{ "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 Crusoe Cloud's 62.4 (B), and leads in 5 of 7 scored categories. Crusoe Cloud leads on reliability and payments \u0026 pricing.", "b": { "slug": "crusoe-cloud", "name": "Crusoe Cloud", "vendor": "Crusoe", "vendorUrl": "https://www.crusoe.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Crusoe Cloud rents NVIDIA and AMD GPU virtual machines with managed Kubernetes and Slurm, and runs hosted model inference, dedicated deployments and LoRA fine-tuning. Resources are managed through a REST API, a CLI, a Terraform provider and a Go client.", "url": "https://www.anchorterminal.com/tools/crusoe-cloud", "markdownUrl": "https://www.anchorterminal.com/tools/crusoe-cloud.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/crusoe-cloud.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/crusoe-cloud.json", "dns": "crusoe-cloud.grade.anchorterminal.com", "repo": "https://github.com/crusoecloud/client-go", "license": "Proprietary service under the Crusoe Cloud Platform Terms of Service. The Go client and the MCP server package are MIT. The CLI ships as binaries, and no licence file was found in the Terraform provider repository", "transports": [ "http", "stdio" ], "remoteUrl": "https://api.cloud.crusoe.ai/v1", "packages": [ { "registry": "go", "name": "github.com/crusoecloud/client-go" }, { "registry": "npm", "name": "@crusoeai/cloud-mcp" } ], "auth": "api-key", "authNotes": "Self-serve. A person signs up in the console with Google, GitHub or an email code, then creates an access key ID and secret key under Security, with an optional alias and expiry. Each request carries `X-Crusoe-Timestamp` and `Authorization: Bearer 1.0:\u003caccess_key_id\u003e:\u003csignature\u003e`, where the signature is an HMAC-SHA256 of the path, sorted query string, verb and timestamp. Keys inherit the roles of the user who made them (`org-admin`, `org-editor`, `org-reader`, `project-editor`, `project-reader`). Managed AI uses separate Intelligence API keys sent as a Bearer token. Service accounts appear in the API description and the Terraform provider 1.6.0, with no docs page found.", "pricing": "usage", "pricingNotes": "Pay as you go, billed per second for on-demand VMs. Per GPU-hour, B300 $8.96, H200 $4.29, H100 $3.90, MI300X $3.45, A100 $2.00 to $2.30 and L40S $1.50. Vera Rubin, GB300, GB200, B200, MI355X and all spot prices are contact sales. Compute needs a non-prepaid credit card. $5 of introductory credits cover Serverless Inference and Fine-Tuning without a card. Ingress and egress are free (https://www.crusoe.ai/cloud/pricing, checked 2026-11-02).", "priceSummary": "$0.04 / vCPU-hr", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the API description or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": 41, "popularity": { "githubStars": null, "npmWeekly": 7, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.crusoecloud.com/", "llmsTxt": "https://docs.crusoecloud.com/llms.txt", "openapi": "https://api.crusoecloud.com/v1/openapi.json", "capabilities": [ "compute.gpu", "compute.containers", "compute.batch", "compute.endpoints" ], "tags": [ "hosted", "usage-priced", "openapi", "llms-txt", "mcp", "cli", "terraform", "go", "status-page", "soc2", "enterprise" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 62.4, "grade": "B", "agentReady": false, "rank": 555, "ranked": true, "rankOf": 1486, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 45, "maintenance": 76, "payments": 30, "reliability": 76, "schema": 79, "security": 74, "transparency": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -3, "negativeNotes": [ "2026-09-12 and 2026-10-02. Crusoe Updates marks two Serverless Inference model deprecations as Breaking, each dated the day it took effect. Z.ai GLM-5.1, Z.ai GLM-5.2, DeepSeek V3, Qwen3 235B A22B and Llama 3.3 70B \"were deprecated for Serverless Inference on September 12, 2026\", and Moonshot Kimi K2.6 on 2 October, with no earlier entry found. On 21 October DeepSeek V4.1 Flash began serving a new checkpoint in place, announced the same day. The terms promise 90 days' notice for incompatible API changes. One folded same-day term of 3 (https://docs.crusoe.ai/updates/index.html)." ], "verdict": "The v1 REST API has a published OpenAPI description, Markdown docs, HMAC-signed keys, reader roles and a 90-day audit log, with on-demand GPU prices public. No idempotency keys or control-plane rate limits were found, and serverless models were withdrawn in September and October 2026 on the day they were announced, despite 90-day notice terms.", "bestFor": "Teams that want whole GPU machines or clusters with managed Kubernetes or Slurm in the US, Iceland or Norway, under an SLA, and are content to manage lifecycles themselves.", "strengths": [ "Requests are signed with HMAC-SHA256 over the path, query, verb and timestamp, so the secret key never travels with a request.", "The API description is published for `/v1` and `/v1alpha5`, with 1,231 examples, and the docs serve `llms.txt` and a Markdown twin of each page.", "On-demand prices are public and billed per second. H100 is $3.90, H200 $4.29 and B300 $8.96 a GPU-hour, with no charge for ingress or egress.", "Organisation and project roles include read-only `org-reader` and `project-reader`, and the audit log keeps 90 days of control-plane actions readable through the API.", "The Terms of Service promise 90 days' notice before a service is discontinued or a customer-facing API changes in a backwards-incompatible way." ], "weaknesses": [ "No idempotency key or safe-retry guidance was found for create and delete calls, which return asynchronous operations to poll.", "No request rate limits were found for the infrastructure API. Numbers are published only for Serverless Inference.", "Spot prices and on-demand prices for Vera Rubin, GB300, GB200, B200 and MI355X are contact sales, and provisioning compute needs a non-prepaid credit card.", "Six Serverless Inference models were deprecated on 12 September and 2 October 2026 in entries dated the same day, with no earlier notice found.", "The Service Specific Terms let customers publish benchmark results only with Crusoe's written consent, and the Intelligence Foundry terms bar competitive analysis or benchmarking. Recorded as a fact, and it matters before any probe is run." ], "agentNotes": [ "Sign every request. Build the payload from path, sorted query string, verb and `X-Crusoe-Timestamp`, HMAC-SHA256 it with the base64url-decoded secret, and send `Authorization: Bearer 1.0:\u003caccess_key_id\u003e:\u003csignature\u003e`.", "Use `https://api.cloud.crusoe.ai/v1`. Some docs pages and the MCP server still name `api.crusoecloud.com` and `/v1alpha5`.", "Creates, updates and deletes return an operation. Poll the matching operations endpoint for `state`, and list existing resources by name before retrying a create, because no idempotency key was found.", "Managed AI uses separate Intelligence API keys and hosts, `api.inference.crusoecloud.com` for OpenAI-compatible calls and `api.intelligence.crusoecloud.com` for files and fine-tuning jobs.", "Delete a VM and its disks to stop charges. A stopped on-demand VM is not billed for compute, but its 128 GB OS disk still bills at $0.08 a GiB-month.", "Check Crusoe Updates before pinning a Serverless Inference model. Six models were withdrawn on the day of announcement, so keep a fallback model id ready." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.4 } ], "editorialScores": { "ergonomics": 45, "maintenance": 76, "payments": 30, "reliability": 76, "schema": 79, "security": 74, "transparency": 64 }, "provenanceScore": 90, "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": "brew install crusoecloud/cli/crusoe", "http": "curl https://api.cloud.crusoe.ai/v1/capacities -H \"X-Crusoe-Timestamp: \u003cRFC3339 timestamp\u003e\" -H \"Authorization: Bearer \u003cversion:access_key_id:base64_encoded_signature\u003e\"", "claudeCode": "claude mcp add crusoe-cloud -- npx -y @crusoeai/cloud-mcp", "config": { "mcpServers": { "crusoe-cloud": { "args": [ "-y", "@crusoeai/cloud-mcp" ], "command": "npx" } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/crusoe-cloud" }, "area": "models", "unitPrices": [ { "item": "NVIDIA B300 288 GB HGX, on demand", "unit": "gpu-hour", "usd": 8.96, "note": "Billed per second while running. Spot is contact sales" }, { "item": "NVIDIA H100 80 GB HGX, on demand", "unit": "gpu-hour", "usd": 3.9, "note": "Billed per second while running. Spot is contact sales" }, { "item": "NVIDIA H200 141 GB HGX, on demand", "unit": "gpu-hour", "usd": 4.29 }, { "item": "NVIDIA A100 80 GB SXM, on demand", "unit": "gpu-hour", "usd": 2.3 }, { "item": "NVIDIA A100 80 GB PCIe, on demand", "unit": "gpu-hour", "usd": 2 }, { "item": "NVIDIA L40S 48 GB, on demand", "unit": "gpu-hour", "usd": 1.5 }, { "item": "AMD MI300X 192 GB, on demand", "unit": "gpu-hour", "usd": 3.45 }, { "item": "NVIDIA H100, Self-Serve Deployment", "unit": "gpu-hour", "usd": 5.5, "note": "Dedicated inference endpoint, billed until deleted. H200 $6.00, B200 $9.65, MI355X $7.40" }, { "item": "General-purpose CPU instance", "unit": "vcpu-hour", "usd": 0.04, "note": "Storage-optimised $0.09" }, { "item": "Persistent disk", "unit": "gb-month", "usd": 0.08, "note": "Per GiB. Shared disks $0.07, Object Storage $0.06" } ], "provenance": { "legalEntity": "Crusoe Technologies LLC", "domain": "crusoe.ai", "domainRegistered": "2019-01-28", "endpointOnVendorDomain": true, "terms": "https://legal.crusoe.ai/#terms-of-service", "privacy": "https://legal.crusoe.ai/#cloud-privacy-policy", "statusPage": "https://status.crusoecloud.com", "changelog": "https://docs.crusoecloud.com/updates", "securityTxt": "valid", "checked": "2026-10-09", "notes": [ "The Crusoe Cloud Platform Terms of Service, version 1.10, effective 10 August 2026, are a contract with Crusoe Technologies LLC and its affiliates. Ten earlier versions are kept on the same page.", "legal.crusoe.ai is one page that holds every legal document and its earlier versions, reached by anchor. The terms and privacy links point at the anchors for the platform terms and the Crusoe Cloud Platform Privacy Notice, not at the separate website terms and website privacy notice.", "The Crusoe Cloud Platform Privacy Notice, version 1.3, effective 12 March 2026, covers Service Data only. Customer Data falls under the Data Processing and Security Terms, version 1.3, effective 14 July 2026.", "The API reference gives `https://api.cloud.crusoe.ai/v1`, under the vendor domain. Other docs pages and the MCP server name `api.crusoecloud.com`, and Managed AI answers at `api.inference.crusoecloud.com` and `api.intelligence.crusoecloud.com`. crusoecloud.com was registered on 14 April 2020 per RDAP and redirects to www.crusoe.ai.", "security.txt at www.crusoe.ai gives security@crusoe.ai and expires on 1 March 2027. It has no Policy field.", "RDAP for crusoe.ai gives a registration date of 2019-01-28. The website footer reads Crusoe, Inc, and the licence files in the CLI and Go client repositories name Crusoe Energy Systems LLC." ], "score": 90 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/crusoe-cloud.json", "live": { "slug": "crusoe-cloud", "probe": { "target": "https://api.cloud.crusoe.ai/v1", "method": "get", "lastAt": "2026-11-07T18:20:19.457357942Z", "lastOk": true, "lastStatus": 200, "lastMs": 230, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 178, "p95ms24h": 273, "samples24h": 239, "samples30d": 7205, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 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.crusoecloud.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:20:59.921798277Z" }, "versions": [ { "registry": "npm", "name": "@crusoeai/cloud-mcp", "version": "0.1.6", "seenAt": "2026-11-06T23:18:42.185227268Z" } ], "githubStars": 4, "npmWeekly": 27, "securityTxt": { "url": "https://crusoe.ai/.well-known/security.txt", "state": "valid", "expires": "2027-03-01T21:00:00.000Z", "checkedAt": "2026-11-07T15:59:35.513641331Z" }, "llmsTxt": { "url": "https://docs.crusoecloud.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:13.809877657Z" }, "domain": { "domain": "crusoe.ai", "registered": "2019-01-28", "source": "https://rdap.identitydigital.services/rdap/domain/crusoe.ai", "checkedAt": "2026-11-01T14:18:14.102667117Z" }, "pages": [ { "url": "https://docs.crusoecloud.com/updates", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:05:59.977059308Z", "changedAt": "2026-11-07T14:05:59.977059308Z", "fingerprint": "37c27a1a3149" }, { "url": "https://docs.crusoe.ai/updates/index.html", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:05:59.878902129Z", "changedAt": "2026-11-07T14:05:59.878902129Z", "fingerprint": "37c27a1a3149" }, { "url": "https://www.crusoe.ai/cloud/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:27:38.401408348Z", "changedAt": "2026-11-07T14:27:38.401408348Z", "fingerprint": "a91c21f49d79" }, { "url": "https://legal.crusoe.ai/", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:12:51.725212267Z", "changedAt": "2026-11-06T13:34:52.347341362Z", "fingerprint": "963ee7400752" } ], "github": { "repo": "crusoecloud/client-go", "checkedAt": "2026-11-02T08:42:22.247028438Z", "stars": 4, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T21:19:26Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0 }, "updatedAt": "2026-11-07T18:20:19.457357942Z" } }, "edges": [ { "by": 21, "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": "Lists take `limit` or `page_size` on 16 of about 104 list calls, and VM lists filter by id, name, type, location and state; no field selection (12 of 25). Token pagination with next and previous tokens and a `sort` parameter where present; most lists return everything (12). Errors are an HTTP status with `code` and `message`, and long-running calls return an operation with `state` and `result` to poll; no documented list of error codes (10). No idempotency key or safe-retry guidance found; the preview MCP server has read tools only, and its annotations were not read (4). VM create needs a name, type, location and SSH key and installs a monitoring agent by default; the Go client is the only official SDK found, beside a CLI and a Terraform provider, and other languages must code the request signature (7)." }, "scores": { "a": 66, "b": 45 } }, { "by": 10, "category": "payments", "leads": "crusoe-cloud", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-second GPU, CPU and memory prices published without a login (20). The Cloud Run free tier covers CPU and memory, not GPUs, and the $300 trial credit needs a payment method (0). A person creates the project and billing account in a browser (0). 0+20+0+0 = 20.", "b": "No machine payment protocol (0). Per-GPU-hour, per-vCPU-hour, per-GiB and per-token prices published without a login, though spot prices and on-demand prices for GB200, B200 and MI355X are contact sales (20). $5 of introductory credits cover Serverless Inference and Serverless Fine-Tuning without a payment method; GPU machines, the product graded here, need a non-prepaid credit card (10 of 20). Signup is a browser flow with Google, GitHub or an emailed code, and the first key is made in the console (0)." }, "scores": { "a": 20, "b": 30 } }, { "by": 7, "category": "transparency", "leads": "cloud-run-gpus", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15). The Cloud Data Processing Addendum and the privacy notice cover customer data, per the Document AI listing's 1 November reading; no Cloud Run statement on GPU instance data after shutdown was found (22). The Cloud terms promise 12 months' notice before a backwards-incompatible API change, and driver versions are announced in the release notes (16). Regions per GPU type listed, with Google's subprocessor list and data-location terms (16). 15+22+16+16 = 69.", "b": "Closed service under Terms of Service version 1.10, effective 10 August 2026, with ten earlier versions kept on the legal page; the Go client and MCP package are MIT (15). The Privacy Notice (version 1.3, 12 March 2026) covers Service Data and the Data Processing and Security Terms (version 1.3, 14 July 2026) cover Customer Data, with deletion on instruction and at the end of the term, and the Intelligence Foundry terms say inputs, outputs and training data are not used to train models without opt-in consent; no retention periods are given in numbers (22). The terms promise 90 days' notice before discontinuing a service or changing a customer-facing API incompatibly, and a deprecation page gives dates such as 8 November 2026 for old CSI drivers, announced 15 September; model deprecations are logged on the day they take effect, six models on 12 September and 2 October 2026 (17). Seven data centre zones are published; the data processing terms point to a sub-processor list that was not found in the pages read (10)." }, "scores": { "a": 84, "b": 77 } }, { "by": 6, "category": "reliability", "leads": "crusoe-cloud", "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 on the REST API. Statuspage at status.crusoecloud.com with components per region and service (20). From 4 August to 2 November 2026 the history shows five incidents, each limited to one region or a subset of resources, so all read as partial. They were VM and Kubernetes cluster creation in us-east2 for about 7.5 hours (2 September, minor), network errors in us-east1 (3 September, no stated impact), a subset of VMs showing as UNSPECIFIED in us-east2 (9 September, no stated impact), Shared Storage, Object Storage and the container registry unreachable in eu-norway1 for about 3 hours 54 minutes (29 September, labelled critical) and a facility issue that powered off a subset of compute instances in us-east2-a from 15 to 18 October (labelled critical). Scheduled maintenance isn't counted. Minor incidents only (20). Rate limits carry numbers only for Serverless Inference (500,000 tokens and 30 requests a minute per model without a payment method, 2,000,000 and 600 with one); none were found for the infrastructure API, whose MCP server throttles itself to 60 requests a minute (8 of 15). Serverless Inference documents 429 and 503 with exponential backoff and `x-ratelimit-*` headers; no Retry-After, no idempotency keys and no retry guidance for infrastructure writes were found (8 of 15). SLA version 8.0 (21 July 2026) of 99.5 per cent a month per GPU virtual machine and per persistent or shared disk, with credits of 10, 25 or 100 per cent (10). The v1 API is labelled Latest and the services graded are generally available; the MCP server is in preview (10)." }, "scores": { "a": 70, "b": 76 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Crusoe", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://api.cloud.crusoe.ai/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, stdio", "name": "Transports" }, { "a": "OAuth", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0", "b": "Proprietary service under the Crusoe Cloud Platform Terms of Service. The Go client and the MCP server package are MIT. The CLI ships as binaries, and no licence file was found in the Terraform provider repository", "name": "Licence" }, { "a": "none", "b": "41", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-27", "name": "Last release" }, { "a": "2026-09-02", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "7 npm/wk", "name": "Popularity" }, { "a": "none", "b": "3.3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Crusoe Cloud's 62.4 (B), and leads in 5 of 7 scored categories. Crusoe Cloud leads on reliability and payments \u0026 pricing.", "question": "Which is better for AI agents, Cloud Run GPUs or Crusoe Cloud?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Crusoe Cloud at https://api.cloud.crusoe.ai/v1.", "question": "Can an agent call Cloud Run GPUs and Crusoe Cloud without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 66 against 45", "Transparency \u0026 trust, 84 against 77" ], "also": [ "No incidents deducted, where Crusoe Cloud 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": [ "Reliability, 76 against 70", "Payments \u0026 pricing, 30 against 20" ], "also": [ "Runs on your own machine" ], "goodFor": "Teams that want whole GPU machines or clusters with managed Kubernetes or Slurm in the US, Iceland or Norway, under an SLA, and are content to manage lifecycles themselves.", "slug": "crusoe-cloud", "watchFor": "No idempotency key or safe-retry guidance was found for create and delete calls, which return asynchronous operations to poll." } ], "history": { "cloud-run-gpus": null, "crusoe-cloud": [ { "causes": [ "correction", "event" ], "date": "2026-11-02", "delta": -1, "from": 63.4, "fromGrade": "B", "to": 62.4, "toGrade": "B" } ] }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.json", "title": "Baseten vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-crusoe-cloud.json", "title": "Baseten vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/baseten-vs-crusoe-cloud" }, { "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-crusoe-cloud.json", "title": "Beam vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/beam-vs-crusoe-cloud" }, { "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-crusoe-cloud.json", "title": "Cerebrium vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-crusoe-cloud" }, { "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-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-crusoe-cloud.json", "title": "CoreWeave vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/coreweave-vs-crusoe-cloud" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-gpusmarket.json", "title": "Crusoe Cloud vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-gpusmarket" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-hugging-face-inference-endpoints.json", "title": "Crusoe Cloud vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-hyperbolic.json", "title": "Crusoe Cloud vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-hyperbolic" }, { "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/crusoe-cloud-vs-lambda.json", "title": "Crusoe Cloud vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-massed-compute.json", "title": "Crusoe Cloud vs Massed Compute", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-modal.json", "title": "Crusoe Cloud vs Modal", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-nebius-ai-cloud.json", "title": "Crusoe Cloud vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-northflank.json", "title": "Crusoe Cloud vs Northflank", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.json", "title": "Crusoe Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod.json", "title": "Crusoe Cloud vs Runpod", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-thunder-compute.json", "title": "Crusoe Cloud vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.json", "title": "Crusoe Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters" }, { "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/crusoe-cloud-vs-verda.json", "title": "Crusoe Cloud vs Verda", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.json", "title": "Cloud Run GPUs vs Koyeb", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.json", "title": "Cloud Run GPUs vs Modal", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.json", "title": "Cloud Run GPUs vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.json", "title": "Cloud Run GPUs vs Runpod", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.json", "title": "Cloud Run GPUs vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.json", "title": "Cloud Run GPUs vs Verda", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda" } ], "panel": null, "scores": [ { "by": 6, "cloud-run-gpus": 70, "crusoe-cloud": 76, "edge": "crusoe-cloud", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 2, "cloud-run-gpus": 81, "crusoe-cloud": 79, "edge": "cloud-run-gpus", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 21, "cloud-run-gpus": 66, "crusoe-cloud": 45, "edge": "cloud-run-gpus", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 4, "cloud-run-gpus": 78, "crusoe-cloud": 74, "edge": "cloud-run-gpus", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "cloud-run-gpus": 20, "crusoe-cloud": 30, "edge": "crusoe-cloud", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 4, "cloud-run-gpus": 80, "crusoe-cloud": 76, "edge": "cloud-run-gpus", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 7, "cloud-run-gpus": 84, "crusoe-cloud": 77, "edge": "cloud-run-gpus", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Crusoe Cloud's 62.4 (B), and leads in 5 of 7 scored categories. Crusoe Cloud leads on reliability and payments \u0026 pricing. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "cloud-run-gpus": "Serverless GPUs on Cloud Run, an L4 or RTX PRO 6000 per instance, billed per second, scaling to zero and starting in about 5 seconds before the model loads, with a published SLA and IAM. One GPU per instance, 3 GPUs of default quota a region and instance-based billing limit it to small and mid-size models.", "crusoe-cloud": "The v1 REST API has a published OpenAPI description, Markdown docs, HMAC-signed keys, reader roles and a 90-day audit log, with on-demand GPU prices public. No idempotency keys or control-plane rate limits were found, and serverless models were withdrawn in September and October 2026 on the day they were announced, despite 90-day notice terms." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Crusoe Cloud's 62.4 (B), and leads in 5 of 7 scored categories. Crusoe Cloud leads on reliability and payments \u0026 pricing. Both do gpu compute.\n\n- Cloud Run GPUs: grade B, 68.4/100, rank #288 of 1486. Markdown https://www.anchorterminal.com/tools/cloud-run-gpus.md · JSON https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json\n- Crusoe Cloud: grade B, 62.4/100, rank #555 of 1486. Markdown https://www.anchorterminal.com/tools/crusoe-cloud.md · JSON https://www.anchorterminal.com/api/v1/tools/crusoe-cloud.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- Agent ergonomics, 66 against 45\n- Transparency \u0026 trust, 84 against 77\n\nAlso in its favour:\n- No incidents deducted, where Crusoe Cloud 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### Crusoe Cloud (B)\n\nGood for: Teams that want whole GPU machines or clusters with managed Kubernetes or Slurm in the US, Iceland or Norway, under an SLA, and are content to manage lifecycles themselves.\n\nAhead on:\n- Reliability, 76 against 70\n- Payments \u0026 pricing, 30 against 20\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: No idempotency key or safe-retry guidance was found for create and delete calls, which return asynchronous operations to poll.\n\n\n## Why the edge\n\n### Agent ergonomics: Cloud Run GPUs +21\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- Crusoe Cloud (45): Lists take `limit` or `page_size` on 16 of about 104 list calls, and VM lists filter by id, name, type, location and state; no field selection (12 of 25). Token pagination with next and previous tokens and a `sort` parameter where present; most lists return everything (12). Errors are an HTTP status with `code` and `message`, and long-running calls return an operation with `state` and `result` to poll; no documented list of error codes (10). No idempotency key or safe-retry guidance found; the preview MCP server has read tools only, and its annotations were not read (4). VM create needs a name, type, location and SSH key and installs a monitoring agent by default; the Go client is the only official SDK found, beside a CLI and a Terraform provider, and other languages must code the request signature (7).\n\n### Payments \u0026 pricing: Crusoe Cloud +10\n\n- Cloud Run GPUs (20): No x402, MPP or L402 (0). Per-second GPU, CPU and memory prices published without a login (20). The Cloud Run free tier covers CPU and memory, not GPUs, and the $300 trial credit needs a payment method (0). A person creates the project and billing account in a browser (0). 0+20+0+0 = 20.\n- Crusoe Cloud (30): No machine payment protocol (0). Per-GPU-hour, per-vCPU-hour, per-GiB and per-token prices published without a login, though spot prices and on-demand prices for GB200, B200 and MI355X are contact sales (20). $5 of introductory credits cover Serverless Inference and Serverless Fine-Tuning without a payment method; GPU machines, the product graded here, need a non-prepaid credit card (10 of 20). Signup is a browser flow with Google, GitHub or an emailed code, and the first key is made in the console (0).\n\n### Transparency \u0026 trust: Cloud Run GPUs +7\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- Crusoe Cloud (77): Closed service under Terms of Service version 1.10, effective 10 August 2026, with ten earlier versions kept on the legal page; the Go client and MCP package are MIT (15). The Privacy Notice (version 1.3, 12 March 2026) covers Service Data and the Data Processing and Security Terms (version 1.3, 14 July 2026) cover Customer Data, with deletion on instruction and at the end of the term, and the Intelligence Foundry terms say inputs, outputs and training data are not used to train models without opt-in consent; no retention periods are given in numbers (22). The terms promise 90 days' notice before discontinuing a service or changing a customer-facing API incompatibly, and a deprecation page gives dates such as 8 November 2026 for old CSI drivers, announced 15 September; model deprecations are logged on the day they take effect, six models on 12 September and 2 October 2026 (17). Seven data centre zones are published; the data processing terms point to a sub-processor list that was not found in the pages read (10).\n\n### Reliability: Crusoe Cloud +6\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- Crusoe Cloud (76): Graded as a hosted service on the REST API. Statuspage at status.crusoecloud.com with components per region and service (20). From 4 August to 2 November 2026 the history shows five incidents, each limited to one region or a subset of resources, so all read as partial. They were VM and Kubernetes cluster creation in us-east2 for about 7.5 hours (2 September, minor), network errors in us-east1 (3 September, no stated impact), a subset of VMs showing as UNSPECIFIED in us-east2 (9 September, no stated impact), Shared Storage, Object Storage and the container registry unreachable in eu-norway1 for about 3 hours 54 minutes (29 September, labelled critical) and a facility issue that powered off a subset of compute instances in us-east2-a from 15 to 18 October (labelled critical). Scheduled maintenance isn't counted. Minor incidents only (20). Rate limits carry numbers only for Serverless Inference (500,000 tokens and 30 requests a minute per model without a payment method, 2,000,000 and 600 with one); none were found for the infrastructure API, whose MCP server throttles itself to 60 requests a minute (8 of 15). Serverless Inference documents 429 and 503 with exponential backoff and `x-ratelimit-*` headers; no Retry-After, no idempotency keys and no retry guidance for infrastructure writes were found (8 of 15). SLA version 8.0 (21 July 2026) of 99.5 per cent a month per GPU virtual machine and per persistent or shared disk, with credits of 10, 25 or 100 per cent (10). The v1 API is labelled Latest and the services graded are generally available; the MCP server is in preview (10).\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Crusoe Cloud | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 76 | Crusoe Cloud +6 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 79 | Cloud Run GPUs +2 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 45 | Cloud Run GPUs +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 74 | Cloud Run GPUs +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 30 | Crusoe Cloud +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 76 | Cloud Run GPUs +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 77 | Cloud Run GPUs +7 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **68.4 · B** | **62.4 · B** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Crusoe Cloud |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Crusoe |\n| Hosted endpoint | `https://run.googleapis.com` | `https://api.cloud.crusoe.ai/v1` |\n| Transports | | HTTP, stdio |\n| Auth | OAuth | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | Proprietary service under the Crusoe Cloud Platform Terms of Service. The Go client and the MCP server package are MIT. The CLI ships as binaries, and no licence file was found in the Terraform provider repository |\n| Tools exposed | none | 41 |\n| Read-only variant documented | no | yes |\n| llms.txt | no | yes |\n| Last release | 2026-10-30 | 2026-10-27 |\n| Terms last updated | 2026-09-02 | couldn't be read |\n| Privacy policy last updated | 2026-09-28 | couldn't be read |\n| Customer content may train models | not found in the text | couldn't be read |\n| Terms restrict automated access | not found in the text | couldn't be read |\n| Terms restrict benchmarking | not found in the text | couldn't be read |\n| Terms or service can change without notice | not found in the text | couldn't be read |\n| Arbitration or class-action waiver | not found in the text | couldn't be read |\n| Popularity | none | 7 npm/wk |\n| Agent reviews | none | 3.3/5 (4) |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Crusoe Cloud\n\n- -1.0 on 2 November 2026: correction, negative event\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**Crusoe Cloud.** The v1 REST API has a published OpenAPI description, Markdown docs, HMAC-signed keys, reader roles and a 90-day audit log, with on-demand GPU prices public. No idempotency keys or control-plane rate limits were found, and serverless models were withdrawn in September and October 2026 on the day they were announced, despite 90-day notice terms.\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### Crusoe Cloud\n\n1. Sign every request. Build the payload from path, sorted query string, verb and `X-Crusoe-Timestamp`, HMAC-SHA256 it with the base64url-decoded secret, and send `Authorization: Bearer 1.0:\u003caccess_key_id\u003e:\u003csignature\u003e`.\n2. Use `https://api.cloud.crusoe.ai/v1`. Some docs pages and the MCP server still name `api.crusoecloud.com` and `/v1alpha5`.\n3. Creates, updates and deletes return an operation. Poll the matching operations endpoint for `state`, and list existing resources by name before retrying a create, because no idempotency key was found.\n4. Managed AI uses separate Intelligence API keys and hosts, `api.inference.crusoecloud.com` for OpenAI-compatible calls and `api.intelligence.crusoecloud.com` for files and fine-tuning jobs.\n5. Delete a VM and its disks to stop charges. A stopped on-demand VM is not billed for compute, but its 128 GB OS disk still bills at $0.08 a GiB-month.\n6. Check Crusoe Updates before pinning a Serverless Inference model. Six models were withdrawn on the day of announcement, so keep a fallback model id ready.\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Crusoe Cloud?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Crusoe Cloud's 62.4 (B), and leads in 5 of 7 scored categories. Crusoe Cloud leads on reliability and payments \u0026 pricing.\n\n### Can an agent call Cloud Run GPUs and Crusoe Cloud without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Crusoe Cloud at https://api.cloud.crusoe.ai/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"crusoe-cloud\"}`. From a terminal: `anchor compare cloud-run-gpus crusoe-cloud`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/crusoe-cloud.json\n\n## Other comparisons with Cloud Run GPUs or Crusoe Cloud\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Crusoe Cloud](https://www.anchorterminal.com/compare/baseten-vs-crusoe-cloud.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Crusoe Cloud](https://www.anchorterminal.com/compare/beam-vs-crusoe-cloud.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Crusoe Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-crusoe-cloud.md)\n- [Cloud Run GPUs vs CoreWeave](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.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 Crusoe Cloud](https://www.anchorterminal.com/compare/coreweave-vs-crusoe-cloud.md)\n- [Crusoe Cloud vs GPUsMarket](https://www.anchorterminal.com/compare/crusoe-cloud-vs-gpusmarket.md)\n- [Crusoe Cloud vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/crusoe-cloud-vs-hugging-face-inference-endpoints.md)\n- [Crusoe Cloud vs Hyperbolic](https://www.anchorterminal.com/compare/crusoe-cloud-vs-hyperbolic.md)\n- [Crusoe Cloud vs Koyeb](https://www.anchorterminal.com/compare/crusoe-cloud-vs-koyeb.md)\n- [Crusoe Cloud vs Lambda Cloud](https://www.anchorterminal.com/compare/crusoe-cloud-vs-lambda.md)\n- [Crusoe Cloud vs Massed Compute](https://www.anchorterminal.com/compare/crusoe-cloud-vs-massed-compute.md)\n- [Crusoe Cloud vs Modal](https://www.anchorterminal.com/compare/crusoe-cloud-vs-modal.md)\n- [Crusoe Cloud vs Nebius AI Cloud](https://www.anchorterminal.com/compare/crusoe-cloud-vs-nebius-ai-cloud.md)\n- [Crusoe Cloud vs Northflank](https://www.anchorterminal.com/compare/crusoe-cloud-vs-northflank.md)\n- [Crusoe Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.md)\n- [Crusoe Cloud vs Runpod](https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod.md)\n- [Crusoe Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/crusoe-cloud-vs-thunder-compute.md)\n- [Crusoe Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.md)\n- [Crusoe Cloud vs Vast.ai](https://www.anchorterminal.com/compare/crusoe-cloud-vs-vast-ai.md)\n- [Crusoe Cloud vs Verda](https://www.anchorterminal.com/compare/crusoe-cloud-vs-verda.md)\n- [Cloud Run GPUs vs Koyeb](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md)\n- [Cloud Run GPUs vs Modal](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.md)\n- [Cloud Run GPUs vs Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md)\n- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md)\n- [Cloud Run GPUs vs Vast.ai](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.md)\n- [Cloud Run GPUs vs Verda](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cloud Run GPUs vs Crusoe Cloud", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Crusoe Cloud's 62.4 (B) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Crusoe Cloud B 62.4", "scores" ], "h1": "Cloud Run GPUs vs Crusoe Cloud", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-crusoe-cloud", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Crusoe Cloud for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud" }, "tokens": { "markdown": 4700, "slim": 2430 }, "version": 1 }