{ "data": { "category": { "area": "models", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "description": "Clouds that run your own models and jobs on GPUs by the second, as serverless functions, endpoints or rented machines. Compared on GPU types and price per hour, cold starts, scaling and what you have to package.", "indexed": [ { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/3doptix-optical-design.json", "kind": "mcp", "name": "3DOptix", "slug": "3doptix-optical-design", "url": "https://www.anchorterminal.com/tools/3doptix-optical-design" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/amplerun-gpu-rentals.json", "kind": "mcp", "name": "AmpleRun GPU rentals", "slug": "amplerun-gpu-rentals", "url": "https://www.anchorterminal.com/tools/amplerun-gpu-rentals" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fitllm.json", "kind": "mcp", "name": "FitLLM", "slug": "fitllm", "url": "https://www.anchorterminal.com/tools/fitllm" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/framebench.json", "kind": "mcp", "name": "framebench", "slug": "framebench", "url": "https://www.anchorterminal.com/tools/framebench" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/prismnetwork-mcp.json", "kind": "mcp", "name": "prismnetwork.tech MCP server", "slug": "prismnetwork-mcp", "url": "https://www.anchorterminal.com/tools/prismnetwork-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/artibot-zhijiangyun.json", "kind": "mcp", "name": "Zhijiangyun Cloud (智匠云)", "slug": "artibot-zhijiangyun", "url": "https://www.anchorterminal.com/tools/artibot-zhijiangyun" } ], "indexedCount": 6, "json": "https://www.anchorterminal.com/categories/gpu-compute.json", "name": "GPU \u0026 serverless compute", "slug": "gpu-compute", "test": "The same model deployed as an endpoint on each platform, called cold and warm, then scaled to zero. We time cold starts, check the scaling and add up the cost per GPU-hour.", "title": "GPU and serverless compute for AI workloads", "toolCount": 9, "tools": [ "modal-sandboxes", "baseten", "modal", "replicate-deploy", "northflank", "beam", "runpod", "lambda", "koyeb" ], "url": "https://www.anchorterminal.com/categories/gpu-compute" }, "tools": [ { "slug": "modal-sandboxes", "name": "Modal Sandboxes", "vendor": "Modal", "vendorUrl": "https://modal.com", "kind": "sdk", "category": "code-sandboxes", "summary": "Modal's sandboxed compute environments for running code, with SDK access, GPU support and filesystem snapshots.", "url": "https://www.anchorterminal.com/tools/modal-sandboxes", "markdownUrl": "https://www.anchorterminal.com/tools/modal-sandboxes.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/modal-sandboxes.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/modal-sandboxes.json", "repo": "https://github.com/modal-labs/modal-client", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "modal" }, { "registry": "npm", "name": "modal" } ], "auth": "api-key", "authNotes": "No public REST API for sandboxes. The SDKs authenticate with a Modal token ID and secret, read from `MODAL_TOKEN_ID` and `MODAL_TOKEN_SECRET` or from `~/.modal.toml` (written by `modal token set`). Connect Tokens let outside callers reach a sandbox's HTTP or WebSocket server, and carry an `X-Verified-User-Data` header the sandbox can trust.", "pricing": "freemium", "pricingNotes": "Sandboxes cost $0.00003942 a physical core-second (one core is 2 vCPU, minimum 0.125 cores) and $0.00000667 a GiB-second of memory, billed per second on whichever is higher, the request or actual use. GPUs bill at Modal's standard per-second GPU rates. Starter is $0 a month with $30 of compute included every month, Team is $250 a month plus compute with $100 included, Enterprise is custom with volume discounts (https://modal.com/pricing, https://modal.com/docs/guide/sandbox-resources.md).", "priceSummary": "$0.071 / vCPU-hr", "where": "local", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 514, "npmWeekly": 940973, "pypiWeekly": 10146778, "asOf": "2026-09-30" }, "docsUrl": "https://modal.com/docs/guide/sandboxes", "llmsTxt": "https://modal.com/llms.txt", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist", "sandbox.gpu" ], "tags": [ "hosted", "freemium", "free-tier", "python", "typescript", "go", "llms-txt", "enterprise" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 75.6, "grade": "BB", "agentReady": true, "rank": 33, "ranked": true, "rankOf": 452, "categoryRank": 1, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 93, "payments": 40, "reliability": 95, "schema": 79, "security": 76, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "GPU sandboxes at the same per-second rates as the rest of Modal. No REST API, and the JavaScript and Go SDKs are beta.", "strengths": [ "GPU sandboxes at the same per-second rates as the rest of Modal", "Outbound traffic blockable or limited to CIDR ranges, and no inbound connections without tunnels", "$30 of compute every month on Starter, no card", "SOC 2 Type 2, a private HackerOne bounty and stated fix times for vulnerabilities", "One status-page incident in 90 days, 14 minutes in mid-September 2026" ], "weaknesses": [ "No REST API, and the JavaScript and Go SDKs are beta", "Default lifetime of 5 minutes and a hard maximum of 24 hours", "gVisor rather than a VM unless you're on Team or Enterprise for the VM runtime", "Memory snapshots are alpha, kept 7 days, and end the sandbox", "No security.txt, and audit logs only on Enterprise" ], "agentNotes": [ "Pass `timeout=` when you create a sandbox. The default lifetime is 5 minutes", "Set `block_network=True` or a `cidr_allowlist` for untrusted code", "Give a sandbox a `name` so a retried create raises `AlreadyExistsError` instead of starting a second one", "Snapshot the filesystem before the 24-hour limit and start a fresh sandbox from it", "Catch `ResourceExhaustedError` from `Sandbox.create()` on SDK 1.6.0 and later" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75.6 } ], "editorialScores": { "ergonomics": 67, "maintenance": 93, "payments": 40, "reliability": 95, "schema": 79, "security": 76, "transparency": 60 }, "provenanceScore": 88 }, "connect": { "install": "pip install modal # or npm i modal" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/modal-sandboxes" }, "sameCompany": [ "modal" ], "alsoIn": [ "gpu-compute" ], "area": "agent-runtime", "unitPrices": [ { "item": "Sandbox CPU", "unit": "vcpu-hour", "usd": 0.071, "note": "$0.00003942 a physical core-second, one core is 2 vCPU. Memory extra at $0.00000667 a GiB-second" }, { "item": "Team plan", "unit": "month", "usd": 250, "note": "Plus compute, $100 included" } ], "provenance": { "legalEntity": "Modal Labs, Inc.", "domain": "modal.com", "domainRegistered": "1999-03-18", "domainNote": "modal.com was registered in 1999, long before Modal Labs, so the domain was bought later.", "endpointOnVendorDomain": null, "terms": "https://modal.com/legal/terms", "privacy": "https://modal.com/legal/privacy-policy", "statusPage": "https://status.modal.com", "changelog": "https://modal.com/docs/sdk/py/releases", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms (May 2026) name Modal Labs, Inc., a Delaware corporation, under California law.", "Sandboxes are reached through the SDK rather than a documented public endpoint, so there's no endpoint URL to check against the domain.", "modal.com/.well-known/security.txt returns 404. The security guide gives security@modal.com and a private HackerOne programme." ], "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/modal-sandboxes.json", "live": { "slug": "modal-sandboxes", "vendorStatus": { "page": "https://status.modal.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:15.629276461Z" }, "versions": [ { "registry": "npm", "name": "modal", "version": "0.11.0", "seenAt": "2026-10-04T16:33:42.820417551Z" }, { "registry": "pypi", "name": "modal", "version": "1.6.1", "released": "2026-10-03", "seenAt": "2026-10-04T16:33:42.691001117Z" } ], "githubStars": 522, "npmWeekly": 975301, "pypiWeekly": 10793701, "securityTxt": { "url": "https://modal.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:42.140189006Z" }, "llmsTxt": { "url": "https://modal.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:59.208696898Z" }, "domain": { "domain": "modal.com", "registered": "1999-03-18", "source": "https://rdap.verisign.com/com/v1/domain/modal.com", "checkedAt": "2026-10-04T13:03:51.14581991Z" }, "pages": [ { "url": "https://modal.com/docs/sdk/py/releases", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:46:02.530693875Z", "changedAt": "2026-10-04T15:46:02.530693875Z", "fingerprint": "2d8a24963498" }, { "url": "https://modal.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:46:09.066130964Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ebb11d7b0f6a" }, { "url": "https://modal.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:46:05.494045324Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ba881cee4162" }, { "url": "https://modal.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:46:06.7314142Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "94e2edecd464" } ], "updatedAt": "2026-10-04T21:40:15.629276461Z" } }, { "slug": "baseten", "name": "Baseten", "vendor": "Baseten", "vendorUrl": "https://www.baseten.co", "kind": "http-api", "category": "gpu-compute", "summary": "Dedicated model deployments packaged with the open-source Truss framework and served behind a per-model HTTPS endpoint, with autoscaling from zero replicas, async inference, a management API and per-minute GPU billing from T4 to B200.", "url": "https://www.anchorterminal.com/tools/baseten", "markdownUrl": "https://www.anchorterminal.com/tools/baseten.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/baseten.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/baseten.json", "repo": "https://github.com/basetenlabs/truss", "license": "MIT", "transports": [ "http" ], "remoteUrl": "https://api.baseten.co", "packages": [ { "registry": "pypi", "name": "truss" } ], "auth": "api-key", "authNotes": "API key from the workspace settings, sent as `Authorization: Bearer $BASETEN_API_KEY` (preferred) or the legacy `Authorization: Api-Key` scheme. Keys created from 1 October 2026 carry a `b10_` prefix. Inference goes to model-\u003cid\u003e.api.baseten.co and management calls to api.baseten.co.", "pricing": "usage", "pricingNotes": "Basic is $0 a month, pay as you go; Pro and Enterprise add volume discounts. Dedicated deployments bill per minute of replica time, including start-up and idle, and nothing at zero replicas. T4 16 GiB $0.01052 a minute (about $0.63 an hour), L4 24 GiB $0.01414 ($0.85), A10G 24 GiB $0.02012 ($1.21), H100 MIG 40 GiB $0.0625 ($3.75), A100 80 GiB $0.06667 ($4.00), H100 80 GiB $0.10833 ($6.50), B200 180 GiB $0.16633 ($9.98). New accounts get a small credit to try the UI. Model APIs bill per token instead (https://www.baseten.co/pricing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1200, "npmWeekly": null, "pypiWeekly": 74496, "asOf": "2026-09-30" }, "docsUrl": "https://docs.baseten.co", "llmsTxt": "https://docs.baseten.co/llms.txt", "openapi": "https://api.baseten.co/v1/spec", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.serverless", "compute.containers" ], "tags": [ "hosted", "usage-priced", "python", "llms-txt", "open-source", "async-jobs", "webhooks", "enterprise" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 66.7, "grade": "B", "agentReady": false, "rank": 157, "ranked": true, "rankOf": 452, "categoryRank": 1, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 90, "payments": 40, "reliability": 80, "schema": 84, "security": 82, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -5, "negativeNotes": [ "-5: a GitHub personal access token for `basetenbot`, exposed in a public Harbor image since March 2023, gave admin and push access to Baseten's main product repository, the GitOps repository that drives its clusters, its Homebrew tap and per-customer private repositories. Reported on 2026-07-13, revoked on 2026-07-14, no misuse found, published with Baseten's approval in September 2026. Deducted less because the fix was quick and documented (https://www.strix.ai/blog/baseten-harbor-github-pat-takeover)" ], "verdict": "Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.", "strengths": [ "Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026", "Public OpenAPI spec for the management API at api.baseten.co/v1/spec, and llms.txt with Markdown twins", "Rate limits published per endpoint with a `retry_after` field on 429", "Free starting credits with no payment method needed until they run out", "Truss (MIT) keeps the model package portable, with three releases in September 2026" ], "weaknesses": [ "H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed", "21 status-page incidents between 31 July and 29 September 2026, mostly single-cluster 5xx", "A bot token with admin access to the product and GitOps repositories sat exposed from March 2023 until July 2026", "No pagination on management list endpoints and no idempotency keys", "No SLA below Enterprise, no bug bounty and no security.txt" ], "agentNotes": [ "Create a team key with inference-only permission for calling models and keep full-access keys out of the agent", "Sleep for `retry_after` seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute", "Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code", "Set `scale_down_delay` below the 900-second default or every burst bills 15 idle minutes", "Send payloads over 256 KiB to `/predict`, not `/async_predict`, unless support has raised the async limit" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.7 } ], "editorialScores": { "ergonomics": 55, "maintenance": 90, "payments": 40, "reliability": 80, "schema": 84, "security": 82, "transparency": 58 }, "provenanceScore": 75 }, "connect": { "install": "pip install truss", "http": "curl -X POST \"https://model-$BASETEN_MODEL_ID.api.baseten.co/environments/production/predict\" \\\n -H \"Authorization: Bearer $BASETEN_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"prompt\":\"Hello, world!\"}'" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/baseten" }, "area": "models", "unitPrices": [ { "item": "H100 80 GiB", "unit": "gpu-hour", "usd": 6.5, "note": "$0.10833 a minute" }, { "item": "B200 180 GiB", "unit": "gpu-hour", "usd": 9.98, "note": "$0.16633 a minute" }, { "item": "A100 80 GiB", "unit": "gpu-hour", "usd": 4, "note": "$0.06667 a minute" }, { "item": "H100 MIG 40 GiB", "unit": "gpu-hour", "usd": 3.75, "note": "$0.0625 a minute" }, { "item": "A10G 24 GiB", "unit": "gpu-hour", "usd": 1.21, "note": "$0.02012 a minute" }, { "item": "L4 24 GiB", "unit": "gpu-hour", "usd": 0.85, "note": "$0.01414 a minute" }, { "item": "T4 16 GiB", "unit": "gpu-hour", "usd": 0.63, "note": "$0.01052 a minute" } ], "provenance": { "legalEntity": "Baseten Labs, Inc.", "domain": "baseten.co", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.baseten.co/terms-and-conditions/", "privacy": "https://www.baseten.co/privacy-policy/", "statusPage": "https://status.baseten.co", "changelog": "https://www.baseten.co/changelog/", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms name Baseten Labs, Inc. under California law with venue in San Francisco. The privacy policy gives 560 Davis St., Suite 250, San Francisco.", "Inference runs on model-\u003cid\u003e.api.baseten.co, a subdomain of the vendor domain.", "www.baseten.co/.well-known/security.txt returns 404.", "The .co registry's RDAP server couldn't be reached, so the registration date is unrecorded." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/baseten.json", "live": { "slug": "baseten", "probe": { "target": "https://api.baseten.co", "method": "get", "lastAt": "2026-10-04T21:48:23.617009636Z", "lastOk": true, "lastStatus": 202, "lastMs": 437, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 455, "p95ms24h": 505, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://status.baseten.co", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T21:39:50.132367632Z" }, "versions": [ { "registry": "github", "name": "basetenlabs/truss", "version": "v0.18.32", "released": "2026-09-28", "seenAt": "2026-10-04T16:22:03.609365578Z" }, { "registry": "pypi", "name": "truss", "version": "0.18.32", "released": "2026-09-28", "seenAt": "2026-10-04T16:22:01.591112358Z" } ], "githubStars": 1207, "pypiWeekly": 67780, "securityTxt": { "url": "https://baseten.co/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:51.119519284Z" }, "llmsTxt": { "url": "https://docs.baseten.co/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:19.413388797Z" }, "domain": { "domain": "baseten.co", "checkedAt": "2026-10-04T13:09:05.701625104Z" }, "pages": [ { "url": "https://www.baseten.co/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:49:24.926514442Z", "changedAt": "2026-10-03T15:37:20.756910326Z", "fingerprint": "6cee5804197b" }, { "url": "https://www.baseten.co/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:49:27.25006425Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "990de850b24f" }, { "url": "https://www.baseten.co/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:49:29.099232624Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "66effb5a49f2" }, { "url": "https://www.baseten.co/terms-and-conditions/", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:49:31.355740184Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "38417e30dfca" } ], "updatedAt": "2026-10-04T21:48:23.617009636Z" } }, { "slug": "modal", "name": "Modal", "vendor": "Modal", "vendorUrl": "https://modal.com", "kind": "platform", "category": "gpu-compute", "summary": "Serverless functions, web endpoints, servers and GPU jobs from a Python decorator, with JavaScript and Go SDKs.", "url": "https://www.anchorterminal.com/tools/modal", "markdownUrl": "https://www.anchorterminal.com/tools/modal.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/modal.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/modal.json", "repo": "https://github.com/modal-labs/modal-client", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "modal" }, { "registry": "npm", "name": "modal" } ], "auth": "api-key", "authNotes": "No public REST API for deploying. The SDKs and CLI authenticate with a token ID and secret from `modal token new`, read from `MODAL_TOKEN_ID` and `MODAL_TOKEN_SECRET` or `~/.modal.toml`; tokens can carry a TTL. Deployed web endpoints are open by default and can be locked with proxy tokens sent as `Modal-Key` and `Modal-Secret` headers. Servers and Endpoints require a proxy token by default, sent as `Authorization: Bearer \u003cid\u003e.\u003csecret\u003e`.", "pricing": "freemium", "pricingNotes": "Starter is $0 a month with $30 of compute included every month, 3 seats, 100 containers and 10 concurrent GPUs. Team is $250 a month plus compute with $100 included, unlimited seats, 5,000 containers and 50 concurrent GPUs. Enterprise is custom. GPUs bill per second with nothing charged at zero containers. T4 $0.000164, L4 $0.000222, A10 $0.000306, L40S $0.000542, A100 40 GB $0.000583, A100 80 GB $0.000694, RTX PRO 6000 $0.000842, H100 $0.001097, H200 $0.001261, B200 $0.001736 and B300 $0.001972 a second. The pricing page lists CPU at $0.0000131 a core-second (0.125 core minimum per container) and memory at $0.00000222 a GiB-second, and volumes at $0.09 a GiB-month after 1 TiB free (https://modal.com/pricing).", "priceSummary": "$250 / mo", "where": "local", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 514, "npmWeekly": 940973, "pypiWeekly": 10146778, "asOf": "2026-09-30" }, "docsUrl": "https://modal.com/docs/guide", "llmsTxt": "https://modal.com/llms.txt", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "tags": [ "hosted", "freemium", "free-tier", "no-card", "python", "typescript", "go", "llms-txt", "enterprise" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 63.8, "grade": "B", "agentReady": false, "rank": 195, "ranked": true, "rankOf": 452, "categoryRank": 2, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 85, "payments": 30, "reliability": 70, "schema": 70, "security": 68, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Scale to zero by default, per-second billing and about one-second container boots. No REST API or OpenAPI spec for deploying or invoking Functions.", "strengths": [ "Scale to zero by default, per-second billing and about one-second container boots", "Retention stated per data type (inputs and outputs up to 7 days, logs 1 to 30 days)", "Python, JavaScript and Go SDKs, with llms.txt and dated release notes", "Four short incidents on the status page between July and September 2026", "SOC 2 Type 2, a private HackerOne programme and published disclosure response times" ], "weaknesses": [ "No REST API or OpenAPI spec for deploying or invoking Functions", "Web endpoints are open by default until proxy tokens are added", "RBAC, audit logs and HIPAA only on Enterprise", "No published SLA, and Starter caps concurrent GPUs at 10", "Region pinning costs 1.15 to 1.75 times the base price" ], "agentNotes": [ "Create a proxy token and require it on every web endpoint before sharing the URL; endpoints are public by default", "Pass a list to `gpu=` (for example `[\"H100\", \"A100-80GB\"]`) so a job still runs when the first choice is unavailable", "Set `scaledown_window` and `min_containers` explicitly; the defaults are 60 seconds and 0", "Use `.spawn()` and poll the call ID for long work instead of holding a web request open", "Keep web endpoint traffic under 200 requests a second or ask Modal to raise the limit" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.8 } ], "editorialScores": { "ergonomics": 57, "maintenance": 85, "payments": 30, "reliability": 70, "schema": 70, "security": 68, "transparency": 63 }, "provenanceScore": 75 }, "connect": { "install": "pip install modal \u0026\u0026 modal setup", "http": "curl -X POST \"https://$MODAL_WORKSPACE--my-app-predict.modal.run\" \\\n -H \"Modal-Key: $MODAL_PROXY_KEY\" -H \"Modal-Secret: $MODAL_PROXY_SECRET\" \\\n -H \"Content-Type: application/json\" -d '{\"prompt\":\"hello\"}'" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/modal" }, "sameCompany": [ "modal-sandboxes" ], "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 3.95, "note": "$0.001097 a second, may be upgraded to H200 at the same price" }, { "item": "H200 141 GB", "unit": "gpu-hour", "usd": 4.54, "note": "$0.001261 a second" }, { "item": "B200 180 GB", "unit": "gpu-hour", "usd": 6.25, "note": "$0.001736 a second" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 2.5, "note": "$0.000694 a second" }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 1.95, "note": "$0.000542 a second" }, { "item": "L4 24 GB", "unit": "gpu-hour", "usd": 0.8, "note": "$0.000222 a second" }, { "item": "T4 16 GB", "unit": "gpu-hour", "usd": 0.59, "note": "$0.000164 a second" }, { "item": "Team plan", "unit": "month", "usd": 250, "note": "Plus compute, $100 included, 50 concurrent GPUs" } ], "provenance": { "legalEntity": "Modal Labs, Inc.", "domain": "modal.com", "domainRegistered": "1999-03-18", "domainNote": "modal.com was registered in 1999, long before Modal Labs, so the domain was bought later.", "endpointOnVendorDomain": false, "terms": "https://modal.com/legal/terms", "privacy": "https://modal.com/legal/privacy-policy", "statusPage": "https://status.modal.com", "changelog": "https://modal.com/docs/sdk/py/releases", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms (May 2026) name Modal Labs, Inc., a Delaware corporation, under California law.", "Deployed web endpoints and Servers are served from *.modal.run, a separate domain from modal.com. Deployment itself goes through the SDK, so there's no public API base URL to check.", "modal.com/.well-known/security.txt returns 404. The security guide gives security@modal.com and a private HackerOne programme.", "Modal Sandboxes are listed separately under code sandboxes." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/modal.json", "live": { "slug": "modal", "vendorStatus": { "page": "https://status.modal.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T18:12:01.451022336Z" }, "versions": [ { "registry": "npm", "name": "modal", "version": "0.11.0", "seenAt": "2026-10-04T16:33:46.797593577Z" }, { "registry": "pypi", "name": "modal", "version": "1.6.1", "released": "2026-10-03", "seenAt": "2026-10-04T16:33:46.666636627Z" } ], "githubStars": 522, "npmWeekly": 975301, "pypiWeekly": 10793701, "securityTxt": { "url": "https://modal.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:42.140189006Z" }, "llmsTxt": { "url": "https://modal.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:01.18366808Z" }, "domain": { "domain": "modal.com", "registered": "1999-03-18", "source": "https://rdap.verisign.com/com/v1/domain/modal.com", "checkedAt": "2026-10-04T13:03:51.14581991Z" }, "updatedAt": "2026-10-04T18:12:01.451022336Z" } }, { "slug": "replicate-deploy", "name": "Replicate Deployments", "vendor": "Replicate", "vendorUrl": "https://replicate.com", "kind": "http-api", "category": "gpu-compute", "summary": "Replicate's service for deploying and running custom models.", "url": "https://www.anchorterminal.com/tools/replicate-deploy", "markdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json", "repo": "https://github.com/replicate/cog", "license": "Apache-2.0", "transports": [ "http", "sse", "stdio" ], "remoteUrl": "https://api.replicate.com/v1", "packages": [ { "registry": "npm", "name": "replicate" }, { "registry": "pypi", "name": "replicate" }, { "registry": "npm", "name": "replicate-mcp" } ], "auth": "api-key", "authNotes": "Bearer API token on every call to api.replicate.com. `cog push` uses the same token to upload a model image. The hosted MCP at https://mcp.replicate.com/sse asks for the token in a browser flow and holds it for the client; the local `replicate-mcp` package reads `REPLICATE_API_TOKEN`.", "pricing": "usage", "pricingNotes": "Private models and deployments bill per second for the whole time an instance is up, set-up and idle included, from prepaid credit or monthly in arrears. CPU $0.000100 a second ($0.36 an hour), T4 $0.000225 ($0.81), L40S $0.000975 ($3.51), A100 80 GB $0.001400 ($5.04), H100 $0.001525 ($5.49), 2x L40S $0.001950 ($7.02), 2x A100 $0.002800 ($10.08). 2x H100 ($10.98), 4x and 8x L40S, A100 and H100 up to $43.92 an hour need a committed-spend contract. Fast-booting fine-tunes bill only while active. Public models bill only active time and not failures (https://replicate.com/pricing, https://replicate.com/docs/topics/billing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 9500, "npmWeekly": 634116, "pypiWeekly": 386704, "asOf": "2026-09-30" }, "docsUrl": "https://replicate.com/docs/topics/deployments", "llmsTxt": "https://replicate.com/docs/llms.txt", "openapi": "https://api.replicate.com/openapi.json", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.serverless", "compute.containers" ], "tags": [ "hosted", "usage-priced", "mcp", "llms-txt", "openapi", "python", "typescript", "async-jobs", "webhooks", "open-source" ], "lastRelease": "2026-09-22", "graded": true, "anchor": { "graded": true, "score": 63.7, "grade": "B", "agentReady": false, "rank": 197, "ranked": true, "rankOf": 452, "categoryRank": 3, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 70, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 80 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "OpenAPI file, llms.txt and an MCP server with a two-tool code mode. Private instances bill set-up and idle time, H100 at $5.49 an hour.", "strengths": [ "OpenAPI file, llms.txt and an MCP server with a two-tool code mode", "Deployment min and max instances settable over the API, 0 allowed", "API prediction data deleted after one hour by default", "Published limits, 600 prediction creates and 3,000 other calls a minute", "Leaked tokens found on GitHub are disabled automatically" ], "weaknesses": [ "Private instances bill set-up and idle time, H100 at $5.49 an hour", "API tokens have no scopes, expiry or audit log", "Changelog silent since 21 April 2026", "Only T4, L40S, A100 and H100, and more than 2 GPUs needs a committed-spend contract", "Two September 2026 incidents ran 15 and 20 hours, both marked minor" ], "agentNotes": [ "List `GET /v1/hardware` first and use the returned `sku` in the deployment body", "Set `min_instances` to 0 for bursty work; a warm H100 bills $5.49 an hour whether called or not", "Send `Prefer: wait` on deployment predictions to block instead of polling", "Copy outputs within an hour; API prediction data is deleted after that", "Wait for the reset time in the 429 body before retrying; prediction creates cap at 600 a minute" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.7 } ], "editorialScores": { "ergonomics": 68, "maintenance": 70, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 69 }, "provenanceScore": 90 }, "connect": { "install": "pip install cog replicate", "http": "curl -X POST \"https://api.replicate.com/v1/deployments/$REPLICATE_OWNER/my-deployment/predictions\" \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" -H \"Content-Type: application/json\" -H \"Prefer: wait\" \\\n -d '{\"input\":{\"prompt\":\"hello\"}}'", "claudeCode": "claude mcp add replicate https://mcp.replicate.com/sse --transport sse --scope user", "config": { "mcpServers": { "replicate": { "args": [ "-y", "replicate-mcp" ], "command": "npx", "env": { "REPLICATE_API_TOKEN": "${REPLICATE_API_TOKEN}" } } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/replicate-deploy" }, "sameCompany": [ "replicate-image", "replicate-musicgen" ], "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 5.49, "note": "$0.001525 a second, including set-up and idle" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 5.04, "note": "$0.001400 a second" }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 3.51, "note": "$0.000975 a second" }, { "item": "T4 16 GB", "unit": "gpu-hour", "usd": 0.81, "note": "$0.000225 a second" } ], "provenance": { "legalEntity": "Replicate, LLC", "domain": "replicate.com", "domainRegistered": "1998-05-26", "domainNote": "replicate.com was registered in 1998, long before Replicate the company existed.", "endpointOnVendorDomain": true, "terms": "https://replicate.com/terms", "privacy": "https://replicate.com/privacy", "statusPage": "https://replicatestatus.com", "changelog": "https://replicate.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms last updated 2026-04-01 name Replicate, LLC as the contracting party.", "replicatestatus.com redirects to Cloudflare's status page filtered to Replicate.", "Replicate's hosted image and music models are listed separately under image generation and music generation." ], "score": 90 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/replicate-deploy.json", "live": { "slug": "replicate-deploy", "probe": { "target": "https://api.replicate.com/v1", "method": "get", "lastAt": "2026-10-04T21:48:35.132540284Z", "lastOk": true, "lastStatus": 401, "lastMs": 143, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 139, "p95ms24h": 327, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://replicatestatus.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:25.933184888Z" }, "versions": [ { "registry": "github", "name": "replicate/cog", "version": "v0.23.0", "released": "2026-09-22", "seenAt": "2026-10-04T16:38:03.363821386Z" }, { "registry": "npm", "name": "replicate", "version": "1.4.0", "seenAt": "2026-10-04T16:38:01.019271447Z" }, { "registry": "npm", "name": "replicate-mcp", "version": "0.9.0", "seenAt": "2026-10-04T16:38:03.126836564Z" }, { "registry": "pypi", "name": "replicate", "version": "1.0.7", "released": "2025-05-27", "seenAt": "2026-10-04T16:38:01.981507625Z" } ], "githubStars": 9486, "npmWeekly": 705916, "pypiWeekly": 374867, "securityTxt": { "url": "https://replicate.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:45.229571506Z" }, "llmsTxt": { "url": "https://replicate.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:09.902788266Z" }, "domain": { "domain": "replicate.com", "registered": "1998-05-26", "source": "https://rdap.verisign.com/com/v1/domain/replicate.com", "checkedAt": "2026-10-04T13:07:04.742407865Z" }, "pages": [ { "url": "https://replicate.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:47:17.68615995Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "490f4836aca3" }, { "url": "https://replicate.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:47:19.974502738Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3f1305f154be" }, { "url": "https://replicate.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:47:22.274270654Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8e299fbc64eb" }, { "url": "https://replicate.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:47:23.877388602Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ea48efe3382b" } ], "updatedAt": "2026-10-04T21:48:35.132540284Z" } }, { "slug": "northflank", "name": "Northflank", "vendor": "Northflank", "vendorUrl": "https://northflank.com", "kind": "platform", "category": "gpu-compute", "summary": "Platform for deploying services, jobs and databases from Git or container images, in managed or customer-owned infrastructure. Supports GPU workloads and sandboxes.", "url": "https://www.anchorterminal.com/tools/northflank", "markdownUrl": "https://www.anchorterminal.com/tools/northflank.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/northflank.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/northflank.json", "transports": [ "http" ], "remoteUrl": "https://api.northflank.com/v1", "packages": [ { "registry": "npm", "name": "@northflank/cli" }, { "registry": "npm", "name": "@northflank/js-client" } ], "auth": "pat", "authNotes": "Personal API token from account settings, or a team token issued under an API role, sent as `Authorization: Bearer` to api.northflank.com/v1. Rate limit headers `x-ratelimit-limit`, `x-ratelimit-remaining` and `x-ratelimit-reset` come back on every response.", "pricing": "freemium", "pricingNotes": "Pay as you go, pro-rated to the second and charged at the end of the monthly cycle. CPU $0.01667 a vCPU-hour and memory $0.00833 a GB-hour, from a 1 vCPU 2 GB plan at $24 a month to 32 vCPU 499 GB at $3,312. GPUs an hour are L4 24 GB $0.80, A100 40 GB $1.42, A100 80 GB $1.76, H100 80 GB $2.74, RTX PRO 6000 96 GB $3.00. SSD $0.15 a GB-month and egress $0.06 a GB. A free sandbox tier gives 2 services, 1 database and 2 cron jobs. Running in your own cloud adds no platform fee on pay as you go (https://northflank.com/pricing).", "priceSummary": "$0.0167 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 19190, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://northflank.com/docs/v1/application", "llmsTxt": "https://northflank.com/docs/llms.txt", "openapi": "https://api.northflank.com/v1/swagger-json", "capabilities": [ "compute.gpu", "compute.containers", "compute.batch", "compute.endpoints" ], "tags": [ "hosted", "freemium", "free-tier", "openapi", "llms-txt", "typescript", "uk", "enterprise" ], "lastRelease": "2026-09-24", "graded": true, "anchor": { "graded": true, "score": 61.8, "grade": "C", "agentReady": false, "rank": 224, "ranked": true, "rankOf": 452, "categoryRank": 4, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 48, "maintenance": 65, "payments": 30, "reliability": 65, "schema": 81, "security": 75, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "OpenAPI 3.0 with over 100 paths, enums and `per_page`, `page` and `cursor` on every list. No scale to zero for services; minimum instances must be at least 1.", "strengths": [ "OpenAPI 3.0 with over 100 paths, enums and `per_page`, `page` and `cursor` on every list", "Team API tokens under API roles with granular permissions, plus audit logs", "Runs in Northflank's cloud or your own AWS, GCP, Azure or bare metal", "llms.txt and a Markdown twin for every docs page", "H100 at $2.74 and A100 80 GB at $1.76 an hour, billed per second" ], "weaknesses": [ "No scale to zero for services; minimum instances must be at least 1", "1,000 API requests an hour by default", "One partial outage of workload starts across regions on 5 August 2026", "Terms and privacy policy unchanged since 1 March 2021, and no security.txt", "No error schemas in the spec, no idempotency keys, no Python SDK" ], "agentNotes": [ "Issue the agent a team token under an API role limited to one project, not a personal token", "Read `x-ratelimit-remaining` and wait `x-ratelimit-reset` seconds on a 429; the default is 1,000 calls an hour", "Page lists with `per_page` up to 100 and the returned `cursor` instead of numbered pages", "Use a job, not a service, for anything that finishes; services bill until paused or deleted", "Fetch any docs page with .md appended to get Markdown" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.8 } ], "editorialScores": { "ergonomics": 48, "maintenance": 65, "payments": 30, "reliability": 65, "schema": 81, "security": 75, "transparency": 33 }, "provenanceScore": 86 }, "connect": { "install": "npm i -g @northflank/cli \u0026\u0026 northflank login", "http": "curl \"https://api.northflank.com/v1/projects\" -H \"Authorization: Bearer $NORTHFLANK_TOKEN\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/northflank" }, "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 2.74, "note": "Billed per second" }, { "item": "RTX PRO 6000 96 GB", "unit": "gpu-hour", "usd": 3 }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 1.76 }, { "item": "A100 40 GB", "unit": "gpu-hour", "usd": 1.42 }, { "item": "L4 24 GB", "unit": "gpu-hour", "usd": 0.8 }, { "item": "CPU", "unit": "vcpu-hour", "usd": 0.01667, "note": "Memory extra at $0.00833 a GB-hour" }, { "item": "SSD storage", "unit": "gb-month", "usd": 0.15 }, { "item": "Egress", "unit": "gb", "usd": 0.06 } ], "provenance": { "legalEntity": "Northflank Ltd", "domain": "northflank.com", "domainRegistered": "2019-03-31", "endpointOnVendorDomain": true, "terms": "https://northflank.com/legal/terms", "privacy": "https://northflank.com/legal/privacy", "statusPage": "https://status.northflank.com", "changelog": "https://northflank.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms and privacy policy, both dated 1 March 2021, name Northflank Ltd, company number 11918540, 20-22 Wenlock Road, London N1 7GU, with legal@northflank.com as contact.", "The API runs on api.northflank.com, a subdomain of the vendor domain.", "northflank.com/.well-known/security.txt returns 404.", "No public source repository for the platform; the CLI and JavaScript client are published on npm." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/northflank.json", "live": { "slug": "northflank", "probe": { "target": "https://api.northflank.com/v1", "method": "get", "lastAt": "2026-10-04T21:48:32.775215095Z", "lastOk": true, "lastStatus": 200, "lastMs": 194, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 36, "p95ms24h": 194, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://status.northflank.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:16.455763445Z" }, "versions": [ { "registry": "npm", "name": "@northflank/cli", "version": "0.13.0", "seenAt": "2026-10-04T16:34:31.591987754Z" }, { "registry": "npm", "name": "@northflank/js-client", "version": "0.11.0", "seenAt": "2026-10-04T16:34:32.039826266Z" } ], "npmWeekly": 5805, "securityTxt": { "url": "https://northflank.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:44.462143205Z" }, "llmsTxt": { "url": "https://northflank.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:03.861255438Z" }, "domain": { "domain": "northflank.com", "registered": "2019-03-31", "source": "https://rdap.verisign.com/com/v1/domain/northflank.com", "checkedAt": "2026-10-04T13:08:04.961258123Z" }, "pages": [ { "url": "https://northflank.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:46:13.215877744Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dded57d72d65" }, { "url": "https://northflank.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:46:19.316082226Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "83f74eaab49c" }, { "url": "https://northflank.com/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:46:15.370395868Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d3ee323ae832" }, { "url": "https://northflank.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:46:17.302681514Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ead1ffa17ca6" } ], "updatedAt": "2026-10-04T21:48:32.775215095Z" } }, { "slug": "beam", "name": "Beam", "vendor": "Beam", "vendorUrl": "https://www.beam.cloud", "kind": "platform", "category": "gpu-compute", "summary": "Serverless GPU endpoints, task queues, functions, pods and sandboxes from Python decorators, on the open-source beta9 runtime.", "url": "https://www.anchorterminal.com/tools/beam", "markdownUrl": "https://www.anchorterminal.com/tools/beam.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/beam.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/beam.json", "repo": "https://github.com/beam-cloud/beta9", "license": "AGPL-3.0", "transports": [ "http" ], "remoteUrl": "https://app.beam.cloud/api/v1", "packages": [ { "registry": "pypi", "name": "beam-client" } ], "auth": "api-key", "authNotes": "API token from platform.beam.cloud, read from `BEAM_TOKEN` by the SDK and CLI or stored by `beam login` in `~/.beam/config.ini`, with named contexts for several workspaces. Deployed endpoints take the same token as `Authorization: Bearer`. The TypeScript SDK sets `beamOpts.token` server-side.", "pricing": "freemium", "pricingNotes": "Developer plan is free plus usage, Team $89 a month plus usage, Growth on request. Billed by the millisecond only while a container runs, which includes `on_start` and `keep_warm_seconds`; cold starts and image pulls aren't billed. Serverless GPUs are RTX 4090 24 GB $0.000192 a second ($0.69 an hour), RTX 5090 32 GB $0.000303 ($1.09), H100 PCIe 80 GB $0.000972 ($3.50). Reserved on-demand machines from $0.44 an hour (RTX 4090), $1.36 (A100 80 GB), $1.83 (H100 PCIe), $2.09 (H200), $4.11 (B200), billed until released even when idle. CPU $0.0000125 a core-second and RAM $0.0000021 a GiB-second on CPU-only work, $0.000105 and $0.0000055 when attached to a GPU, $0.0000375 and $0.0000064 in sandboxes. Storage 1 TB included, then $0.021 a GB-month (https://www.beam.cloud/pricing, https://docs.beam.cloud/v2/resources/pricing-and-billing).", "priceSummary": "$0.045 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1800, "npmWeekly": null, "pypiWeekly": 8481, "asOf": "2026-09-30" }, "docsUrl": "https://docs.beam.cloud", "llmsTxt": "https://docs.beam.cloud/llms.txt", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "tags": [ "hosted", "freemium", "free-tier", "open-source", "self-hosted", "python", "typescript", "llms-txt", "async-jobs" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 55.5, "grade": "C", "agentReady": false, "rank": 313, "ranked": true, "rankOf": 452, "categoryRank": 5, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 85, "payments": 40, "reliability": 55, "schema": 58, "security": 50, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -2, "negativeNotes": [ "-2: `beam deploy --format json` writes the full workspace bearer token into the JSON logs array that CI systems keep. Filed by a Beam engineer on 2026-08-04 and still open on 2026-10-01 (https://github.com/beam-cloud/beta9/issues/1828)" ], "verdict": "Per-millisecond billing with cold starts and image pulls free, H100 PCIe at $3.50 and RTX 4090 at $0.69 an hour. No published request rate limits, 429 handling or SLA.", "strengths": [ "Per-millisecond billing with cold starts and image pulls free, H100 PCIe at $3.50 and RTX 4090 at $0.69 an hour", "Free Developer plan with no card required", "beta9, the engine the hosted cloud runs on, is AGPL-3.0 and self-hostable", "Workspace REST API and an official MCP server, local or remote, on the same token", "Privacy policy with retention periods per category and a published subprocessor list" ], "weaknesses": [ "No published request rate limits, 429 handling or SLA", "No public changelog or deprecation notices; releases show up only on PyPI and GitHub", "Tokens have no documented scopes or read-only mode", "`beam deploy --format json` leaks the workspace token into its logs, open since 4 August 2026", "Status page silent since June 2025 despite sign-up failures reported on GitHub in August 2026" ], "agentNotes": [ "Check the response body for `ok: false` on gateway calls; a failure can arrive as HTTP 200", "Don't pipe `beam deploy --format json` output into CI logs, since it contains the workspace token", "Route anything over 180 seconds to a task queue and poll the task instead of holding the endpoint request", "Set `keep_warm_seconds` deliberately; the 180-second endpoint default bills three minutes of GPU after every call", "Pass `gpu=[\"RTX4090\", \"A10G\"]` so a job still schedules when one type is out" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.5 } ], "editorialScores": { "ergonomics": 58, "maintenance": 85, "payments": 40, "reliability": 55, "schema": 58, "security": 50, "transparency": 71 }, "provenanceScore": 76 }, "connect": { "install": "pip install beam-client \u0026\u0026 beam login", "http": "curl -X POST \"https://my-function-$BEAM_DEPLOYMENT_ID-v1.app.beam.cloud\" \\\n -H \"Authorization: Bearer $BEAM_TOKEN\" -H \"Content-Type: application/json\" \\\n -d '{\"x\":10}'" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/beam" }, "area": "models", "unitPrices": [ { "item": "H100 PCIe 80 GB serverless", "unit": "gpu-hour", "usd": 3.5, "note": "$0.000972 a second" }, { "item": "RTX 5090 32 GB serverless", "unit": "gpu-hour", "usd": 1.09, "note": "$0.000303 a second" }, { "item": "RTX 4090 24 GB serverless", "unit": "gpu-hour", "usd": 0.69, "note": "$0.000192 a second" }, { "item": "B200 180 GB reserved machine", "unit": "gpu-hour", "usd": 4.11, "note": "From price, billed while reserved" }, { "item": "H200 141 GB reserved machine", "unit": "gpu-hour", "usd": 2.09, "note": "From price, billed while reserved" }, { "item": "A100 80 GB reserved machine", "unit": "gpu-hour", "usd": 1.36, "note": "From price, billed while reserved" }, { "item": "CPU-only compute", "unit": "vcpu-hour", "usd": 0.045, "note": "$0.0000125 a core-second, RAM extra at $0.0000021 a GiB-second" }, { "item": "Team plan", "unit": "month", "usd": 89, "note": "Plus usage" } ], "provenance": { "legalEntity": "Smartshare, Inc.", "domain": "beam.cloud", "domainRegistered": "2019-07-31", "endpointOnVendorDomain": true, "terms": "https://docs.beam.cloud/v2/security/terms-and-conditions", "privacy": "https://docs.beam.cloud/v2/security/privacy-policy", "statusPage": "https://status.beam.cloud", "changelog": "", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms dated 14 September 2026 name Smartshare, Inc., a Delaware corporation doing business as Beam. The site footer reads © 2026 Smartshare, Inc.", "Deployed endpoints run on app.beam.cloud, a subdomain of the vendor domain. There's no public REST base URL for deploying.", "www.beam.cloud/.well-known/security.txt and www.beam.cloud/terms return 404; the legal pages live under docs.beam.cloud.", "No public changelog found; releases show up as commits in the beam-client and beta9 repositories." ], "score": 76 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/beam.json", "live": { "slug": "beam", "probe": { "target": "https://app.beam.cloud/api/v1", "method": "get", "lastAt": "2026-10-04T21:48:23.649798268Z", "lastOk": true, "lastStatus": 404, "lastMs": 277, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 259, "p95ms24h": 323, "samples24h": 272, "samples30d": 618, "days": [ { "date": "2026-10-02", "probes": 100, "ok": 100 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://status.beam.cloud", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T21:39:50.317551159Z" }, "versions": [ { "registry": "github", "name": "beam-cloud/beta9", "version": "worker-0.1.781", "released": "2026-10-03", "seenAt": "2026-10-04T16:22:06.02863332Z" }, { "registry": "pypi", "name": "beam-client", "version": "0.2.217", "released": "2026-10-02", "seenAt": "2026-10-04T16:22:05.839399711Z" } ], "githubStars": 1802, "pypiWeekly": 9877, "securityTxt": { "url": "https://beam.cloud/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:16:04.647716161Z" }, "llmsTxt": { "url": "https://docs.beam.cloud/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:19.657901017Z" }, "domain": { "domain": "beam.cloud", "registered": "2019-07-31", "source": "https://rdap.registry.cloud/rdap/domain/beam.cloud", "checkedAt": "2026-10-04T13:04:15.987834596Z" }, "pages": [ { "url": "https://docs.beam.cloud/v2/resources/pricing-and-billing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:43:14.08690057Z", "changedAt": "2026-10-04T15:43:14.08690057Z", "fingerprint": "9430ae529da0" }, { "url": "https://www.beam.cloud/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:49:25.671086961Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dedbd2b07b0a" }, { "url": "https://docs.beam.cloud/v2/security/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:43:16.313382922Z", "changedAt": "2026-10-04T15:43:16.313382922Z", "fingerprint": "4072b33654b6" }, { "url": "https://docs.beam.cloud/v2/security/terms-and-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:43:18.294864193Z", "changedAt": "2026-10-04T15:43:18.294864193Z", "fingerprint": "988292e328cf" } ], "updatedAt": "2026-10-04T21:48:23.649798268Z" } }, { "slug": "runpod", "name": "Runpod", "vendor": "Runpod", "vendorUrl": "https://www.runpod.io", "kind": "http-api", "category": "gpu-compute", "summary": "Serverless GPU endpoints, queue-based or load-balanced, and rented GPU Pods, billed per second from prepaid credit.", "url": "https://www.anchorterminal.com/tools/runpod", "markdownUrl": "https://www.anchorterminal.com/tools/runpod.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/runpod.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/runpod.json", "repo": "https://github.com/runpod/runpod-python", "license": "MIT", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.runpod.ai/v2", "packages": [ { "registry": "pypi", "name": "runpod" }, { "registry": "npm", "name": "runpod-sdk" }, { "registry": "npm", "name": "@runpod/mcp-server" }, { "registry": "pypi", "name": "runpod-flash" } ], "auth": "mixed", "authNotes": "API key from the console sent as `Authorization: Bearer` to serverless endpoints at api.runpod.ai/v2/\u003cendpoint-id\u003e and to the management REST API v2 at api.runpod.io/v2. Keys can be All, Read Only or Restricted per serverless endpoint. The deprecated GraphQL API takes the key as `?api_key=` in the URL. The hosted MCP server at mcp.getrunpod.io signs in with OAuth (Sign in with Runpod) or takes an API key as a Bearer header; the local `@runpod/mcp-server` reads `RUNPOD_API_KEY`.", "pricing": "usage", "pricingNotes": "Prepaid credit, billed per second and rounded up to the nearest second, with no data transfer fees and no free tier. Serverless flex workers an hour are 16 GB A4000 class $0.58, L4, A5000 or RTX 3090 $0.69, RTX 4090 $1.10, RTX Pro 4500 $1.15, A6000 or A40 $1.22, RTX 5090 $1.58, L40, L40S or RTX 6000 Ada $1.75, A100 80 GB $2.72, RTX Pro 6000 $3.49, H100 $4.79, H200 $5.93, B200 $8.64, B300 $9.98. Active (always-on) workers are discounted through sales. Pods run from $0.27 an hour (RTX A5000) to $7.89 (B300) on Community or Secure Cloud. Container disk $0.10 a GB-month, volume disk $0.10 running and $0.20 idle, network volumes $0.07 a GB-month under 1 TB and $0.05 above, high-performance $0.14. Default spend cap $80 an hour. Cards, crypto after KYC, prepaid cards at $100 or more a transaction, invoicing above $5,000 (https://www.runpod.io/pricing, https://docs.runpod.io/serverless/pricing, https://docs.runpod.io/accounts-billing/billing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 314, "npmWeekly": 21838, "pypiWeekly": 146926, "asOf": "2026-09-30" }, "docsUrl": "https://docs.runpod.io", "llmsTxt": "https://docs.runpod.io/llms.txt", "openapi": "https://api.runpod.io/v2/openapi.json", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "tags": [ "hosted", "usage-priced", "prepaid", "mcp", "oauth", "llms-txt", "python", "typescript", "async-jobs", "batch", "webhooks", "enterprise" ], "lastRelease": "2026-09-15", "graded": true, "anchor": { "graded": true, "score": 53.7, "grade": "D", "agentReady": false, "rank": 329, "ranked": true, "rankOf": 452, "categoryRank": 6, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 47, "maintenance": 82, "payments": 20, "reliability": 35, "schema": 81, "security": 60, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour. Data-centre outages of 6 to 24 hours in each of July, August and September 2026.", "strengths": [ "Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour", "API keys can be Read Only or restricted per serverless endpoint", "OpenAPI file for REST v2, llms.txt and dated release notes with deprecation dates", "Official MCP server, hosted with OAuth or local over stdio", "Valid security.txt and SOC 2 Type 2 and ISO 27001 in the trust centre" ], "weaknesses": [ "Data-centre outages of 6 to 24 hours in each of July, August and September 2026", "No published rate limits, 429 guidance, error codes or SLA", "The GraphQL API, live until early 2027, takes the API key in the URL", "No free tier, prepaid credit only", "Three APIs in flight, with REST v1 retiring on 15 November 2026" ], "agentNotes": [ "Create a Restricted or Read Only key per endpoint for the agent, not an All key", "Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL", "Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone", "Call `/retry` on a failed job ID rather than submitting a duplicate job", "Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.7 } ], "editorialScores": { "ergonomics": 47, "maintenance": 82, "payments": 20, "reliability": 35, "schema": 81, "security": 60, "transparency": 60 }, "provenanceScore": 70 }, "connect": { "install": "pip install runpod # or npm i runpod-sdk", "http": "curl -X POST \"https://api.runpod.ai/v2/$RUNPOD_ENDPOINT_ID/runsync\" \\\n -H \"Authorization: Bearer $RUNPOD_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"input\":{\"prompt\":\"Hello, world!\"}}'", "claudeCode": "claude mcp add --transport http runpod https://mcp.getrunpod.io/ --header \"Authorization: Bearer $RUNPOD_API_KEY\"", "config": { "mcpServers": { "runpod": { "args": [ "-y", "@runpod/mcp-server@latest" ], "command": "npx", "env": { "RUNPOD_API_KEY": "${RUNPOD_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/runpod" }, "area": "models", "unitPrices": [ { "item": "H100 80 GB serverless flex", "unit": "gpu-hour", "usd": 4.79, "note": "Billed per second" }, { "item": "H200 141 GB serverless flex", "unit": "gpu-hour", "usd": 5.93 }, { "item": "B200 180 GB serverless flex", "unit": "gpu-hour", "usd": 8.64 }, { "item": "A100 80 GB serverless flex", "unit": "gpu-hour", "usd": 2.72 }, { "item": "L40S 48 GB serverless flex", "unit": "gpu-hour", "usd": 1.75 }, { "item": "RTX 4090 24 GB serverless flex", "unit": "gpu-hour", "usd": 1.1 }, { "item": "L4 24 GB serverless flex", "unit": "gpu-hour", "usd": 0.69 }, { "item": "Container disk", "unit": "gb-month", "usd": 0.1 }, { "item": "Network volume under 1 TB", "unit": "gb-month", "usd": 0.07, "note": "$0.05 above 1 TB, $0.14 high-performance" } ], "provenance": { "legalEntity": "Runpod, Inc.", "domain": "runpod.io", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://www.runpod.io/legal/terms-of-service", "privacy": "https://www.runpod.io/legal/privacy-policy", "statusPage": "https://uptime.runpod.io", "changelog": "https://docs.runpod.io/release-notes", "securityTxt": "valid", "checked": "2026-09-30", "notes": [ "Terms effective 24 March 2026 name Runpod, Inc. under Delaware law. The privacy policy gives 329 Bryant St #4D, San Francisco.", "Serverless endpoints are served from api.runpod.ai and the management API from api.runpod.io, while the hosted MCP server sits on getrunpod.io.", "security.txt points to trust.runpod.io and expires 2027-01-31.", "The .io registry's RDAP server rate-limited our lookup, so the registration date is unrecorded." ], "score": 70 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/runpod.json", "live": { "slug": "runpod", "probe": { "target": "https://api.runpod.ai/v2", "method": "get", "lastAt": "2026-10-04T21:48:35.741163533Z", "lastOk": true, "lastStatus": 404, "lastMs": 56, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 47, "p95ms24h": 91, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://uptime.runpod.io", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:27.797321476Z" }, "versions": [ { "registry": "github", "name": "runpod/runpod-python", "version": "v1.12.0", "released": "2026-08-10", "seenAt": "2026-10-04T16:38:45.92301028Z" }, { "registry": "npm", "name": "@runpod/mcp-server", "version": "4.0.0", "seenAt": "2026-10-04T16:38:44.129996109Z" }, { "registry": "npm", "name": "runpod-sdk", "version": "1.1.2", "seenAt": "2026-10-04T16:38:43.626700927Z" }, { "registry": "pypi", "name": "runpod", "version": "1.12.0", "released": "2026-08-10", "seenAt": "2026-10-04T16:38:43.443916692Z" }, { "registry": "pypi", "name": "runpod-flash", "version": "1.20.0", "released": "2026-09-24", "seenAt": "2026-10-04T16:38:45.837849754Z" } ], "githubStars": 313, "npmWeekly": 29952, "securityTxt": { "url": "https://runpod.io/.well-known/security.txt", "state": "valid", "expires": "2027-01-31T23:59:59Z", "checkedAt": "2026-10-04T15:15:41.463706841Z" }, "llmsTxt": { "url": "https://docs.runpod.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:12.095308214Z" }, "domain": { "domain": "runpod.io", "checkedAt": "2026-10-04T13:06:54.960688955Z" }, "pages": [ { "url": "https://docs.runpod.io/release-notes", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-04T15:44:00.021950941Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "64302af06aec" }, { "url": "https://docs.runpod.io/serverless/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:44:02.16843867Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "acdfc6a36a7f" }, { "url": "https://www.runpod.io/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:52:04.97613805Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4e4c891c31f7" }, { "url": "https://www.runpod.io/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:52:00.890880838Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "00b9defcdf3d" }, { "url": "https://www.runpod.io/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:52:02.970729657Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4163df004c48" } ], "updatedAt": "2026-10-04T21:48:35.741163533Z" } }, { "slug": "lambda", "name": "Lambda Cloud", "vendor": "Lambda", "vendorUrl": "https://lambda.ai", "kind": "http-api", "category": "gpu-compute", "summary": "On-demand GPU virtual machines and clusters, with an API for provisioning compute and persistent storage.", "url": "https://www.anchorterminal.com/tools/lambda", "markdownUrl": "https://www.anchorterminal.com/tools/lambda.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/lambda.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/lambda.json", "transports": [ "http" ], "remoteUrl": "https://cloud.lambda.ai/api/v1", "packages": [], "auth": "api-key", "authNotes": "API key created at cloud.lambda.ai/api-keys and sent as `Authorization: Bearer`. HTTP Basic with the key as the username (`curl -u 'KEY:'`) still works as a legacy option. SSH keys registered in the account are injected into launched instances.", "pricing": "usage", "pricingNotes": "On-demand, per GPU an hour, Tesla V100 16 GB $0.79, A100 40 GB $1.99, A100 80 GB $2.79, H100 SXM 80 GB $3.99, B200 180 GB $6.69. 1-Click Clusters of HGX B200 are quoted per GPU-hour at $9.86 for 16 GPUs, $9.36 for 64 and $8.87 for 256 or more on two-week to one-year commitments. Instances bill in one-minute increments from the moment they pass health checks until you terminate them, invoiced weekly. Filesystems bill per GB used a month in one-hour increments. No free tier (https://lambda.ai/pricing, https://docs.lambda.ai/public-cloud/billing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.lambda.ai/public-cloud/on-demand/", "openapi": "https://docs.lambda.ai/api/cloud/spec.json", "capabilities": [ "compute.gpu", "compute.containers" ], "tags": [ "hosted", "usage-priced", "openapi", "enterprise" ], "graded": true, "anchor": { "graded": true, "score": 50.1, "grade": "D", "agentReady": false, "rank": 363, "ranked": true, "rankOf": 452, "categoryRank": 7, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 5, "payments": 20, "reliability": 50, "schema": 69, "security": 60, "transparency": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated.", "strengths": [ "H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing", "OpenAPI 3.1 spec with documented error codes, a `suggestion` field and cursor pagination", "Audit events endpoint filterable by time and resource type", "Published rate limits, one request a second and one launch every 12 seconds", "Trust portal with SOC 2 Type 2 and four ISO certifications, and a named subprocessor list" ], "weaknesses": [ "No scale to zero, autoscaling or endpoints; an idle VM bills until terminated", "Ten status incidents in two months, including a two-day regional outage in August 2026", "No changelog, no llms.txt and no official SDK", "API keys have no scopes and launch has no idempotency key", "security.txt expired on 1 June 2026 and no free tier" ], "agentNotes": [ "Call `GET /instance-types` first and read `regions_with_capacity_available` before trying to launch", "Space launch calls 12 seconds apart; a sixth in a minute returns 429 with `global/rate-limited`", "Branch on the error `code`, not the `message` or `suggestion`, which Lambda says may change", "List instances before retrying a failed launch, since there's no idempotency key and a retry can start a second machine", "Terminate the instance in a `finally` block; billing runs by the minute until you do" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.1 } ], "editorialScores": { "ergonomics": 63, "maintenance": 5, "payments": 20, "reliability": 50, "schema": 69, "security": 60, "transparency": 48 }, "provenanceScore": 70 }, "connect": { "http": "curl \"https://cloud.lambda.ai/api/v1/instance-types\" -H \"Authorization: Bearer $LAMBDA_API_KEY\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/lambda" }, "area": "models", "unitPrices": [ { "item": "H100 SXM 80 GB", "unit": "gpu-hour", "usd": 3.99, "note": "Billed per minute" }, { "item": "B200 180 GB", "unit": "gpu-hour", "usd": 6.69 }, { "item": "A100 SXM 80 GB", "unit": "gpu-hour", "usd": 2.79 }, { "item": "A100 SXM 40 GB", "unit": "gpu-hour", "usd": 1.99 }, { "item": "Tesla V100 16 GB", "unit": "gpu-hour", "usd": 0.79 }, { "item": "HGX B200 1-Click Cluster, 16 GPUs", "unit": "gpu-hour", "usd": 9.86, "note": "Two-week to one-year commitment; $8.87 at 256 GPUs or more" } ], "provenance": { "legalEntity": "Lambda, Inc.", "domain": "lambda.ai", "domainRegistered": "", "domainNote": "Lambda moved from lambdalabs.com, registered 2008-05-29, to lambda.ai. The .ai registry's RDAP server rate-limited our lookup of the new domain.", "endpointOnVendorDomain": true, "terms": "https://lambda.ai/legal/terms-of-service", "privacy": "https://lambda.ai/legal/privacy-policy", "statusPage": "https://status.lambda.ai", "changelog": "", "securityTxt": "expired", "checked": "2026-09-30", "notes": [ "Terms dated August 2025 and the privacy policy of 1 January 2026 name Lambda, Inc., 2510 Zanker Road, San Jose, California.", "The API runs on cloud.lambda.ai, a subdomain of the vendor domain.", "security.txt expired 2026-06-01 and has no Policy field.", "No public changelog found for the cloud. The OpenAPI spec reports version 1.10.0." ], "score": 70 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/lambda.json", "live": { "slug": "lambda", "probe": { "target": "https://cloud.lambda.ai/api/v1", "method": "get", "lastAt": "2026-10-04T21:48:30.427410181Z", "lastOk": true, "lastStatus": 403, "lastMs": 574, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 561, "p95ms24h": 901, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://status.lambda.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T21:40:11.367004648Z" }, "securityTxt": { "url": "https://lambda.ai/.well-known/security.txt", "state": "expired", "expires": "2026-06-01T16:00:00Z", "checkedAt": "2026-10-04T15:15:58.764976134Z" }, "domain": { "domain": "lambda.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/lambda.ai", "checkedAt": "2026-10-04T13:04:37.89683091Z" }, "pages": [ { "url": "https://lambda.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:45:18.84160567Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ad7e156559d1" }, { "url": "https://lambda.ai/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:45:14.766678886Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "921eec75dd83" }, { "url": "https://lambda.ai/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:45:16.817640272Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "40e40aee2e7c" } ], "updatedAt": "2026-10-04T21:48:30.427410181Z" } }, { "slug": "koyeb", "name": "Koyeb", "vendor": "Koyeb", "vendorUrl": "https://www.koyeb.com", "kind": "platform", "category": "gpu-compute", "summary": "Serverless platform for deploying applications and containers on CPU or GPU instances, with autoscaling and an API.", "url": "https://www.anchorterminal.com/tools/koyeb", "markdownUrl": "https://www.anchorterminal.com/tools/koyeb.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/koyeb.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/koyeb.json", "repo": "https://github.com/koyeb/koyeb-cli", "license": "Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://app.koyeb.com/v1", "packages": [], "auth": "pat", "authNotes": "Personal access token created in the control panel (app.koyeb.com/user/settings/api) and sent as `Authorization: Bearer` to app.koyeb.com/v1. The CLI stores it from `koyeb login` and hides it in debug output. Organisation-scoped tokens can be created for teams.", "pricing": "freemium", "pricingNotes": "Pro is $29 a month with $10 of usage included, Scale $299 with $100, Enterprise custom. The Starter plan closed to new sign-ups after the Mistral AI agreement. Everything bills per second. GPUs an hour are RTX 4000 SFF Ada $0.50, L4 $0.70, RTX A6000 $0.75, L40S $1.20, A100 $1.60, A100 SXM $2.15, RTX PRO 6000 $2.20, H100 $2.50, H200 $3.00, 2x A100 $3.20, 2x H100 $5.00, 4x A100 $6.40, 8x H100 $20.00, 8x H200 $24.00. CPU services start at $0.000006 a second (https://www.koyeb.com/pricing, https://www.koyeb.com/blog/koyeb-is-joining-mistral-ai-to-build-the-future-of-ai-infrastructure).", "priceSummary": "$29 / mo", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 72, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://www.koyeb.com/docs", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.containers" ], "tags": [ "hosted", "freemium", "eu", "enterprise" ], "lastRelease": "2026-05-12", "graded": true, "anchor": { "graded": true, "score": 47, "grade": "D", "agentReady": false, "rank": 389, "ranked": true, "rankOf": 452, "categoryRank": 8, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 56, "maintenance": 23, "payments": 20, "reliability": 60, "schema": 41, "security": 50, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "H100 at $2.50 and H200 at $3.00 an hour, billed per second. Changelog silent since 27 February 2026 and no CLI release since 12 May 2026.", "strengths": [ "H100 at $2.50 and H200 at $3.00 an hour, billed per second", "Scale to zero after 5 idle minutes by default, configurable up to 12 hours on higher plans", "99.9 per cent uptime SLA published from the Pro plan", "List endpoints filter by name, type, status and region with `limit` and `offset`, and create and update take `dry_run`", "French company under French law with a published DPA" ], "weaknesses": [ "Changelog silent since 27 February 2026 and no CLI release since 12 May 2026", "No free compute tier; Starter closed after the Mistral AI agreement", "No llms.txt, no downloadable OpenAPI file, no documented rate limits or error codes", "Audit logs and RBAC only on Enterprise, and tokens have no scopes", "Platform due to fold into Mistral Compute with no dated migration plan" ], "agentNotes": [ "Pass `dry_run` on service create or update to validate the definition before anything deploys", "Page service lists with `limit` and `offset` and filter by `statuses` instead of fetching everything", "Expect the first request after deep sleep to take 1 to 5 seconds and retry once with a timeout", "Set `--min-scale 0` on GPU services so idle instances stop billing", "Re-check the Mistral transition before building anything long-lived on it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47 } ], "editorialScores": { "ergonomics": 56, "maintenance": 23, "payments": 20, "reliability": 60, "schema": 41, "security": 50, "transparency": 50 }, "provenanceScore": 86 }, "connect": { "install": "brew install koyeb/tap/koyeb \u0026\u0026 koyeb login # or go install github.com/koyeb/koyeb-cli/cmd/koyeb", "http": "curl \"https://app.koyeb.com/v1/services\" -H \"Authorization: Bearer $KOYEB_TOKEN\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/koyeb" }, "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 2.5 }, { "item": "H200 141 GB", "unit": "gpu-hour", "usd": 3 }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 1.6 }, { "item": "RTX PRO 6000", "unit": "gpu-hour", "usd": 2.2 }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 1.2 }, { "item": "L4 24 GB", "unit": "gpu-hour", "usd": 0.7 }, { "item": "Pro plan", "unit": "month", "usd": 29, "note": "$10 of usage included" }, { "item": "Scale plan", "unit": "month", "usd": 299, "note": "$100 of usage included" } ], "provenance": { "legalEntity": "Koyeb SAS", "domain": "koyeb.com", "domainRegistered": "2019-03-11", "endpointOnVendorDomain": true, "terms": "https://www.koyeb.com/docs/legal/terms", "privacy": "https://www.koyeb.com/docs/legal/data-processing-agreement", "statusPage": "https://status.koyeb.com", "changelog": "https://www.koyeb.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The Master Services Agreement of 28 June 2024 names Koyeb, a simplified joint-stock company registered in Nanterre under 850 183 948, at 9 rue des Longs Prés, Boulogne-Billancourt, under French law.", "The site footer's privacy link points at the data processing agreement rather than a separate privacy policy.", "www.koyeb.com/.well-known/security.txt returns 404 and there's no llms.txt at www.koyeb.com or under /docs.", "Koyeb announced on 17 February 2026 that it is joining Mistral AI." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/koyeb.json", "live": { "slug": "koyeb", "probe": { "target": "https://app.koyeb.com/v1", "method": "get", "lastAt": "2026-10-04T21:48:30.303978836Z", "lastOk": true, "lastStatus": 200, "lastMs": 107, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 67, "p95ms24h": 120, "samples24h": 272, "samples30d": 875, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 247, "ok": 247 } ] }, "vendorStatus": { "page": "https://status.koyeb.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:11.113089843Z" }, "versions": [ { "registry": "github", "name": "koyeb/koyeb-cli", "version": "v5.12.0", "released": "2026-09-16", "seenAt": "2026-10-04T16:30:59.654487485Z" } ], "githubStars": 75, "securityTxt": { "url": "https://koyeb.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:39.623181757Z" }, "domain": { "domain": "koyeb.com", "registered": "2019-03-11", "source": "https://rdap.verisign.com/com/v1/domain/koyeb.com", "checkedAt": "2026-10-04T13:09:21.713025238Z" }, "pages": [ { "url": "https://www.koyeb.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:50:56.745854439Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7e4e89b36b63" }, { "url": "https://www.koyeb.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:51:02.824779527Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9d7cf517fa78" }, { "url": "https://www.koyeb.com/docs/legal/data-processing-agreement", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:50:58.811207008Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6e08cc6e8919" }, { "url": "https://www.koyeb.com/docs/legal/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-04T15:51:00.911838778Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "089f524cdbd6" } ], "updatedAt": "2026-10-04T21:48:30.303978836Z" } } ] }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/categories/gpu-compute", "json": "https://www.anchorterminal.com/categories/gpu-compute.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/categories/gpu-compute.md", "slim": "https://www.anchorterminal.com/categories/gpu-compute.min.md" }, "markdown": "Clouds that run your own models and jobs on GPUs by the second, as serverless functions, endpoints or rented machines. Compared on GPU types and price per hour, cold starts, scaling and what you have to package.\n\n- Tools ranked: 9 · agent-ready (BB or better): 1 · accept x402: 0 · hosted endpoints: 7 · desk reviews by the panel: 24\n- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)\n- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/\n\n- Capabilities in this category: compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers\n- https://letme.dev/compute.gpu picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)\n\n## Ranking\n\n| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 33 | Modal Sandboxes | Modal | SDK + MCP | Sandboxes | BB | 75.6 | medium | no | API key | local | 3.3/5 (8) | https://www.anchorterminal.com/tools/modal-sandboxes.md |\n| 157 | Baseten | Baseten | HTTP API | GPU compute | B | 66.7 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/baseten.md |\n| 195 | Modal | Modal | Model platform | GPU compute | B | 63.8 | medium | no | API key | local | 4/5 (2) | https://www.anchorterminal.com/tools/modal.md |\n| 197 | Replicate Deployments | Replicate | HTTP API | GPU compute | B | 63.7 | medium | no | API key | hosted + local | 3/5 (2) | https://www.anchorterminal.com/tools/replicate-deploy.md |\n| 224 | Northflank | Northflank | Model platform | GPU compute | C | 61.8 | medium | no | Token | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/northflank.md |\n| 313 | Beam | Beam | Model platform | GPU compute | C | 55.5 | medium | no | API key | hosted | 3/5 (2) | https://www.anchorterminal.com/tools/beam.md |\n| 329 | Runpod | Runpod | HTTP API | GPU compute | D | 53.7 | medium | no | OAuth or key | hosted + local | 3/5 (2) | https://www.anchorterminal.com/tools/runpod.md |\n| 363 | Lambda Cloud | Lambda | HTTP API | GPU compute | D | 50.1 | medium | no | API key | hosted | 3/5 (2) | https://www.anchorterminal.com/tools/lambda.md |\n| 389 | Koyeb | Koyeb | Model platform | GPU compute | D | 47 | medium | no | Token | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/koyeb.md |\n\nScores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.\n\n## Summaries\n\n### 33. Modal Sandboxes, BB (75.6)\n\nModal's sandboxed compute environments for running code, with SDK access, GPU support and filesystem snapshots. GPU sandboxes at the same per-second rates as the rest of Modal. No REST API, and the JavaScript and Go SDKs are beta.\n\n- Page: https://www.anchorterminal.com/tools/modal-sandboxes · Markdown: https://www.anchorterminal.com/tools/modal-sandboxes.md · JSON: https://www.anchorterminal.com/api/v1/tools/modal-sandboxes.json\n- Capabilities: sandbox.code, sandbox.fs, sandbox.persist, sandbox.gpu\n\n### 157. Baseten, B (66.7)\n\nDedicated model deployments packaged with the open-source Truss framework and served behind a per-model HTTPS endpoint, with autoscaling from zero replicas, async inference, a management API and per-minute GPU billing from T4 to B200. Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.\n\n- Page: https://www.anchorterminal.com/tools/baseten · Markdown: https://www.anchorterminal.com/tools/baseten.md · JSON: https://www.anchorterminal.com/api/v1/tools/baseten.json\n- Capabilities: compute.gpu, compute.endpoints, compute.serverless, compute.containers · endpoint: `https://api.baseten.co`\n\n### 195. Modal, B (63.8)\n\nServerless functions, web endpoints, servers and GPU jobs from a Python decorator, with JavaScript and Go SDKs. Scale to zero by default, per-second billing and about one-second container boots. No REST API or OpenAPI spec for deploying or invoking Functions.\n\n- Page: https://www.anchorterminal.com/tools/modal · Markdown: https://www.anchorterminal.com/tools/modal.md · JSON: https://www.anchorterminal.com/api/v1/tools/modal.json\n- Capabilities: compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers\n\n### 197. Replicate Deployments, B (63.7)\n\nReplicate's service for deploying and running custom models. OpenAPI file, llms.txt and an MCP server with a two-tool code mode. Private instances bill set-up and idle time, H100 at $5.49 an hour.\n\n- Page: https://www.anchorterminal.com/tools/replicate-deploy · Markdown: https://www.anchorterminal.com/tools/replicate-deploy.md · JSON: https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json\n- Capabilities: compute.gpu, compute.endpoints, compute.serverless, compute.containers · endpoint: `https://api.replicate.com/v1`\n\n### 224. Northflank, C (61.8)\n\nPlatform for deploying services, jobs and databases from Git or container images, in managed or customer-owned infrastructure. Supports GPU workloads and sandboxes. OpenAPI 3.0 with over 100 paths, enums and `per_page`, `page` and `cursor` on every list. No scale to zero for services; minimum instances must be at least 1.\n\n- Page: https://www.anchorterminal.com/tools/northflank · Markdown: https://www.anchorterminal.com/tools/northflank.md · JSON: https://www.anchorterminal.com/api/v1/tools/northflank.json\n- Capabilities: compute.gpu, compute.containers, compute.batch, compute.endpoints · endpoint: `https://api.northflank.com/v1`\n\n### 313. Beam, C (55.5)\n\nServerless GPU endpoints, task queues, functions, pods and sandboxes from Python decorators, on the open-source beta9 runtime. Per-millisecond billing with cold starts and image pulls free, H100 PCIe at $3.50 and RTX 4090 at $0.69 an hour. No published request rate limits, 429 handling or SLA.\n\n- Page: https://www.anchorterminal.com/tools/beam · Markdown: https://www.anchorterminal.com/tools/beam.md · JSON: https://www.anchorterminal.com/api/v1/tools/beam.json\n- Capabilities: compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers · endpoint: `https://app.beam.cloud/api/v1`\n\n### 329. Runpod, D (53.7)\n\nServerless GPU endpoints, queue-based or load-balanced, and rented GPU Pods, billed per second from prepaid credit. Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour. Data-centre outages of 6 to 24 hours in each of July, August and September 2026.\n\n- Page: https://www.anchorterminal.com/tools/runpod · Markdown: https://www.anchorterminal.com/tools/runpod.md · JSON: https://www.anchorterminal.com/api/v1/tools/runpod.json\n- Capabilities: compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers · endpoint: `https://api.runpod.ai/v2`\n\n### 363. Lambda Cloud, D (50.1)\n\nOn-demand GPU virtual machines and clusters, with an API for provisioning compute and persistent storage. H100 SXM at $3.99 and B200 at $6.69 an hour with per-minute billing. No scale to zero, autoscaling or endpoints; an idle VM bills until terminated.\n\n- Page: https://www.anchorterminal.com/tools/lambda · Markdown: https://www.anchorterminal.com/tools/lambda.md · JSON: https://www.anchorterminal.com/api/v1/tools/lambda.json\n- Capabilities: compute.gpu, compute.containers · endpoint: `https://cloud.lambda.ai/api/v1`\n\n### 389. Koyeb, D (47)\n\nServerless platform for deploying applications and containers on CPU or GPU instances, with autoscaling and an API. H100 at $2.50 and H200 at $3.00 an hour, billed per second. Changelog silent since 27 February 2026 and no CLI release since 12 May 2026.\n\n- Page: https://www.anchorterminal.com/tools/koyeb · Markdown: https://www.anchorterminal.com/tools/koyeb.md · JSON: https://www.anchorterminal.com/api/v1/tools/koyeb.json\n- Capabilities: compute.gpu, compute.serverless, compute.endpoints, compute.containers · endpoint: `https://app.koyeb.com/v1`\n\n## How we test this category\n\nThe same model deployed as an endpoint on each platform, called cold and warm, then scaled to zero. We time cold starts, check the scaling and add up the cost per GPU-hour. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.\n\n## Indexed, not reviewed (6)\n\nSorted into this category from public catalogues, with facts and our own checks but no score, grade or rank (https://www.anchorterminal.com/indexed/index.md).\n\n| Listing | Kind | What it does | Why it's here |\n| --- | --- | --- | --- |\n| [3DOptix](https://www.anchorterminal.com/tools/3doptix-optical-design.md) | MCP server | Optical design, simulation and analysis with GPU-powered ray tracing. Import from Zemax and CAD. | vendor's own |\n| [AmpleRun GPU rentals](https://www.anchorterminal.com/tools/amplerun-gpu-rentals.md) | MCP server | Find, price, rent and stop GPUs on AmpleRun. Paid in USDC or USDT on Base. Flat 5% fee. | vendor's own |\n| [FitLLM](https://www.anchorterminal.com/tools/fitllm.md) | MCP server | Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM \u0026 KV-cache math. Read-only. | vendor's own |\n| [framebench](https://www.anchorterminal.com/tools/framebench.md) | MCP server | Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks. | vendor's own |\n| [prismnetwork.tech MCP server](https://www.anchorterminal.com/tools/prismnetwork-mcp.md) | MCP server | Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain. | vendor's own |\n| [Zhijiangyun Cloud (智匠云)](https://www.anchorterminal.com/tools/artibot-zhijiangyun.md) | MCP server | Robot embodied-AI cloud for GPU training, inference, benchmarks, and robot data collection. | vendor's own |\n\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-04", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "GPU \u0026 serverless compute", "url": "" } ], "description": "9 GPU \u0026 serverless compute listings ranked by the Anchor benchmark. Leader Modal Sandboxes (BB). Clouds that run your own models and jobs on GPUs by the second, as serverless functions, endpoints or rented machines. Compared on GPU types and price per hour, cold starts, scaling and what you have to package.", "facts": [ "Modal Sandboxes BB", "Baseten B", "Modal B" ], "h1": "GPU and serverless compute for AI workloads", "image": "https://www.anchorterminal.com/assets/og/categories-gpu-compute.png", "path": "/categories/gpu-compute", "published": "", "section": "tools", "title": "GPU and serverless compute for AI workloads, ranked | Anchor Terminal", "toc": null, "updated": "2026-10-04", "url": "https://www.anchorterminal.com/categories/gpu-compute" }, "tokens": { "markdown": 2750, "slim": 480 }, "version": 1 }