "title": "Cloud Run GPUs vs Modal", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.json", "title": "Cloud Run GPUs vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.json", "title": "Cloud Run GPUs vs Runpod", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-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", "name": "Reliability", "vast-ai": 50, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "cloud-run-gpus": 81, "edge": "cloud-run-gpus", "key": "schema", "name": "Schema \u0026 documentation", "vast-ai": 78, "weight": 13 }, { "by": 9, "cloud-run-gpus": 66, "edge": "cloud-run-gpus", "key": "ergonomics", "name": "Agent ergonomics", "vast-ai": 57, "weight": 13 }, { "by": 8, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "key": "security", "name": "Security \u0026 auth", "vast-ai": 70, "weight": 14 }, { "by": 0, "cloud-run-gpus": 20, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "vast-ai": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "cloud-run-gpus": 80, "edge": "vast-ai", "key": "maintenance", "name": "Maintenance \u0026 community", "vast-ai": 81, "weight": 7 }, { "by": 20, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "key": "transparency", "name": "Transparency \u0026 trust", "vast-ai": 64, "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Vast.ai's 56.4 (C), and leads in 5 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.", "vast-ai": "API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships about weekly with a skill file and editor plugins for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Vast.ai's 56.4 (C), and leads in 5 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- Vast.ai: grade C, 56.4/100, rank #824 of 1486. Markdown https://www.anchorterminal.com/tools/vast-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/vast-ai.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- Agent ergonomics, 66 against 57\n- Security \u0026 auth, 78 against 70\n- Transparency \u0026 trust, 84 against 64\n\nAlso in its favour:\n- No incidents deducted, where Vast.ai loses 3 points for them\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### Vast.ai (C)\n\nGood for: Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.\n\nWatch for: No SLA. The terms say availability is not guaranteed and the service can change without notice\n\n\n## Why the edge\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- Vast.ai (50): Graded as a hosted service. status.vast.ai is Vast.ai's own page with three components (vast, console, serverless) and 30-day bars built from roughly hourly checks, with no incident write-ups (20). The page draws its bars by script from check-log files on the same host. The 8 October count came from those files, the page's own data, which this run doesn't read (as the Docusign and SeaTable listings read their status pages' data feeds), so it's struck, and the window from 4 August to 2 November is unread (5). The page covers Vast.ai's control plane and not the independent hosts' machines. Rate limits are described as a minimum interval per endpoint and identity, re-read on 2 November, but thresholds are unpublished apart from an `x-rateLimit` value on 2 of 89 operations in the OpenAPI file (5 of 15). 429 is documented with backoff advice and the CLI retries it, but the docs say the API sets no `Retry-After` header, and there is no idempotency key for instance creation (10 of 15). No SLA found, and the terms say availability is not guaranteed (0). Instances, serverless and the REST API carry no beta label (10). 20 + 5 + 5 + 10 + 0 + 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- Vast.ai (64): A closed service with an MIT CLI and SDK. The Terms of Use Agreement of 1 September 2026, re-read on 2 November, prohibits scripts and automated access to the services without a separate written agreement, which conflicts with the public API and agent tooling (17 of 30). The compliance page says data is destroyed when an instance is deleted, and the DPA allows return or deletion on written notice within 30 days of termination. The privacy policy of 18 June 2025 is written for website users, gives no retention periods, allows targeted advertising and contains an unfilled `[INSERT HYPERLINK]` placeholder (15 of 30). No deprecation policy was found, and the terms allow changes or discontinuation without notice. v0 and v1 routes coexist (3 of 20). The DPA names five sub-processors without locations and gives new ones only on request. Host location is shown per listing and can be filtered (10 of 20). 17 + 15 + 3 + 10 = 45.\n\n### Agent ergonomics: Cloud Run GPUs +9\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- Vast.ai (57): No MCP server for account actions. The CLI skill file is about 19 KB, `--raw` returns JSON on every command, and the v1 instances route supports column selection (18 of 25). Search takes filter operators, sort fields and a price cap, and v1 instances use keyset pagination with at most 25 a page (16 of 20). The usual error body has `success`, `error` and `msg`, but some endpoints omit fields and 429 is often plain text (10 of 20). No idempotency keys were found in the OpenAPI file. The CLI retries only 429, and `vastai destroy instance` asks for confirmation unless `-y` is passed (5 of 20). Templates supply launch defaults. The only official SDK is Python, and the docs send other languages to raw REST (8 of 15). 18 + 16 + 10 + 5 + 8 = 57.\n\n### Security \u0026 auth: Cloud Run GPUs +8\n\n- Cloud Run GPUs (78): OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.\n- Vast.ai (70): Keys can be scoped to 11 permission categories and narrowed by constraints to resource IDs, are shown once, and can be reset or deleted with immediate effect (30). The rate-limit page, re-read on 2 November, names an `api_key` query parameter as part of a caller's identity while the authentication page shows only the Bearer header. We took 5 of the checklist's 10 points for a key that can travel in a URL, a judgement call because the option is acknowledged but not taught (25 of 30). Read-only categories and per-instance constraints exist. The CLI confirms a destroy, and Vast.ai's auth.md asks agents to confirm paid or destructive actions, but nothing on the server enforces approval and default keys have full access (15 of 20). The service runs the customer's own containers and returns their logs (10). `vastai show audit-logs` returns account action history. Its retention and fields were not reviewed (10 of 15). A vulnerability disclosure policy dated 23 July 2025, re-read on 2 November, has safe harbour, triage within 5 business days and security@vast.ai. Its bounty is discretionary, which this checklist doesn't count. The compliance page states SOC 2 Type 2 and makes a SOC 3 report available on request. There is no security.txt (404 on 2 November) and no advisories for `vastai` in OSV, and the security FAQ says individual hosts may have less formal security. A reporting route and SOC 2 with no counted bounty take 10, as Sinch's messaging listing (10 of 20). 25 + 15 + 10 + 10 + 10 = 70.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Vast.ai | 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 | 78 | Cloud Run GPUs +3 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 57 | Cloud Run GPUs +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 70 | Cloud Run GPUs +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 81 | Vast.ai +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 64 | Cloud Run GPUs +20 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **68.4 · B** | **56.4 · C** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Vast.ai |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Vast.ai Inc. |\n| Hosted endpoint | `https://run.googleapis.com` | `https://console.vast.ai/api/v0` |\n| Transports | | HTTP |\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 | Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-30 | 2026-10-30 |\n| Terms last updated | 2026-09-02 | 2026-09-01 |\n| Privacy policy last updated | 2026-09-28 | 2025-06-18 |\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 | yes |\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 | 223 stars, 33k PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Vast.ai\n\n- -6.3 on 2 November 2026 (B to C): correction, negative event\n- +0.1 on 27 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**Vast.ai.** API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships about weekly with a skill file and editor plugins for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier.\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### Vast.ai\n\n1. Create a scoped key with `vastai create api-key --permissions` for the agent. A default key has full account access, billing and key management included\n2. Pass `--raw` on every CLI command for JSON output, and `-y` on `vastai destroy instance`, which otherwise waits for a confirmation prompt\n3. Register an SSH key with `vastai create ssh-key` before creating an instance, or the host is unreachable\n4. Destroy instances when finished. A stopped instance still bills storage, and a zero balance without a saved card leads to deletion\n5. Back off on HTTP 429 yourself when calling REST directly. The CLI retries 429, honouring a Retry-After header when one comes back, and stops on a daily search quota\n6. Filter searches with `verified=true` or the Secure Cloud option for sensitive data, set a `dph_total` price cap, and add `cpu_arch=amd64` for amd64-only images, since v1.10.0 searches arm64 machines too\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Vast.ai?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Vast.ai's 56.4 (C), and leads in 5 of 7 scored categories.\n\n### Can an agent call Cloud Run GPUs and Vast.ai without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Vast.ai at https://console.vast.ai/api/v0.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"vast-ai\"}`. From a terminal: `anchor compare cloud-run-gpus vast-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/vast-ai.json\n\n## Other comparisons with Cloud Run GPUs or Vast.ai\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Vast.ai](https://www.anchorterminal.com/compare/baseten-vs-vast-ai.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Vast.ai](https://www.anchorterminal.com/compare/beam-vs-vast-ai.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Vast.ai](https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.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 Vast.ai](https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.md)\n- [Crusoe Cloud vs Vast.ai](https://www.anchorterminal.com/compare/crusoe-cloud-vs-vast-ai.md)\n- [GPUsMarket vs Vast.ai](https://www.anchorterminal.com/compare/gpusmarket-vs-vast-ai.md)\n- [Hugging Face Inference Endpoints vs Vast.ai](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai.md)\n- [Hyperbolic vs Vast.ai](https://www.anchorterminal.com/compare/hyperbolic-vs-vast-ai.md)\n- [Koyeb vs Vast.ai](https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.md)\n- [Lambda Cloud vs Vast.ai](https://www.anchorterminal.com/compare/lambda-vs-vast-ai.md)\n- [Massed Compute vs Vast.ai](https://www.anchorterminal.com/compare/massed-compute-vs-vast-ai.md)\n- [Modal vs Vast.ai](https://www.anchorterminal.com/compare/modal-vs-vast-ai.md)\n- [Nebius AI Cloud vs Vast.ai](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-vast-ai.md)\n- [Northflank vs Vast.ai](https://www.anchorterminal.com/compare/northflank-vs-vast-ai.md)\n- [Replicate Deployments vs Vast.ai](https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.md)\n- [Runpod vs Vast.ai](https://www.anchorterminal.com/compare/runpod-vs-vast-ai.md)\n- [Thunder Compute vs Vast.ai](https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai.md)\n- [Together GPU Clusters vs Vast.ai](https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.md)\n- [Vast.ai vs Verda](https://www.anchorterminal.com/compare/vast-ai-vs-verda.md)\n- [Cloud Run GPUs vs Koyeb](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md)\n- [Cloud Run GPUs vs Modal](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.md)\n- [Cloud Run GPUs vs Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md)\n- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md)\n- [Cloud Run GPUs vs 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 Vast.ai", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Vast.ai's 56.4 (C) for compute serverless. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Vast.ai C 56.4", "scores" ], "h1": "Cloud Run GPUs vs Vast.ai", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-vast-ai", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Vast.ai for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai" }, "tokens": { "markdown": 4700, "slim": 2480 }, "version": 1 }