{ "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 Thunder Compute's 51.3 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "thunder-compute", "name": "Thunder Compute", "vendor": "Thunder Compute", "vendorUrl": "https://www.thundercompute.com", "kind": "http-api", "category": "gpu-compute", "summary": "Thunder Compute is a US GPU cloud renting RTX A6000, L40, A100 and H100 instances by the minute and GPU sandboxes by the second. Agents use its REST API, a hosted MCP server with OAuth, or the `tnr` CLI.", "url": "https://www.anchorterminal.com/tools/thunder-compute", "markdownUrl": "https://www.anchorterminal.com/tools/thunder-compute.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/thunder-compute.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/thunder-compute.json", "dns": "thunder-compute.grade.anchorterminal.com", "repo": "https://github.com/Thunder-Compute/thunder-cli", "license": "Proprietary service under Thunder Compute's Terms and Conditions. The `tnr` CLI on GitHub is MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.thundercompute.com:8443/v1", "packages": [ { "registry": "go", "name": "github.com/Thunder-Compute/thunder-cli" }, { "registry": "pypi", "name": "thunder-sandbox" } ], "auth": "mixed", "authNotes": "Self-serve. The hosted MCP server uses OAuth 2.0 with discovery. The first connection opens a browser to sign in and approve, tokens refresh, and the scopes are `instances:read`, `instances:write`, `snapshots:read`, `snapshots:write`, `sandboxes:read`, `sandboxes:write`, `billing:read` and `org:read`. The REST API takes a named API token as a Bearer header. Tokens are created and revoked one at a time in the console, or with the MCP `create_token` tool, and no token scopes were found. The CLI and the sandbox SDK read `TNR_API_TOKEN` for headless use. Price, specification, availability and template endpoints need no token.", "pricing": "usage", "pricingNotes": "No general free tier. Instances are billed by the minute while they run, paid by saved card or preloaded credit that is non-refundable. Per GPU an hour on 9 October 2026, RTX A6000 is $0.35, L40 $0.79, A100 80 GB $1.09 and H100 $3.20. Sandboxes are billed by the second and need access enabled by the vendor. Students with a US university email get $20 of credit for A6000 and L40 GPUs. Reserved capacity is by quote (https://www.thundercompute.com/pricing).", "priceSummary": "$0.04 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs corpus, the OpenAPI document or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": 28, "popularity": { "githubStars": 34, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://www.thundercompute.com/docs", "llmsTxt": "https://www.thundercompute.com/docs/llms.txt", "openapi": "https://api.thundercompute.com:8443/openapi.json", "registryName": "io.github.Thunder-Compute/thunder-compute", "capabilities": [ "compute.gpu", "compute.containers" ], "tags": [ "hosted", "usage-priced", "openapi", "llms-txt", "mcp", "cli", "oauth", "api-key", "python", "go", "status-page", "card-required", "closed-source" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 51.3, "grade": "D", "agentReady": false, "rank": 1024, "ranked": true, "rankOf": 1486, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 48, "maintenance": 79, "payments": 20, "reliability": 65, "schema": 70, "security": 51, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -5, "negativeNotes": [ "-3, released fixes of described flaws with no advisory. The CLI's v2.1.0 (16 September 2026) changelog has a Security section that stops \"copying the local CLI authentication credential onto instances during connect\" and stops configuration and API URL overrides \"sending browser login credentials to a different API origin\". v2.0.71 (30 July) made the updater require verified checksums. OSV holds no record for thunder-cli (https://github.com/Thunder-Compute/thunder-cli/blob/main/CHANGELOG.md).", "-2, undisclosed default telemetry. Released CLI builds inject a Sentry DSN at build time, so error reports go to Sentry by default with a user ID derived from a hash of the API token, the machine's HOSTNAME as `instance_id`, OS, architecture and Go version, and tracing is enabled at a 10 per cent sample with request breadcrumbs. No opt-out was found in the CLI, its README or, per the 9 October check, the docs. The v2.2.0 changelog mentions \"released CLI error reports\" without describing them, and Sentry isn't on the sub-processor list (https://github.com/Thunder-Compute/thunder-cli/blob/main/main.go)." ], "verdict": "The hosted MCP server signs in with OAuth and separate read and write scopes, and the REST API has a public OpenAPI 3.1 document. No rate limits, SLA or API changelog were found, instance creation has no idempotency key, and the CLI sends error reports to Sentry by default with no documented opt-out.", "bestFor": "Agents in coding tools that rent a single persistent GPU machine for development, fine-tuning or a model server, at low hourly prices and over MCP.", "strengths": [ "Hosted MCP server at `https://www.thundercompute.com/mcp` with OAuth and ten scopes that separate read from write for instances, snapshots and sandboxes", "Public OpenAPI 3.1 document with 41 operations, plus `llms.txt`, `llms-full.txt` and a Markdown copy of every docs page", "Per-GPU-hour, per-vCPU-hour and storage prices are public on the pricing page", "Section 28 of the terms, dated 28 September 2026, permits access by AI agents, scripts and SDKs through the account holder's own credentials", "The `tnr` CLI had three code releases between 15 September and 27 October 2026, with a dated changelog" ], "weaknesses": [ "No rate limits, 429 guidance or SLA were found in the reviewed documentation, and the terms disclaim availability", "`POST /instances/create` has no idempotency key, so a retried launch can start a second billed instance", "Instances cannot be stopped. Pausing means taking a snapshot, deleting the instance and restoring later", "No security.txt or disclosure policy was found, and the SOC 2 Type II claim in `llms.txt` has no report or trust page linked", "The CLI sends error reports to Sentry by default with a hashed token ID, and no opt-out was found", "Credential-handling fixes in CLI v2.1.0 (16 September 2026) shipped with no advisory" ], "agentNotes": [ "Call `GET /v2/status` or the `get_availability` tool before creating an instance. Availability can change before launch, and creation fails when a type is sold out.", "List instances before retrying a failed create, because the call has no idempotency key.", "Pass `public_key` on create. If omitted, the response carries a generated private key that is returned once.", "To pause work, create a snapshot, delete the instance and later create a new instance from the snapshot. Snapshot storage keeps billing until deleted.", "For headless use set `TNR_API_TOKEN` to a token from the console, and upgrade the CLI to v2.1.0 or later, which stops copying that credential onto instances." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.3 } ], "editorialScores": { "ergonomics": 48, "maintenance": 79, "payments": 20, "reliability": 65, "schema": 70, "security": 51, "transparency": 51 }, "provenanceScore": 80, "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": { "install": "curl -fsSL https://raw.githubusercontent.com/Thunder-Compute/thunder-cli/main/scripts/install.sh | bash", "http": "curl https://api.thundercompute.com:8443/v2/pricing", "claudeCode": "claude mcp add --transport http thunder-compute https://www.thundercompute.com/mcp", "config": { "mcpServers": { "thunder-compute": { "url": "https://www.thundercompute.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/thunder-compute" }, "area": "models", "unitPrices": [ { "item": "RTX A6000 48 GB instance", "unit": "gpu-hour", "usd": 0.35, "note": "Billed per minute. One GPU per instance" }, { "item": "L40 48 GB instance", "unit": "gpu-hour", "usd": 0.79, "note": "Billed per minute" }, { "item": "A100 80 GB instance", "unit": "gpu-hour", "usd": 1.09, "note": "Billed per minute. 4 and 8 GPU shapes cost $1.49 a GPU per the price endpoint" }, { "item": "H100 80 GB instance", "unit": "gpu-hour", "usd": 3.2, "note": "Billed per minute" }, { "item": "H100 80 GB sandbox", "unit": "gpu-hour", "usd": 2.95, "note": "Billed per second, plus vCPU and memory. Access on request" }, { "item": "A100 80 GB sandbox", "unit": "gpu-hour", "usd": 1.95, "note": "Billed per second, plus vCPU and memory. Access on request" }, { "item": "Extra instance vCPU", "unit": "vcpu-hour", "usd": 0.04, "note": "Above the vCPUs included with each GPU" }, { "item": "Sandbox vCPU", "unit": "vcpu-hour", "usd": 0.051, "note": "Memory is $0.016 per GiB an hour" }, { "item": "Instance disk above 100 GB per GPU", "unit": "gb-month", "usd": 0.219, "note": "Billed only while the instance runs" }, { "item": "Snapshot storage", "unit": "gb-month", "usd": 0.05, "note": "Kept until deleted" } ], "provenance": { "legalEntity": "Thunder GPU, Inc.", "domain": "thundercompute.com", "domainRegistered": "2024-02-29", "endpointOnVendorDomain": true, "terms": "https://www.thundercompute.com/terms-and-conditions", "privacy": "https://www.thundercompute.com/privacy-policy", "statusPage": "https://status.thundercompute.com", "changelog": "https://github.com/Thunder-Compute/thunder-cli/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The Terms and Conditions, last updated 28 September 2026, name Thunder GPU, Inc., doing business as Thunder Compute, a Delaware company, and apply Delaware law. They cover the site and the services, with sections on automated access, usage billing and instance data deletion.", "The privacy policy, last updated 28 September 2026, covers the website and the GPU platform, including access by AI agents.", "The API answers at api.thundercompute.com on port 8443, and the MCP server at www.thundercompute.com/mcp, both on the vendor domain.", "/.well-known/security.txt answers 404.", "RDAP for thundercompute.com gives a registration date of 2024-02-29.", "The changelog linked is the CLI's. No API changelog was found.", "A Data Processing Addendum is published in the docs and a sub-processor list on the site, last updated 27 August 2025." ], "score": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/thunder-compute.json", "live": { "slug": "thunder-compute", "probe": { "target": "https://api.thundercompute.com:8443/v1", "method": "get", "lastAt": "2026-11-07T18:20:59.744291248Z", "lastOk": true, "lastStatus": 404, "lastMs": 290, "authRequired": false, "uptime24h": 100, "uptime30d": 99.89, "p50ms24h": 612, "p95ms24h": 725, "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": 252 }, { "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": 244 }, { "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": 247 }, { "date": "2026-10-28", "probes": 250, "ok": 249 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.thundercompute.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:22:05.637730425Z" }, "versions": [ { "registry": "github", "name": "Thunder-Compute/thunder-cli", "version": "v2.3.0", "released": "2026-11-05", "seenAt": "2026-11-07T00:11:24.374859251Z" }, { "registry": "mcp-registry", "name": "io.github.Thunder-Compute/thunder-compute", "version": "1.0.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "pypi", "name": "thunder-sandbox", "version": "0.7.11", "released": "2026-11-04", "seenAt": "2026-11-07T00:11:24.191658707Z" } ], "githubStars": 34, "pypiWeekly": 7292, "securityTxt": { "url": "https://thundercompute.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:02:02.689166619Z" }, "llmsTxt": { "url": "https://www.thundercompute.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:08.029305428Z" }, "domain": { "domain": "thundercompute.com", "registered": "2024-02-29", "source": "https://rdap.verisign.com/com/v1/domain/thundercompute.com", "checkedAt": "2026-11-01T14:19:55.118917218Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/Thunder-Compute/thunder-cli/main/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:19:37.649850655Z", "changedAt": "2026-11-05T13:04:01.9071579Z", "fingerprint": "e59bfd9db845" }, { "url": "https://www.thundercompute.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:35:36.789186909Z", "changedAt": "2026-11-07T14:35:36.789186909Z", "fingerprint": "adbd67a657df" }, { "url": "https://www.thundercompute.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:35:39.012108629Z", "changedAt": "2026-10-23T02:07:42.099244407Z", "fingerprint": "15f556e42b20" }, { "url": "https://www.thundercompute.com/terms-and-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:35:41.000439019Z", "changedAt": "2026-10-23T02:07:44.212693674Z", "fingerprint": "bcc6d526ecf3" } ], "mcpTools": { "url": "https://www.thundercompute.com/mcp", "checkedAt": "2026-11-07T01:48:36.126087407Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:48:36.126087407Z" }, "github": { "repo": "thunder-compute/thunder-cli", "checkedAt": "2026-11-02T09:31:35.915022229Z", "stars": 34, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-27T23:09:19Z", "openIssues": 0, "openPRs": 2, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0, "replies": { "sampled": 12, "unanswered": 0, "medianDays": 2.3 } }, "updatedAt": "2026-11-07T18:22:05.637730425Z" } }, "edges": [ { "by": 27, "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": "The MCP server uses OAuth 2.0 with discovery, refresh tokens and ten scopes that separate read from write for instances, snapshots and sandboxes. The REST API uses named API tokens that are created and revoked one at a time, with no scopes found. No secret travels in a URL (25 of 30). Read scopes exist, and the CLI requires `--yes` to delete without a prompt. No confirmation step for `delete_instance` or `delete_snapshot` was found in the MCP docs, and both are described as irreversible (8 of 20). Responses are infrastructure metadata, except `run_command` output and sandbox logs, with no guidance found on untrusted output (8 of 15). `GET /tokens` returns creation and last-used times and sandbox logs are listed by API. No audit log was found (4 of 15). No security.txt, disclosure policy or bug bounty was found. `llms.txt` states SOC 2 Type II and GDPR compliance with no report or trust page linked, and the DPA promises an audit summary on written request and incident notice within 72 hours (6 of 20). The site readings are per the 9 October check, not re-read on 4 November. 25+8+8+4+6 = 51." }, "scores": { "a": 78, "b": 51 } }, { "by": 18, "category": "ergonomics", "leads": "cloud-run-gpus", "name": "Agent ergonomics", "reasons": { "a": "Platform reading. One `gcloud run deploy` with `--gpu` and `--gpu-type` adds a GPU to a container, and responses carry the service object with `fieldMask` on updates (15). List calls page with `pageSize` and `pageToken` (15). Google's status codes and messages, with quota errors that name the limit (12). Revisions are immutable, traffic can be moved back, and etags guard updates, but no idempotency key on create (12). Client libraries in many languages and gcloud, though a GPU deploy needs instance-based billing, minimum CPU and memory and, past 3 GPUs, a quota request (12). 15+15+12+12+12 = 66.", "b": "No field selection, and `GET /instances/list` returns every instance in one map. The MCP server has 28 tools in one set, with no toolsets found (12 of 25). `limit` up to 100, `page_token` and a status filter on sandboxes and sandbox logs. No pagination on instances, snapshots or keys (8 of 20). Errors carry a numeric `code`, a string `error` such as `invalid_request` and a `message`, documented per operation (14 of 20). Duplicate SSH keys are a no-op and port changes are deduplicated in one transaction, but create calls have no idempotency key. MCP tool annotations were not read (7 of 20). A create call needs five fields. The official Python SDK covers sandboxes only, and the Go CLI covers instances (7 of 15). All of this is per the 9 October check, not re-read on 4 November. 12+8+14+7+7 = 48." }, "scores": { "a": 66, "b": 48 } }, { "by": 18, "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 and Conditions dated 28 September 2026 and Delaware law. The CLI is MIT. The OpenAPI document names Apache 2.0 and a placeholder terms address (15 of 30). The privacy policy of 28 September 2026 says instance data is not used to train AI models, the terms say instance data may be deleted 60 days after the account was last active, and a DPA is published. The sub-processor list names Firebase for sign-in while the MCP docs name Stytch, and the FAQ says instances are EC2 while the list names Azure (18 of 30). No deprecation policy. The terms allow changes without notice, and the billing docs say rates can change without notice. Legacy endpoints are marked as retained for compatibility (6 of 20). Five sub-processors with locations are listed and the DPA sets 10 business days' notice of changes. The list is dated 27 August 2025 and omits Stytch and Sentry, which the MCP docs and the CLI source name (12 of 20). The site readings are per the 9 October check, not re-read on 4 November. 15+18+6+12 = 51." }, "scores": { "a": 84, "b": 66 } }, { "by": 11, "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": "Public OpenAPI 3.1 document at api.thundercompute.com:8443/openapi.json with 41 operations and 72 schemas (25). `llms.txt`, `llms-full.txt` and a Markdown copy of every docs page (10). 28 of 41 operations have a description. Instance operations state side effects such as the private key being returned once, while most sandbox operations have a summary only (12 of 20). Required fields are marked, but the document has six enums, `gpu_type` and `template` are free strings and the instance list is a map keyed by ID (8 of 15). 12 examples and one error schema with `code`, `error` and `message`. Most operations document 400, 401 and 500, and none documents 429 (9 of 15). `/v1` and `/v2` paths, with legacy endpoints and the `mode` field marked as retained or deprecated. No API changelog was found. The CLI has a dated one (6 of 15). No published copy of the MCP tool definitions was found, so they were not read. All of this is per the 9 October check, not re-read on 4 November. 25+10+12+8+9+6 = 70." }, "scores": { "a": 81, "b": 70 } }, { "by": 5, "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 and the hosted MCP server. Thunder Compute's terms bar robots, scrapers and data-gathering tools on the Services, so its site, status page and API host weren't requested on 4 November and the readings below are per the 9 October check, not re-read on 4 November. Status page on incident.io at status.thundercompute.com with Website, API and Instances components and monthly history (20). No incidents listed for July to 9 October 2026. The rest of the window is unread and not credited, so the line keeps its recorded award (30). No rate limits with numbers were found in the docs or the OpenAPI document (0). No 429 or retry guidance in the docs. The CLI source reads a `Retry-After` header on errors, adding a duplicate SSH key is a no-op and port updates are atomic, but instance creation has no idempotency key (5 of 15, a partial value kept and flagged). No SLA found, and the terms say availability is not guaranteed (0). The API and MCP server carry no beta label (10). 20+30+0+5+0+10 = 65." }, "scores": { "a": 70, "b": 65 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Google Cloud", "b": "Thunder Compute", "name": "Vendor" }, { "a": "https://run.googleapis.com", "b": "https://api.thundercompute.com:8443/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "not published", "b": "$0.219 per GB per month", "name": "Price for gpu compute" }, { "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 Thunder Compute's Terms and Conditions. The `tnr` CLI on GitHub is MIT", "name": "Licence" }, { "a": "none", "b": "28", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.Thunder-Compute/thunder-compute", "name": "MCP registry" }, { "a": "2026-10-30", "b": "2026-10-27", "name": "Last release" }, { "a": "2026-09-02", "b": "2026-09-28", "name": "Terms last updated" }, { "a": "2026-09-28", "b": "2026-09-28", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "34 stars", "name": "Popularity" } ], "faq": [ { "answer": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Thunder Compute's 51.3 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Cloud Run GPUs or Thunder Compute?" }, { "answer": "Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Thunder Compute at https://api.thundercompute.com:8443/v1.", "question": "Can an agent call Cloud Run GPUs and Thunder Compute without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 65", "Schema \u0026 documentation, 81 against 70", "Agent ergonomics, 66 against 48", "Security \u0026 auth, 78 against 51", "Transparency \u0026 trust, 84 against 66" ], "also": [ "No incidents deducted, where Thunder Compute loses 5 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 in coding tools that rent a single persistent GPU machine for development, fine-tuning or a model server, at low hourly prices and over MCP.", "slug": "thunder-compute", "watchFor": "No rate limits, 429 guidance or SLA were found in the reviewed documentation, and the terms disclaim availability" } ], "history": { "cloud-run-gpus": null, "thunder-compute": [ { "causes": [ "event" ], "date": "2026-11-04", "delta": -5, "from": 56.3, "fromGrade": "C", "to": 51.3, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 56.1, "fromGrade": "C", "to": 56.3, "toGrade": "C" } ] }, "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-thunder-compute.json", "title": "Baseten vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/baseten-vs-thunder-compute" }, { "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-thunder-compute.json", "title": "Beam vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/beam-vs-thunder-compute" }, { "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-thunder-compute.json", "title": "Cerebrium vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.json", "title": "Cloud Run GPUs vs CoreWeave", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.json", "title": "Cloud Run GPUs vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.json", "title": "Cloud Run GPUs vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.json", "title": "Cloud Run GPUs vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.json", "title": "Cloud Run GPUs vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.json", "title": "Cloud Run GPUs vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.json", "title": "Cloud Run GPUs vs Massed Compute", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.json", "title": "Cloud Run GPUs vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.json", "title": "Cloud Run GPUs vs Northflank", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-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-thunder-compute.json", "title": "CoreWeave vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/coreweave-vs-thunder-compute" }, { "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/gpusmarket-vs-thunder-compute.json", "title": "GPUsMarket vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute.json", "title": "Hugging Face Inference Endpoints vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute" }, { "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/koyeb-vs-thunder-compute.json", "title": "Koyeb vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/koyeb-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-thunder-compute.json", "title": "Lambda Cloud vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/lambda-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/massed-compute-vs-thunder-compute.json", "title": "Massed Compute vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-thunder-compute.json", "title": "Modal vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/modal-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-thunder-compute.json", "title": "Nebius AI Cloud vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-thunder-compute.json", "title": "Northflank vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/northflank-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute.json", "title": "Replicate Deployments vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.json", "title": "Runpod vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/runpod-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.json", "title": "Thunder Compute vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai.json", "title": "Thunder Compute vs Vast.ai", "url": "https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-verda.json", "title": "Thunder Compute vs Verda", "url": "https://www.anchorterminal.com/compare/thunder-compute-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": 5, "cloud-run-gpus": 70, "edge": "cloud-run-gpus", "key": "reliability", "name": "Reliability", "thunder-compute": 65, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "cloud-run-gpus": 81, "edge": "cloud-run-gpus", "key": "schema", "name": "Schema \u0026 documentation", "thunder-compute": 70, "weight": 13 }, { "by": 18, "cloud-run-gpus": 66, "edge": "cloud-run-gpus", "key": "ergonomics", "name": "Agent ergonomics", "thunder-compute": 48, "weight": 13 }, { "by": 27, "cloud-run-gpus": 78, "edge": "cloud-run-gpus", "key": "security", "name": "Security \u0026 auth", "thunder-compute": 51, "weight": 14 }, { "by": 0, "cloud-run-gpus": 20, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "thunder-compute": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "cloud-run-gpus": 80, "edge": "cloud-run-gpus", "key": "maintenance", "name": "Maintenance \u0026 community", "thunder-compute": 79, "weight": 7 }, { "by": 18, "cloud-run-gpus": 84, "edge": "cloud-run-gpus", "key": "transparency", "name": "Transparency \u0026 trust", "thunder-compute": 66, "weight": 7 } ], "summary": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Thunder Compute's 51.3 (D), and leads in 6 of 7 scored categories. 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.", "thunder-compute": "The hosted MCP server signs in with OAuth and separate read and write scopes, and the REST API has a public OpenAPI 3.1 document. No rate limits, SLA or API changelog were found, instance creation has no idempotency key, and the CLI sends error reports to Sentry by default with no documented opt-out." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute", "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.min.md" }, "markdown": "Cloud Run GPUs scores 68.4 (B) on agent readiness against Thunder Compute's 51.3 (D), and leads in 6 of 7 scored categories. 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- Thunder Compute: grade D, 51.3/100, rank #1024 of 1486. Markdown https://www.anchorterminal.com/tools/thunder-compute.md · JSON https://www.anchorterminal.com/api/v1/tools/thunder-compute.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 65\n- Schema \u0026 documentation, 81 against 70\n- Agent ergonomics, 66 against 48\n- Security \u0026 auth, 78 against 51\n- Transparency \u0026 trust, 84 against 66\n\nAlso in its favour:\n- No incidents deducted, where Thunder Compute loses 5 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### Thunder Compute (D)\n\nGood for: Agents in coding tools that rent a single persistent GPU machine for development, fine-tuning or a model server, at low hourly prices and over MCP.\n\nWatch for: No rate limits, 429 guidance or SLA were found in the reviewed documentation, and the terms disclaim availability\n\n\n## Why the edge\n\n### Security \u0026 auth: Cloud Run GPUs +27\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- Thunder Compute (51): The MCP server uses OAuth 2.0 with discovery, refresh tokens and ten scopes that separate read from write for instances, snapshots and sandboxes. The REST API uses named API tokens that are created and revoked one at a time, with no scopes found. No secret travels in a URL (25 of 30). Read scopes exist, and the CLI requires `--yes` to delete without a prompt. No confirmation step for `delete_instance` or `delete_snapshot` was found in the MCP docs, and both are described as irreversible (8 of 20). Responses are infrastructure metadata, except `run_command` output and sandbox logs, with no guidance found on untrusted output (8 of 15). `GET /tokens` returns creation and last-used times and sandbox logs are listed by API. No audit log was found (4 of 15). No security.txt, disclosure policy or bug bounty was found. `llms.txt` states SOC 2 Type II and GDPR compliance with no report or trust page linked, and the DPA promises an audit summary on written request and incident notice within 72 hours (6 of 20). The site readings are per the 9 October check, not re-read on 4 November. 25+8+8+4+6 = 51.\n\n### Agent ergonomics: Cloud Run GPUs +18\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- Thunder Compute (48): No field selection, and `GET /instances/list` returns every instance in one map. The MCP server has 28 tools in one set, with no toolsets found (12 of 25). `limit` up to 100, `page_token` and a status filter on sandboxes and sandbox logs. No pagination on instances, snapshots or keys (8 of 20). Errors carry a numeric `code`, a string `error` such as `invalid_request` and a `message`, documented per operation (14 of 20). Duplicate SSH keys are a no-op and port changes are deduplicated in one transaction, but create calls have no idempotency key. MCP tool annotations were not read (7 of 20). A create call needs five fields. The official Python SDK covers sandboxes only, and the Go CLI covers instances (7 of 15). All of this is per the 9 October check, not re-read on 4 November. 12+8+14+7+7 = 48.\n\n### Transparency \u0026 trust: Cloud Run GPUs +18\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- Thunder Compute (66): Closed service under Terms and Conditions dated 28 September 2026 and Delaware law. The CLI is MIT. The OpenAPI document names Apache 2.0 and a placeholder terms address (15 of 30). The privacy policy of 28 September 2026 says instance data is not used to train AI models, the terms say instance data may be deleted 60 days after the account was last active, and a DPA is published. The sub-processor list names Firebase for sign-in while the MCP docs name Stytch, and the FAQ says instances are EC2 while the list names Azure (18 of 30). No deprecation policy. The terms allow changes without notice, and the billing docs say rates can change without notice. Legacy endpoints are marked as retained for compatibility (6 of 20). Five sub-processors with locations are listed and the DPA sets 10 business days' notice of changes. The list is dated 27 August 2025 and omits Stytch and Sentry, which the MCP docs and the CLI source name (12 of 20). The site readings are per the 9 October check, not re-read on 4 November. 15+18+6+12 = 51.\n\n### Schema \u0026 documentation: Cloud Run GPUs +11\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- Thunder Compute (70): Public OpenAPI 3.1 document at api.thundercompute.com:8443/openapi.json with 41 operations and 72 schemas (25). `llms.txt`, `llms-full.txt` and a Markdown copy of every docs page (10). 28 of 41 operations have a description. Instance operations state side effects such as the private key being returned once, while most sandbox operations have a summary only (12 of 20). Required fields are marked, but the document has six enums, `gpu_type` and `template` are free strings and the instance list is a map keyed by ID (8 of 15). 12 examples and one error schema with `code`, `error` and `message`. Most operations document 400, 401 and 500, and none documents 429 (9 of 15). `/v1` and `/v2` paths, with legacy endpoints and the `mode` field marked as retained or deprecated. No API changelog was found. The CLI has a dated one (6 of 15). No published copy of the MCP tool definitions was found, so they were not read. All of this is per the 9 October check, not re-read on 4 November. 25+10+12+8+9+6 = 70.\n\n### Reliability: Cloud Run GPUs +5\n\n- Cloud Run GPUs (70): Hosted reading. Google Cloud's status page with a JSON incident feed (20). In the 90 days from 8 August 2026 the feed names Cloud Run in three multi-product incidents, a service outage on 20 August (15:40 to 19:20 UTC, 27 products, global and us-west1), a network degradation in us-central1-b on 1 September and a europe-west2 disruption on 20 October. One major (10). Resource limits and GPU quota are published with numbers (3 GPUs a region by default), but no request rate for the Admin API was found on the quotas page (10). Google's client libraries retry with backoff and the Admin API takes etags, while no GPU-specific retry guidance was found (10). An SLA for GPU services, 99.95% with zonal redundancy and 99.5% without (10). GPU services generally available since 7 April 2025 (10). 20+10+10+10+10+10 = 70.\n- Thunder Compute (65): Graded on the hosted lines for the REST API and the hosted MCP server. Thunder Compute's terms bar robots, scrapers and data-gathering tools on the Services, so its site, status page and API host weren't requested on 4 November and the readings below are per the 9 October check, not re-read on 4 November. Status page on incident.io at status.thundercompute.com with Website, API and Instances components and monthly history (20). No incidents listed for July to 9 October 2026. The rest of the window is unread and not credited, so the line keeps its recorded award (30). No rate limits with numbers were found in the docs or the OpenAPI document (0). No 429 or retry guidance in the docs. The CLI source reads a `Retry-After` header on errors, adding a duplicate SSH key is a no-op and port updates are atomic, but instance creation has no idempotency key (5 of 15, a partial value kept and flagged). No SLA found, and the terms say availability is not guaranteed (0). The API and MCP server carry no beta label (10). 20+30+0+5+0+10 = 65.\n\n## Score by category\n\n| Category | Weight | Cloud Run GPUs | Thunder Compute | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 65 | Cloud Run GPUs +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 70 | Cloud Run GPUs +11 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 48 | Cloud Run GPUs +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 51 | Cloud Run GPUs +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 79 | Cloud Run GPUs +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 66 | Cloud Run GPUs +18 |\n| Negative events | ≤15 | 0 | -5 | |\n| **Total** | | **68.4 · B** | **51.3 · D** | |\n\n## Facts side by side\n\n| Fact | Cloud Run GPUs | Thunder Compute |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Google Cloud | Thunder Compute |\n| Hosted endpoint | `https://run.googleapis.com` | `https://api.thundercompute.com:8443/v1` |\n| Transports | | HTTP, Streamable HTTP |\n| Auth | OAuth | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| Price for gpu compute | not published | $0.219 per GB per month |\n| x402 | no | no |\n| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | Proprietary service under Thunder Compute's Terms and Conditions. The `tnr` CLI on GitHub is MIT |\n| Tools exposed | none | 28 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `io.github.Thunder-Compute/thunder-compute` |\n| Last release | 2026-10-30 | 2026-10-27 |\n| Terms last updated | 2026-09-02 | 2026-09-28 |\n| Privacy policy last updated | 2026-09-28 | 2026-09-28 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | none | 34 stars |\n\n## How the scores have moved\n\n### Cloud Run GPUs\n\nNo score change since it was listed.\n\n### Thunder Compute\n\n- -5.0 on 4 November 2026 (C to D): negative event\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**Cloud Run GPUs.** Serverless GPUs on Cloud Run, an L4 or RTX PRO 6000 per instance, billed per second, scaling to zero and starting in about 5 seconds before the model loads, with a published SLA and IAM. One GPU per instance, 3 GPUs of default quota a region and instance-based billing limit it to small and mid-size models.\n\n**Thunder Compute.** The hosted MCP server signs in with OAuth and separate read and write scopes, and the REST API has a public OpenAPI 3.1 document. No rate limits, SLA or API changelog were found, instance creation has no idempotency key, and the CLI sends error reports to Sentry by default with no documented opt-out.\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### Thunder Compute\n\n1. Call `GET /v2/status` or the `get_availability` tool before creating an instance. Availability can change before launch, and creation fails when a type is sold out.\n2. List instances before retrying a failed create, because the call has no idempotency key.\n3. Pass `public_key` on create. If omitted, the response carries a generated private key that is returned once.\n4. To pause work, create a snapshot, delete the instance and later create a new instance from the snapshot. Snapshot storage keeps billing until deleted.\n5. For headless use set `TNR_API_TOKEN` to a token from the console, and upgrade the CLI to v2.1.0 or later, which stops copying that credential onto instances.\n\n## Questions\n\n### Which is better for AI agents, Cloud Run GPUs or Thunder Compute?\n\nCloud Run GPUs scores 68.4 (B) on agent readiness against Thunder Compute's 51.3 (D), and leads in 6 of 7 scored categories.\n\n### Can an agent call Cloud Run GPUs and Thunder Compute without installing anything?\n\nYes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Thunder Compute at https://api.thundercompute.com:8443/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloud-run-gpus\", \"b\": \"thunder-compute\"}`. From a terminal: `anchor compare cloud-run-gpus thunder-compute`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/thunder-compute.json\n\n## Other comparisons with Cloud Run GPUs or Thunder Compute\n\n- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)\n- [Baseten vs Thunder Compute](https://www.anchorterminal.com/compare/baseten-vs-thunder-compute.md)\n- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)\n- [Beam vs Thunder Compute](https://www.anchorterminal.com/compare/beam-vs-thunder-compute.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs Thunder Compute](https://www.anchorterminal.com/compare/cerebrium-vs-thunder-compute.md)\n- [Cloud Run GPUs vs CoreWeave](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.md)\n- [Cloud Run GPUs vs Crusoe Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.md)\n- [Cloud Run GPUs vs GPUsMarket](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.md)\n- [Cloud Run GPUs vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.md)\n- [Cloud Run GPUs vs Hyperbolic](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.md)\n- [Cloud Run GPUs vs Lambda Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.md)\n- [Cloud Run GPUs vs Massed Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.md)\n- [Cloud Run GPUs vs Nebius AI Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.md)\n- [Cloud Run GPUs vs Northflank](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.md)\n- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md)\n- [CoreWeave vs Thunder Compute](https://www.anchorterminal.com/compare/coreweave-vs-thunder-compute.md)\n- [Crusoe Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/crusoe-cloud-vs-thunder-compute.md)\n- [GPUsMarket vs Thunder Compute](https://www.anchorterminal.com/compare/gpusmarket-vs-thunder-compute.md)\n- [Hugging Face Inference Endpoints vs Thunder Compute](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute.md)\n- [Hyperbolic vs Thunder Compute](https://www.anchorterminal.com/compare/hyperbolic-vs-thunder-compute.md)\n- [Koyeb vs Thunder Compute](https://www.anchorterminal.com/compare/koyeb-vs-thunder-compute.md)\n- [Lambda Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/lambda-vs-thunder-compute.md)\n- [Massed Compute vs Thunder Compute](https://www.anchorterminal.com/compare/massed-compute-vs-thunder-compute.md)\n- [Modal vs Thunder Compute](https://www.anchorterminal.com/compare/modal-vs-thunder-compute.md)\n- [Nebius AI Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-thunder-compute.md)\n- [Northflank vs Thunder Compute](https://www.anchorterminal.com/compare/northflank-vs-thunder-compute.md)\n- [Replicate Deployments vs Thunder Compute](https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute.md)\n- [Runpod vs Thunder Compute](https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.md)\n- [Thunder Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.md)\n- [Thunder Compute vs Vast.ai](https://www.anchorterminal.com/compare/thunder-compute-vs-vast-ai.md)\n- [Thunder Compute vs Verda](https://www.anchorterminal.com/compare/thunder-compute-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 Thunder Compute", "url": "" } ], "description": "Cloud Run GPUs scores 68.4 (B) to Thunder Compute's 51.3 (D) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloud Run GPUs B 68.4", "Thunder Compute D 51.3", "scores" ], "h1": "Cloud Run GPUs vs Thunder Compute", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloud-run-gpus-vs-thunder-compute", "published": "2026-10-01", "section": "tools", "title": "Cloud Run GPUs vs Thunder Compute for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute" }, "tokens": { "markdown": 5150, "slim": 2880 }, "version": 1 }