{ "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 Hyperbolic's 38.7 (E), and leads in every scored category.", "b": { "slug": "hyperbolic", "name": "Hyperbolic", "vendor": "Hyperbolic Labs, Inc.", "vendorUrl": "https://www.hyperbolic.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Hyperbolic is a GPU cloud from Hyperbolic Labs that rents H100, H200 and B200 virtual machines and bare-metal nodes by the hour, with reserved terms and private clusters. Agents use its REST API with an API key.", "url": "https://www.anchorterminal.com/tools/hyperbolic", "markdownUrl": "https://www.anchorterminal.com/tools/hyperbolic.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hyperbolic.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hyperbolic.json", "dns": "hyperbolic.grade.anchorterminal.com", "license": "Proprietary service under Hyperbolic's Terms of Service. The unmaintained hyperbolic-mcp repository on GitHub is MIT", "transports": [ "http" ], "remoteUrl": "https://api.hyperbolic.ai", "packages": [], "auth": "api-key", "authNotes": "Self-serve. A signed-in user creates an API key in the console's settings, and the secret is shown once. Requests send it as `Authorization: Bearer \u003capi-key\u003e`. An account can hold any number of keys and revoke any of them. Keys created inside an Organisation belong to it and are attributed to the member who made them. Members revoke their own keys and admins revoke any. No scopes, read-only keys or expiry were found in the reviewed documentation.", "pricing": "usage", "pricingNotes": "Prepaid credits, minimum purchase $5 through Stripe, 1 to 1 with dollars and with no expiry. A new account is on the free tier and cannot rent GPUs or storage until it has deposited $5 once. No trial was found, apart from credit codes handed out at events. On-demand rentals bill hourly from the moment an instance is ready, and the balance must cover one hour of all running instances. On 8 October 2026 the marketplace page gave a starting price of $3.19 a GPU-hour. Reserved terms of 7, 14 and 30 days take 1, 3 and 5 per cent off and are paid up front. Private Cloud is by contract (https://www.hyperbolic.ai/docs/on-demand/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs corpus or the OpenAPI document for the GPU API. The archived HyperbolicLabs/hyperbolic-x402 repository covered chat completions on a separate host, not GPU rentals (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://www.hyperbolic.ai/docs/overview/overview", "llmsTxt": "https://www.hyperbolic.ai/docs/llms.txt", "openapi": "https://api.hyperbolic.ai/v2/openapi.json", "capabilities": [ "compute.gpu" ], "tags": [ "hosted", "usage-priced", "openapi", "llms-txt", "api-key", "bare-metal", "status-page", "prepaid" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 38.7, "grade": "E", "agentReady": false, "rank": 1335, "ranked": true, "rankOf": 1486, "categoryRank": 22, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 39, "payments": 15, "reliability": 25, "schema": 52, "security": 48, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -3, "negativeNotes": [ "2026-10-05, removing the `roles` list from the `GET /v2/users/me` response and changing timestamps to RFC 3339 on the v2 API. Both are recorded in the changelog entry for the week they shipped, and no advance notice was found. Documented, so 3 points (https://www.hyperbolic.ai/docs/changelog)." ], "verdict": "Hyperbolic's docs carry llms.txt, Markdown pages and a dated 1 March 2027 end for legacy paths, and billing starts only once an instance is ready. API keys carry no scopes and can delete the account, rental creation has no idempotency key, no 429 guidance is documented, and renting needs a browser signup and a $5 deposit.", "bestFor": "Agents that rent whole H100, H200 or B200 machines or multi-node clusters for training and batch work and that have a funded account.", "strengths": [ "Deprecated paths answer with a `Sunset` header and a stated end date of 1 March 2027, and each names its replacement", "Docs index at `/docs/llms.txt`, every page as Markdown and the whole corpus in `llms-full.txt` (188 KB)", "Billing starts only when an instance is ready, and instances that fail to provision within about 3 hours are not charged, per the pricing docs", "The security page asks for vulnerability reports by email and states a 48-hour acknowledgement", "A rental needs only `rentalType` and `gpuCount`, with defaults for region, GPU type and SSH key" ], "weaknesses": [ "API keys carry no scopes or expiry in the reviewed documentation, and the same key can call `DELETE /v2/users/me`", "`POST /v2/on-demand/rentals` has no idempotency key, so a retried call can start a second billed rental", "No 429 response, `Retry-After` header or backoff guidance was found in the docs", "A free-tier account cannot rent GPUs or storage. Renting needs a one-time deposit of at least $5 through Stripe", "The Terms of Service describe a marketplace in which uptime is between buyer and supplier, while the docs state a 99.5 per cent uptime SLA", "No official SDK or CLI for the v2 API was found. The vendor's MCP repository last changed in May 2025 and calls the legacy v1 marketplace paths" ], "agentNotes": [ "Check current GPU configurations and hourly prices before renting. The docs point to the console for rates, and the marketplace page gave $3.19 a GPU-hour on 8 October 2026.", "Send `rentalType` and `gpuCount` to `POST /v2/on-demand/rentals`. Region defaults to `us-central-1` and GPU type to `h100`, so set both from the options list.", "List active rentals before retrying a failed create call. There is no idempotency key and every ready rental bills hourly.", "Save an SSH public key with `POST /v2/ssh-keys` before renting. Without `sshPublicKeyIds` the newest saved key is attached.", "Do not create reserved rentals unless asked. They are paid in full up front and cannot be terminated early." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 38.7 } ], "editorialScores": { "ergonomics": 55, "maintenance": 39, "payments": 15, "reliability": 25, "schema": 52, "security": 48, "transparency": 45 }, "provenanceScore": 82, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST https://api.hyperbolic.ai/v2/ssh-keys -H \"Authorization: Bearer $HYPERBOLIC_API_KEY\" -H \"Content-Type: application/json\" -d \"{\\\"publicKey\\\": \\\"$(cat ~/.ssh/id_ed25519.pub)\\\", \\\"name\\\": \\\"Work laptop\\\"}\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/hyperbolic" }, "area": "models", "unitPrices": [ { "item": "H100 SXM5 80 GB virtual machine, on-demand", "unit": "gpu-hour", "usd": 3.19, "note": "Starting price on the marketplace page on 8 October 2026. Reserved terms take 1 to 5 per cent off" } ], "provenance": { "legalEntity": "Hyperbolic Labs, Inc.", "domain": "hyperbolic.ai", "domainRegistered": "2021-10-11", "endpointOnVendorDomain": true, "terms": "https://www.hyperbolic.ai/terms", "privacy": "https://www.hyperbolic.ai/privacy", "statusPage": "https://status.hyperbolic.ai", "changelog": "https://www.hyperbolic.ai/docs/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Terms of Service, last updated 24 March 2025, name Hyperbolic Labs, Inc. as owner and operator of the platform, apply California law and set AAA arbitration. They cover the website and all services, and no separate API or cloud agreement was found.", "The Privacy Policy is effective 3 June 2024 and names Hyperbolic Labs, Inc. One clause on business transfers names Babylon three times where the company's own name would be expected.", "The API answers at api.hyperbolic.ai, a subdomain of the vendor domain, and on the legacy host api.hyperbolic.xyz.", "https://www.hyperbolic.ai/.well-known/security.txt answered 404. The docs ask for vulnerability reports by email to support@hyperbolic.ai.", "RDAP for hyperbolic.ai gives a registration date of 2021-10-11." ], "score": 82 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hyperbolic.json", "live": { "slug": "hyperbolic", "probe": { "target": "https://api.hyperbolic.ai", "method": "get", "lastAt": "2026-11-07T18:20:31.396131453Z", "lastOk": true, "lastStatus": 200, "lastMs": 606, "authRequired": false, "uptime24h": 100, "uptime30d": 99.99, "p50ms24h": 548, "p95ms24h": 663, "samples24h": 239, "samples30d": 7289, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 169 }, { "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": 249 }, { "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.hyperbolic.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:55.787305505Z" }, "securityTxt": { "url": "https://hyperbolic.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:48.055957691Z" }, "llmsTxt": { "url": "https://www.hyperbolic.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:43.902264652Z" }, "domain": { "domain": "hyperbolic.ai", "registered": "2021-10-11", "source": "https://rdap.identitydigital.services/rdap/domain/hyperbolic.ai", "checkedAt": "2026-11-01T14:21:49.876675266Z" }, "pages": [ { "url": "https://www.hyperbolic.ai/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:29:58.147501999Z", "changedAt": "2026-11-06T13:50:40.528326876Z", "fingerprint": "1a10dd67c657" }, { "url": "https://www.hyperbolic.ai/docs/on-demand/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:30:00.509963551Z", "changedAt": "2026-11-06T13:50:42.957918679Z", "fingerprint": "42de0112476b" }, { "url": "https://www.hyperbolic.ai/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:30:02.429568985Z", "changedAt": "2026-11-06T13:50:44.72967179Z", "fingerprint": "c7a0abc04871" }, { "url": "https://www.hyperbolic.ai/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:30:04.1682072Z", "changedAt": "2026-11-06T13:50:46.96264626Z", "fingerprint": "08db2ae53bbf" } ], "updatedAt": "2026-11-07T18:20:31.396131453Z" } }, "edges": [ { "by": 45, "category": "reliability", "leads": "cloud-run-gpus", "name": "Reliability", "reasons": { "a": "Hosted reading. Google Cloud's status page with a JSON incident feed (20). In the 90 days from 8 August 2026 the feed names Cloud Run in three multi-product incidents, a service outage on 20 August (15:40 to 19:20 UTC, 27 products, global and us-west1), a network degradation in us-central1-b on 1 September and a europe-west2 disruption on 20 October. One major (10). Resource limits and GPU quota are published with numbers (3 GPUs a region by default), but no request rate for the Admin API was found on the quotas page (10). Google's client libraries retry with backoff and the Admin API takes etags, while no GPU-specific retry guidance was found (10). An SLA for GPU services, 99.95% with zonal redundancy and 99.5% without (10). GPU services generally available since 7 April 2025 (10). 20+10+10+10+10+10 = 70.", "b": "Graded on the hosted lines for the REST API. Hyperbolic's Terms of Service (24 March 2025) bar spiders, robots and scrapers from downloading data from any web page in the Services, which cover the website, so hyperbolic.ai pages and the status page keep their 8 October readings, not re-read on 4 November 2026. Status page at status.hyperbolic.ai on UptimeRobot. The page draws its monitors and history by script from `/api/`, a path its robots.txt closes, so no component was ever read, and a status-page line with no readable component scores 0, as for fonoa, n8n and windmill (was 20). The incident record was never read either (5, unreadable history). Rate limits appear as numbers only on the plan cards in the docs, 60 requests a minute on the free tier and 600 on the pro tier, and the terms let Hyperbolic change limits without notice (10 of 15). No 429 response, `Retry-After` or backoff guidance in the docs, and no idempotency key on rental creation (0). SLA 7 to 0. The docs state a 99.5 per cent uptime figure for On-Demand and Reserved with credits reviewed case by case, and the Terms of Service disclaim uptime and any duty to give credits. A figure with discretionary credits and no SLA document isn't an SLA (manatal). The v2 API is not marked beta (10). 0 + 5 + 10 + 0 + 0 + 10 = 25." }, "scores": { "a": 70, "b": 25 } }, { "by": 41, "category": "maintenance", "leads": "cloud-run-gpus", "name": "Maintenance \u0026 community", "reasons": { "a": "Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026. The newest changelog entry is for the week of 5 October 2026, 30 days before today (30); it drops to 20 after 4 November unless a newer entry appears. It was the only dated entry on the changelog and its RSS feed, so the three-entry test is not met (0 of 20). A public changelog with RSS, in-app chat and email support with stated hours of Monday to Friday, 06:00 to 17:00 Pacific Time (9 of 15). No current official SDK for the v2 API. The vendor's MCP repository still ends at its 21 May 2025 commit (clone, 4 November) and targets legacy v1 paths (0 of 15). Package health 3 to 0. The partial rested on the spec served by the API, a struck reading, and there is no client package to assess. 30 + 0 + 9 + 0 + 0 = 39." }, "scores": { "a": 80, "b": 39 } }, { "by": 30, "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": "Readings are per the 8 October check, not re-read on 4 November 2026. Plain API keys sent as a Bearer header, shown once, revocable, any number per account, and attributed to their creator inside an Organisation. No scopes or expiry found, and no secret in a URL (20 of 30). No read-only key and no confirmation step. A key can rent and terminate machines and can call `DELETE /v2/users/me`. Organisation members cannot deposit funds or see billing history (4 of 20). Responses are infrastructure metadata (10). Key lists show each key's creator and revocation time, and rental and transaction histories exist. No audit log was found for self-serve accounts (4 of 15). Programme 9 to 10. The docs ask for vulnerability reports by email with a 48-hour acknowledgement and claim a completed SOC 2 Type I audit with Type II under way, reports under NDA. A disclosure route with a stated acknowledgement time is 10; no security.txt or bug bounty, and the trust centre is drawn by script. 20 + 4 + 10 + 4 + 10 = 48." }, "scores": { "a": 78, "b": 48 } }, { "by": 29, "category": "schema", "leads": "cloud-run-gpus", "name": "Schema \u0026 documentation", "reasons": { "a": "API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026. Contract line 25 to 0. The OpenAPI document was read from the API host (api.hyperbolic.ai/v2/openapi.json, the product's own endpoint) and from a copy under /docs/api-reference/ with no recorded docs page that shows or links it. The first reading is struck, and a contract on a now-paused host with no recorded visible link is struck too (jambonz, stable-audio). `llms.txt`, every docs page as Markdown and a 188 KB `llms-full.txt` (10). Of the 34 current operations, 17 have a description that only repeats the summary. The rest state behaviour, limits and named error cases, and every deprecated operation names its replacement (10 of 20). Required fields, 89 enums, numeric bounds and a `oneOf` for new or existing storage volumes, but rental IDs accept an integer or a string (12 of 15). Five error schemas with examples and 400, 401, 403 and 500 on every operation. No request body has an example and no 429 is listed (8 of 15). Versioned in the path with a dated changelog and RSS feed, which held one entry (12 of 15). 0 + 10 + 10 + 12 + 8 + 12 = 52." }, "scores": { "a": 81, "b": 52 } }, { "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": "Readings are per the 8 October check, not re-read on 4 November 2026, apart from the Terms of Service, re-read and unchanged (24 March 2025). Closed service under California law. The terms describe a marketplace in which the contract for compute is between buyer and supplier, which does not match the docs' description of a GPU cloud with an SLA (13 of 30). The Privacy Policy is effective 3 June 2024, gives no retention periods and names Babylon three times in one clause. The terms say user content is not used to train generative models. The docs promise data wiping on termination, a 30-day grace period for volumes and a DPA on request, and no published DPA was found (12 of 30). No written deprecation policy, but legacy paths carry a `Sunset` header with an end date of 1 March 2027 and each deprecated operation names its replacement (14 of 20). Stripe is named as payment processor. The suppliers that host the machines are not named, and the trust centre's sub-processor list, if any, was unreadable (6 of 20). 13 + 12 + 14 + 6 = 45." }, "scores": { "a": 84, "b": 64 } }, { "by": 11, "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": "Readings are per the 8 October check, not re-read on 4 November 2026. No field selection. Lists page at 25 by default and 100 at most, and `GET /v2/on-demand/active-rental-summary` returns counts and hourly cost without the rental bodies (13 of 25). `page` and `pageSize` on active rentals, a cursor on history, and filters for GPU type, region and term type. Storage volumes and SSH keys return whole arrays (15 of 20). Errors carry `code`, `message` and `issues`, with named cases such as INVALID_INPUT_FOR_RENTAL_TYPE and REBOOT_ALREADY_IN_PROGRESS (14 of 20). No idempotency key on create calls. A duplicate SSH key is rejected and terminating an ended rental returns RENTAL_NOT_FOUND (5 of 20). A rental needs only `rentalType` and `gpuCount`, with defaults for region, GPU type and SSH key. No official SDK or CLI for the v2 API was found (8 of 15). 13 + 15 + 14 + 5 + 8 = 55." }, "scores": { "a": 66, "b": 55 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Hyperbolic Labs, Inc.", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://api.hyperbolic.ai", "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 Hyperbolic's Terms of Service. The unmaintained hyperbolic-mcp repository on GitHub is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-05", "name": "Last release" }, { "a": "2026-09-02", "b": "2025-03-24", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Hyperbolic's 38.7 (E), and leads in every scored category.", "question": "Which is better for AI agents, Cloud Run GPUs or Hyperbolic?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Hyperbolic at https://api.hyperbolic.ai.", "question": "Can an agent call Cloud Run GPUs and Hyperbolic without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 25", "Schema \u0026 documentation, 81 against 52", "Agent ergonomics, 66 against 55", "Security \u0026 auth, 78 against 48", "Payments \u0026 pricing, 20 against 15", "Maintenance \u0026 community, 80 against 39", "Transparency \u0026 trust, 84 against 64" ], "also": [ "No incidents deducted, where Hyperbolic 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": "Agents that rent whole H100, H200 or B200 machines or multi-node clusters for training and batch work and that have a funded account.", "slug": "hyperbolic", "watchFor": "API keys carry no scopes or expiry in the reviewed documentation, and the same key can call `DELETE /v2/users/me`" } ], "history": { "cloud-run-gpus": null, "hyperbolic": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": -9.5, "from": 48.2, "fromGrade": "D", "to": 38.7, "toGrade": "E" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 48.1, "fromGrade": "D", "to": 48.2, "toGrade": "D" }, { "causes": [ "time" ], "date": "2026-10-12", "delta": 0.1, "from": 48, "fromGrade": "D", "to": 48.1, "toGrade": "D" } ] }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.json", "title": "Baseten vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-hyperbolic.json", "title": "Baseten vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/baseten-vs-hyperbolic" }, { "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-hyperbolic.json", "title": "Beam vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/beam-vs-hyperbolic" }, { "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-hyperbolic.json", "title": "Cerebrium vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-hyperbolic" }, { "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-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-hyperbolic.json", "title": "CoreWeave vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/coreweave-vs-hyperbolic" }, { "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/gpusmarket-vs-hyperbolic.json", "title": "GPUsMarket vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic.json", "title": "Hugging Face Inference Endpoints vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb.json", "title": "Hyperbolic vs Koyeb", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-lambda.json", "title": "Hyperbolic vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-massed-compute.json", "title": "Hyperbolic vs Massed Compute", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-modal.json", "title": "Hyperbolic vs Modal", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-nebius-ai-cloud.json", "title": "Hyperbolic vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-northflank.json", "title": "Hyperbolic vs Northflank", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.json", "title": "Hyperbolic vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-runpod.json", "title": "Hyperbolic vs Runpod", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-thunder-compute.json", "title": "Hyperbolic vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.json", "title": "Hyperbolic vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters" }, { "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/hyperbolic-vs-verda.json", "title": "Hyperbolic vs Verda", "url": "https://www.anchorterminal.com/compare/hyperbolic-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": 45, "cloud-run-gpus": 70, "edge": "cloud-run-gpus", "hyperbolic": 25, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 29, "cloud-run-gpus": 81, "edge": "cloud-run-gpus", "hyperbolic": 52, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 11, "cloud-run-gpus": 66, "edge": "cloud-run-gpus", "hyperbolic": 55, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 30, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "hyperbolic": 48, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 5, "cloud-run-gpus": 20, "edge": "cloud-run-gpus", "hyperbolic": 15, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 41, "cloud-run-gpus": 80, "edge": "cloud-run-gpus", "hyperbolic": 39, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 20, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "hyperbolic": 64, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Hyperbolic's 38.7 (E), and leads in every scored category. 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.", "hyperbolic": "Hyperbolic's docs carry llms.txt, Markdown pages and a dated 1 March 2027 end for legacy paths, and billing starts only once an instance is ready. API keys carry no scopes and can delete the account, rental creation has no idempotency key, no 429 guidance is documented, and renting needs a browser signup and a $5 deposit." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Hyperbolic's 38.7 (E), and leads in every scored category. 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- Hyperbolic: grade E, 38.7/100, rank #1335 of 1486. Markdown https://www.anchorterminal.com/tools/hyperbolic.md · JSON https://www.anchorterminal.com/api/v1/tools/hyperbolic.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 25\n- Schema \u0026 documentation, 81 against 52\n- Agent ergonomics, 66 against 55\n- Security \u0026 auth, 78 against 48\n- Payments \u0026 pricing, 20 against 15\n- Maintenance \u0026 community, 80 against 39\n- Transparency \u0026 trust, 84 against 64\n\nAlso in its favour:\n- No incidents deducted, where Hyperbolic 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### Hyperbolic (E)\n\nGood for: Agents that rent whole H100, H200 or B200 machines or multi-node clusters for training and batch work and that have a funded account.\n\nWatch for: API keys carry no scopes or expiry in the reviewed documentation, and the same key can call `DELETE /v2/users/me`\n\n\n## Why the edge\n\n### Reliability: Cloud Run GPUs +45\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- Hyperbolic (25): Graded on the hosted lines for the REST API. Hyperbolic's Terms of Service (24 March 2025) bar spiders, robots and scrapers from downloading data from any web page in the Services, which cover the website, so hyperbolic.ai pages and the status page keep their 8 October readings, not re-read on 4 November 2026. Status page at status.hyperbolic.ai on UptimeRobot. The page draws its monitors and history by script from `/api/`, a path its robots.txt closes, so no component was ever read, and a status-page line with no readable component scores 0, as for fonoa, n8n and windmill (was 20). The incident record was never read either (5, unreadable history). Rate limits appear as numbers only on the plan cards in the docs, 60 requests a minute on the free tier and 600 on the pro tier, and the terms let Hyperbolic change limits without notice (10 of 15). No 429 response, `Retry-After` or backoff guidance in the docs, and no idempotency key on rental creation (0). SLA 7 to 0. The docs state a 99.5 per cent uptime figure for On-Demand and Reserved with credits reviewed case by case, and the Terms of Service disclaim uptime and any duty to give credits. A figure with discretionary credits and no SLA document isn't an SLA (manatal). The v2 API is not marked beta (10). 0 + 5 + 10 + 0 + 0 + 10 = 25.\n\n### Maintenance \u0026 community: Cloud Run GPUs +41\n\n- Cloud Run GPUs (80): Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.\n- Hyperbolic (39): Readings are per the 8 October check, not re-read on 4 November 2026. The newest changelog entry is for the week of 5 October 2026, 30 days before today (30); it drops to 20 after 4 November unless a newer entry appears. It was the only dated entry on the changelog and its RSS feed, so the three-entry test is not met (0 of 20). A public changelog with RSS, in-app chat and email support with stated hours of Monday to Friday, 06:00 to 17:00 Pacific Time (9 of 15). No current official SDK for the v2 API. The vendor's MCP repository still ends at its 21 May 2025 commit (clone, 4 November) and targets legacy v1 paths (0 of 15). Package health 3 to 0. The partial rested on the spec served by the API, a struck reading, and there is no client package to assess. 30 + 0 + 9 + 0 + 0 = 39.\n\n### Security \u0026 auth: Cloud Run GPUs +30\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- Hyperbolic (48): Readings are per the 8 October check, not re-read on 4 November 2026. Plain API keys sent as a Bearer header, shown once, revocable, any number per account, and attributed to their creator inside an Organisation. No scopes or expiry found, and no secret in a URL (20 of 30). No read-only key and no confirmation step. A key can rent and terminate machines and can call `DELETE /v2/users/me`. Organisation members cannot deposit funds or see billing history (4 of 20). Responses are infrastructure metadata (10). Key lists show each key's creator and revocation time, and rental and transaction histories exist. No audit log was found for self-serve accounts (4 of 15). Programme 9 to 10. The docs ask for vulnerability reports by email with a 48-hour acknowledgement and claim a completed SOC 2 Type I audit with Type II under way, reports under NDA. A disclosure route with a stated acknowledgement time is 10; no security.txt or bug bounty, and the trust centre is drawn by script. 20 + 4 + 10 + 4 + 10 = 48.\n\n### Schema \u0026 documentation: Cloud Run GPUs +29\n\n- Cloud Run GPUs (81): API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.\n- Hyperbolic (52): Readings are per the 8 October check, not re-read on 4 November 2026. Contract line 25 to 0. The OpenAPI document was read from the API host (api.hyperbolic.ai/v2/openapi.json, the product's own endpoint) and from a copy under /docs/api-reference/ with no recorded docs page that shows or links it. The first reading is struck, and a contract on a now-paused host with no recorded visible link is struck too (jambonz, stable-audio). `llms.txt`, every docs page as Markdown and a 188 KB `llms-full.txt` (10). Of the 34 current operations, 17 have a description that only repeats the summary. The rest state behaviour, limits and named error cases, and every deprecated operation names its replacement (10 of 20). Required fields, 89 enums, numeric bounds and a `oneOf` for new or existing storage volumes, but rental IDs accept an integer or a string (12 of 15). Five error schemas with examples and 400, 401, 403 and 500 on every operation. No request body has an example and no 429 is listed (8 of 15). Versioned in the path with a dated changelog and RSS feed, which held one entry (12 of 15). 0 + 10 + 10 + 12 + 8 + 12 = 52.\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- Hyperbolic (64): Readings are per the 8 October check, not re-read on 4 November 2026, apart from the Terms of Service, re-read and unchanged (24 March 2025). Closed service under California law. The terms describe a marketplace in which the contract for compute is between buyer and supplier, which does not match the docs' description of a GPU cloud with an SLA (13 of 30). The Privacy Policy is effective 3 June 2024, gives no retention periods and names Babylon three times in one clause. The terms say user content is not used to train generative models. The docs promise data wiping on termination, a 30-day grace period for volumes and a DPA on request, and no published DPA was found (12 of 30). No written deprecation policy, but legacy paths carry a `Sunset` header with an end date of 1 March 2027 and each deprecated operation names its replacement (14 of 20). Stripe is named as payment processor. The suppliers that host the machines are not named, and the trust centre's sub-processor list, if any, was unreadable (6 of 20). 13 + 12 + 14 + 6 = 45.\n\n### Agent ergonomics: Cloud Run GPUs +11\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- Hyperbolic (55): Readings are per the 8 October check, not re-read on 4 November 2026. No field selection. Lists page at 25 by default and 100 at most, and `GET /v2/on-demand/active-rental-summary` returns counts and hourly cost without the rental bodies (13 of 25). `page` and `pageSize` on active rentals, a cursor on history, and filters for GPU type, region and term type. Storage volumes and SSH keys return whole arrays (15 of 20). Errors carry `code`, `message` and `issues`, with named cases such as INVALID_INPUT_FOR_RENTAL_TYPE and REBOOT_ALREADY_IN_PROGRESS (14 of 20). No idempotency key on create calls. A duplicate SSH key is rejected and terminating an ended rental returns RENTAL_NOT_FOUND (5 of 20). A rental needs only `rentalType` and `gpuCount`, with defaults for region, GPU type and SSH key. No official SDK or CLI for the v2 API was found (8 of 15). 13 + 15 + 14 + 5 + 8 = 55.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Hyperbolic | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 25 | Cloud Run GPUs +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 52 | Cloud Run GPUs +29 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 55 | Cloud Run GPUs +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 48 | Cloud Run GPUs +30 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 15 | Cloud Run GPUs +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 39 | Cloud Run GPUs +41 |\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** | **38.7 · E** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Hyperbolic |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Hyperbolic Labs, Inc. |\n| Hosted endpoint | `https://run.googleapis.com` | `https://api.hyperbolic.ai` |\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 Hyperbolic's Terms of Service. The unmaintained hyperbolic-mcp repository on GitHub is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-30 | 2026-10-05 |\n| Terms last updated | 2026-09-02 | 2025-03-24 |\n| Privacy policy last updated | 2026-09-28 | no date given |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Hyperbolic\n\n- -9.5 on 4 November 2026 (D to E): correction\n- +0.1 on 27 October 2026: checklist\n- +0.1 on 12 October 2026: time\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**Hyperbolic.** Hyperbolic's docs carry llms.txt, Markdown pages and a dated 1 March 2027 end for legacy paths, and billing starts only once an instance is ready. API keys carry no scopes and can delete the account, rental creation has no idempotency key, no 429 guidance is documented, and renting needs a browser signup and a $5 deposit.\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### Hyperbolic\n\n1. Check current GPU configurations and hourly prices before renting. The docs point to the console for rates, and the marketplace page gave $3.19 a GPU-hour on 8 October 2026.\n2. Send `rentalType` and `gpuCount` to `POST /v2/on-demand/rentals`. Region defaults to `us-central-1` and GPU type to `h100`, so set both from the options list.\n3. List active rentals before retrying a failed create call. There is no idempotency key and every ready rental bills hourly.\n4. Save an SSH public key with `POST /v2/ssh-keys` before renting. Without `sshPublicKeyIds` the newest saved key is attached.\n5. Do not create reserved rentals unless asked. They are paid in full up front and cannot be terminated early.\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Hyperbolic?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Hyperbolic's 38.7 (E), and leads in every scored category.\n\n### Can an agent call Cloud Run GPUs and Hyperbolic without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Hyperbolic at https://api.hyperbolic.ai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"hyperbolic\"}`. From a terminal: `anchor compare cloud-run-gpus hyperbolic`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/hyperbolic.json\n\n## Other comparisons with Cloud Run GPUs or Hyperbolic\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Hyperbolic](https://www.anchorterminal.com/compare/baseten-vs-hyperbolic.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Hyperbolic](https://www.anchorterminal.com/compare/beam-vs-hyperbolic.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Hyperbolic](https://www.anchorterminal.com/compare/cerebrium-vs-hyperbolic.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 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 Hyperbolic](https://www.anchorterminal.com/compare/coreweave-vs-hyperbolic.md)\n- [Crusoe Cloud vs Hyperbolic](https://www.anchorterminal.com/compare/crusoe-cloud-vs-hyperbolic.md)\n- [GPUsMarket vs Hyperbolic](https://www.anchorterminal.com/compare/gpusmarket-vs-hyperbolic.md)\n- [Hugging Face Inference Endpoints vs Hyperbolic](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic.md)\n- [Hyperbolic vs Koyeb](https://www.anchorterminal.com/compare/hyperbolic-vs-koyeb.md)\n- [Hyperbolic vs Lambda Cloud](https://www.anchorterminal.com/compare/hyperbolic-vs-lambda.md)\n- [Hyperbolic vs Massed Compute](https://www.anchorterminal.com/compare/hyperbolic-vs-massed-compute.md)\n- [Hyperbolic vs Modal](https://www.anchorterminal.com/compare/hyperbolic-vs-modal.md)\n- [Hyperbolic vs Nebius AI Cloud](https://www.anchorterminal.com/compare/hyperbolic-vs-nebius-ai-cloud.md)\n- [Hyperbolic vs Northflank](https://www.anchorterminal.com/compare/hyperbolic-vs-northflank.md)\n- [Hyperbolic vs Replicate Deployments](https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.md)\n- [Hyperbolic vs Runpod](https://www.anchorterminal.com/compare/hyperbolic-vs-runpod.md)\n- [Hyperbolic vs Thunder Compute](https://www.anchorterminal.com/compare/hyperbolic-vs-thunder-compute.md)\n- [Hyperbolic vs Together GPU Clusters](https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.md)\n- [Hyperbolic vs Vast.ai](https://www.anchorterminal.com/compare/hyperbolic-vs-vast-ai.md)\n- [Hyperbolic vs Verda](https://www.anchorterminal.com/compare/hyperbolic-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 Hyperbolic", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Hyperbolic's 38.7 (E) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Hyperbolic E 38.7", "scores" ], "h1": "Cloud Run GPUs vs Hyperbolic", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-hyperbolic", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Hyperbolic for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic" }, "tokens": { "markdown": 5450, "slim": 3230 }, "version": 1 }