{ "data": { "a": { "slug": "cerebrium", "name": "Cerebrium", "vendor": "Cerebrium Inc.", "vendorUrl": "https://www.cerebrium.ai", "kind": "platform", "category": "gpu-compute", "summary": "Cerebrium is a serverless platform for running your own models and code on GPUs and CPUs. A CLI packages code into containers served as REST, streaming and WebSocket endpoints, managed through a REST API.", "url": "https://www.anchorterminal.com/tools/cerebrium", "markdownUrl": "https://www.anchorterminal.com/tools/cerebrium.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cerebrium.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cerebrium.json", "dns": "cerebrium.grade.anchorterminal.com", "repo": "https://github.com/CerebriumAI/cerebrium", "license": "Proprietary service under Cerebrium's terms of service. The CLI is MIT", "transports": [ "http" ], "remoteUrl": "https://rest.cerebrium.ai", "packages": [ { "registry": "pypi", "name": "cerebrium" } ], "auth": "api-key", "authNotes": "Two credentials. A service account token, created in the dashboard or over the API with an expiry of up to one year and a list of granted projects, authenticates the CLI (`CEREBRIUM_SERVICE_ACCOUNT_TOKEN`) and the management API at rest.cerebrium.ai as `Authorization: Bearer`. A project API key (a JWT) authenticates calls to deployed endpoints, and only when `cerebrium.toml` sets `disable_auth = false`. Signup and `cerebrium login` are browser flows.", "pricing": "freemium", "pricingNotes": "Hobby plan is $0 a month plus compute, Standard $100 a month plus compute, Enterprise on request. GPU, CPU and memory bill per second, from T4 at $0.000164 a second ($0.59 an hour) to H100 at $0.000944 ($3.40) and B200 at $0.00167 ($6.01). CPU $0.00000655 a vCPU-second, memory $0.00000222 a GB-second, storage $0.05 a GB-month after 100 GB free. Listed rates are for the default interruptible tier, and `protected` compute costs twice as much. Cold-start time is free, builds and model initialisation are billed. An account can start on Hobby without a contract. The pricing page does not say whether a card is needed or state a free compute allowance (https://www.cerebrium.ai/pricing, https://cerebrium.ai/docs/calculating-cost).", "priceSummary": "$0.0236 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://cerebrium.ai/docs", "llmsTxt": "https://cerebrium.ai/docs/llms.txt", "openapi": "https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "tags": [ "hosted", "freemium", "serverless", "gpu", "cli", "openapi", "llms-txt", "python", "async-jobs", "multi-region", "status-page", "soc2", "hipaa" ], "lastRelease": "2026-09-16", "graded": true, "anchor": { "graded": true, "score": 52.5, "grade": "D", "agentReady": false, "rank": 989, "ranked": true, "rankOf": 1510, "categoryRank": 17, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 49, "maintenance": 65, "payments": 30, "reliability": 48, "schema": 70, "security": 60, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -2, "negativeNotes": [ "-2, misleading claim, standing on 4 November 2026. The CLI's `cerebrium config telemetry enable` help, there since BugSnag reporting was added (52f892d, 21 November 2025) and shipped in v2.9.0, says \"No personal data or code is ever transmitted - only error messages and system metadata\". The same builds attach the account's user ID from the token (the JWT subject, or the username) and the project ID to every report, with session tracking on. Reporting is on by default with documented off switches, so it is charged as a misleading claim, not as undisclosed telemetry (docker-model-runner, astrbot). https://github.com/CerebriumAI/cerebrium/blob/main/internal/commands/config/telemetry.go" ], "verdict": "Per-second GPU prices are public, a 94-operation OpenAPI spec covers the management API, and service account tokens expire and are limited to named projects. Deployed endpoints are callable without a token unless `disable_auth = false` is set, and no request rate limits, 429 handling or SLA were found in the reviewed documentation.", "bestFor": "Teams serving their own models as real-time endpoints (voice, LLM, image) who want per-second billing, multi-region placement and a scriptable management API.", "strengths": [ "Per-second prices for ten GPU types published without a login, from T4 at $0.59 an hour to B200 at $6.01", "Public OpenAPI 3.0 spec for the management API at rest.cerebrium.ai, with 94 operations, plus llms.txt and Markdown docs", "Service account tokens carry an expiry of up to one year and a list of 1 to 50 granted projects", "Audit log of 22 actions with actor, IP address and outcome, readable over the API on Standard and Enterprise", "Status page with 11 components and 90 days of incident history, and five CLI releases between 7 August and 16 September 2026" ], "weaknesses": [ "`disable_auth` defaults to true, so a deployed endpoint answers without a token unless the owner changes it", "No request rate limits, 429 guidance, idempotency keys or SLA found in the reviewed documentation", "Multi-hour degradations of the Inference API on 19 August (US) and 2 September 2026 (EU), per the 8 October status reading", "No deprecation policy, platform changelog or public subprocessor list found", "The CLI stores tokens in plaintext in `~/.cerebrium/config.yaml` with mode 0644, per its own SECURITY.md" ], "agentNotes": [ "Set `disable_auth = false` in `cerebrium.toml` before deploying. The default leaves the endpoint callable by anyone with the URL", "Authenticate headless with `CEREBRIUM_SERVICE_ACCOUNT_TOKEN`. `cerebrium login` opens a browser", "Raise `response_grace_period` for long work. It defaults to 15 minutes and async runs stop at 12 hours", "Send `?async=true` to get a `run_id` with HTTP 202, and add `webhookEndpoint` because async calls return no result to the caller", "Check the plan before choosing hardware. A100, H100, H200, B200 and RTX PRO 6000 need Standard, and `protected` compute bills at twice the listed rate" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.5 } ], "editorialScores": { "ergonomics": 49, "maintenance": 65, "payments": 30, "reliability": 48, "schema": 70, "security": 60, "transparency": 45 }, "provenanceScore": 82, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install cerebrium \u0026\u0026 cerebrium login", "http": "curl --location --request POST 'https://api.cerebrium.ai/v4/p-xxxxxxxx/{app-name}/{function}' \\\n --header 'Authorization: Bearer \u003cJWT_TOKEN\u003e' \\\n --header 'Content-Type: application/json' \\\n --data '{\"function_param\": \"data\"}'" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/cerebrium" }, "area": "models", "unitPrices": [ { "item": "B200 180 GB", "unit": "gpu-hour", "usd": 6.01, "note": "$0.00167 a second, interruptible tier" }, { "item": "H200 141 GB", "unit": "gpu-hour", "usd": 4.2, "note": "$0.001166 a second, interruptible tier" }, { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 3.4, "note": "$0.000944 a second, interruptible tier" }, { "item": "RTX PRO 6000 96 GB", "unit": "gpu-hour", "usd": 2.5, "note": "$0.000694 a second, interruptible tier" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 2.1, "note": "$0.000583 a second, interruptible tier" }, { "item": "A100 40 GB", "unit": "gpu-hour", "usd": 2, "note": "$0.000555 a second, interruptible tier" }, { "item": "L40s 48 GB", "unit": "gpu-hour", "usd": 1.95, "note": "$0.000542 a second, interruptible tier" }, { "item": "A10 24 GB", "unit": "gpu-hour", "usd": 1.1, "note": "$0.000306 a second, interruptible tier" }, { "item": "L4 24 GB", "unit": "gpu-hour", "usd": 0.8, "note": "$0.000222 a second, interruptible tier" }, { "item": "T4 16 GB", "unit": "gpu-hour", "usd": 0.59, "note": "$0.000164 a second, interruptible tier" }, { "item": "CPU-only compute", "unit": "vcpu-hour", "usd": 0.0236, "note": "$0.00000655 a vCPU-second, memory extra at $0.00000222 a GB-second" }, { "item": "Persistent storage", "unit": "gb-month", "usd": 0.05, "note": "First 100 GB free" }, { "item": "Standard plan", "unit": "month", "usd": 100, "note": "Plus compute" } ], "provenance": { "legalEntity": "Cerebrium Inc.", "domain": "cerebrium.ai", "domainRegistered": "2021-06-11", "endpointOnVendorDomain": true, "terms": "https://www.cerebrium.ai/terms-of-service", "privacy": "https://www.cerebrium.ai/privacy", "statusPage": "https://status.cerebrium.ai", "changelog": "https://github.com/CerebriumAI/cerebrium/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service name Cerebrium Inc and say they are governed by the laws of the United Kingdom. The privacy policy names Cerebrium Inc. as data controller at 251 Little Falls Drive, Wilmington, Delaware.", "The terms of service are the only terms Cerebrium publishes. They cover accounts, subscriptions and the Service, and the OpenAPI spec names them as the API's licence. Neither document states a date.", "Deployed endpoints answer at api.cerebrium.ai and the management API at rest.cerebrium.ai. The OpenAPI file is served from an AWS S3 bucket.", "cerebrium.ai/.well-known/security.txt and cerebrium.ai/security.txt returned 404 on 8 October 2026. The CLI repository's SECURITY.md and the docs give security@cerebrium.ai.", "The changelog link is the CLI's GitHub releases. No platform changelog was found. Domain registration date from RDAP." ], "score": 82 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cerebrium.json", "live": { "slug": "cerebrium", "probe": { "target": "https://rest.cerebrium.ai", "method": "get", "lastAt": "2026-11-07T19:21:59.014046766Z", "lastOk": true, "lastStatus": 403, "lastMs": 302, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 266, "p95ms24h": 370, "samples24h": 238, "samples30d": 7450, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.cerebrium.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:13.408276382Z" }, "versions": [ { "registry": "github", "name": "CerebriumAI/cerebrium", "version": "v2.9.0", "released": "2026-09-16", "seenAt": "2026-11-06T23:13:53.482267422Z" }, { "registry": "pypi", "name": "cerebrium", "version": "2.9.0", "released": "2026-09-16", "seenAt": "2026-11-06T23:13:53.249762741Z" } ], "githubStars": 6, "pypiWeekly": 801, "securityTxt": { "url": "https://cerebrium.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:45.765472019Z" }, "llmsTxt": { "url": "https://cerebrium.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:47.523695504Z" }, "domain": { "domain": "cerebrium.ai", "registered": "2021-06-11", "source": "https://rdap.identitydigital.services/rdap/domain/cerebrium.ai", "checkedAt": "2026-11-01T14:23:43.566923398Z" }, "pages": [ { "url": "https://www.cerebrium.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:26:30.141529853Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "be1ada48db42" }, { "url": "https://www.cerebrium.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:26:32.469828061Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "017a8d228768" }, { "url": "https://www.cerebrium.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:26:35.603397919Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a99804810a11" } ], "github": { "repo": "cerebriumai/cerebrium", "checkedAt": "2026-11-02T08:37:49.566844702Z", "stars": 6, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-27T13:05:03Z", "openIssues": 1, "openPRs": 8, "issuesOpened90d": 1, "issuesClosed90d": 0, "prsMerged90d": 22, "ci": { "branch": "main", "runs": 6, "success": 0, "failure": 6, "other": 0, "latest": "failure", "latestAt": "2025-11-24T16:25:07Z" }, "replies": { "sampled": 2, "unanswered": 1, "medianDays": 0 } }, "updatedAt": "2026-11-07T19:21:59.014046766Z" } }, "answer": "Together GPU Clusters scores 58.1 (C) on agent readiness against Cerebrium's 52.5 (D), and leads in 5 of 7 scored categories. Cerebrium leads on reliability and payments \u0026 pricing.", "b": { "slug": "together-gpu-clusters", "name": "Together GPU Clusters", "vendor": "Together AI", "vendorUrl": "https://www.together.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Together GPU Clusters rents multi-node NVIDIA H100, H200, B200 and B300 clusters with InfiniBand and shared storage, run as Kubernetes or Slurm, by the GPU-hour. Clusters are created and scaled from the console, the tg CLI, SDKs or REST API.", "url": "https://www.anchorterminal.com/tools/together-gpu-clusters", "markdownUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json", "dns": "together-gpu-clusters.grade.anchorterminal.com", "repo": "https://github.com/togethercomputer/together-py", "license": "Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT", "transports": [], "remoteUrl": "https://api.together.ai/v1/compute/clusters", "packages": [ { "registry": "pypi", "name": "together" }, { "registry": "npm", "name": "together-ai" } ], "auth": "api-key", "authNotes": "Bearer `TOGETHER_API_KEY`, scoped to a project, revocable and optionally expiring, the same keys as Together's other APIs. Only a project admin's key returns the cluster's admin kubeconfig. Team members can reach the Kubernetes API through OIDC with their own identity provider, and SSH uses OIDC or uploaded keys.", "pricing": "usage", "pricingNotes": "On-demand from $3.99 per GPU-hour (H100) to $9.99 (B300); reserved 3 to 180 days from $3.19 to $7.99; preemptible (preview) from $1.99. Storage per GiB-month. No ingress or egress fees. Reservations are prepaid and non-refundable, and creation needs enough credit to cover them.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the GPU clusters docs, billing pages or OpenAPI document (checked 2026-11-06). An exhausted balance returns 402 to scale requests with no payment requirements.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.together.ai/docs/gpu-clusters-overview", "llmsTxt": "https://docs.together.ai/llms.txt", "openapi": "https://github.com/togethercomputer/openapi", "capabilities": [ "compute.gpu", "compute.containers", "compute.batch" ], "tags": [ "hosted", "official", "usage", "prepaid", "openapi", "llms-txt", "kubernetes", "slurm", "python", "typescript", "cli", "h100", "b200" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 58.1, "grade": "C", "agentReady": false, "rank": 768, "ranked": true, "rankOf": 1510, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 75, "payments": 20, "reliability": 38, "schema": 92, "security": 68, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create.", "bestFor": "Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.", "strengths": [ "Public OpenAPI 3.1, llms.txt and Markdown docs, with an automation guide for CI pipelines", "Published per GPU-hour prices for on-demand, reserved and preemptible capacity, with no egress fees", "Kubernetes or Slurm on the same hardware, with InfiniBand and a persistent shared volume", "Automatic health checks and node repair, approved by hand or run automatically", "Project-scoped keys, admin-only kubeconfig and OIDC access for team members" ], "weaknesses": [ "Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero", "No status page component, SLA or published rate limits for GPU clusters", "No idempotency key on creation, so a retried create can bill a second cluster", "No free trial; reservations are prepaid and non-refundable", "Volumes bill until deleted and outlive the clusters they were attached to" ], "agentNotes": [ "Use `tg clusters`, not `tg beta clusters`, which stopped working with CLI 3.0 on 22 October 2026", "Pass `--json` and `--non-interactive`, poll `tg clusters retrieve` until status is Ready, and delete the cluster in a cleanup step", "Check for an existing cluster by name before retrying a create, since creation has no idempotency key", "Read live availability from the regions API and prices from the pricing page; the regions response has no prices", "Use a project admin's key when the task needs the kubeconfig, since other roles get none" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.1 } ], "editorialScores": { "ergonomics": 55, "maintenance": 75, "payments": 20, "reliability": 38, "schema": 92, "security": 68, "transparency": 46 }, "provenanceScore": 83, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv tool install \"together[cli]\"", "http": "curl -H \"Authorization: Bearer $TOGETHER_API_KEY\" https://api.together.ai/v1/compute/clusters" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/together-gpu-clusters" }, "sameCompany": [ "together-inference", "together-fine-tuning", "together-code-sandbox" ], "area": "models", "unitPrices": [ { "item": "H100 on-demand", "unit": "gpu-hour", "usd": 3.99, "note": "reserved $3.69 to $3.19, preemptible $1.99" }, { "item": "H200 on-demand", "unit": "gpu-hour", "usd": 5.99, "note": "reserved $4.99 to $3.99, preemptible $2.99" }, { "item": "B200 on-demand", "unit": "gpu-hour", "usd": 8.19, "note": "reserved $7.99 to $6.79, preemptible $4.09" }, { "item": "B300 on-demand", "unit": "gpu-hour", "usd": 9.99, "note": "preemptible $4.99, reserved by sales" } ], "provenance": { "legalEntity": "Together Computer, Inc.", "domain": "together.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.together.ai/terms-of-service", "privacy": "https://www.together.ai/privacy", "statusPage": "https://status.together.ai", "changelog": "https://docs.together.ai/docs/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Legal entity, terms, privacy and security.txt as on the Together AI Inference listing, checked 1 November 2026, and not re-read for this listing.", "docs.together.ai/robots.txt disallows only /cdn-cgi/ and /_next/, with Content-Signal ai-train=yes, search=yes, ai-input=yes. www.together.ai/robots.txt allows all.", "status.together.ai has no component for GPU clusters on 6 November 2026." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.json", "live": { "slug": "together-gpu-clusters", "probe": { "target": "https://api.together.ai/v1/compute/clusters", "method": "get", "lastAt": "2026-11-07T19:22:40.660879578Z", "lastOk": true, "lastStatus": 401, "lastMs": 263, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 493, "p95ms24h": 857, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "github", "name": "togethercomputer/together-py", "version": "v3.1.1", "released": "2026-11-04", "seenAt": "2026-11-07T00:12:15.100983119Z" }, { "registry": "npm", "name": "together-ai", "version": "1.0.0", "seenAt": "2026-11-07T00:12:15.067840103Z" }, { "registry": "pypi", "name": "together", "version": "3.1.1", "released": "2026-11-04", "seenAt": "2026-11-07T00:12:14.921893617Z" } ], "githubStars": 12, "npmWeekly": 99619, "pypiWeekly": 424792, "securityTxt": { "url": "https://together.ai/.well-known/security.txt", "state": "valid", "expires": "2028-09-30T00:00:00.000Z", "checkedAt": "2026-11-07T16:00:47.073630606Z" }, "llmsTxt": { "url": "https://docs.together.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:12.138384896Z" }, "updatedAt": "2026-11-07T19:22:40.660879578Z" } }, "edges": [ { "by": 22, "category": "schema", "leads": "together-gpu-clusters", "name": "Schema \u0026 documentation", "reasons": { "a": "Public OpenAPI 3.0 spec for the management API with 94 operations on 73 paths. Deployed endpoints take whatever the owner's function defines (25). llms.txt and a .md twin of every docs page (10). Operation descriptions are one line each. The guides say when to use the protected tier, async runs or a custom runtime (12 of 20). Required fields are marked, but the spec has no enums (valid values such as member and billing sit in prose) and several arrays and objects are untyped (7 of 15). The guides carry many worked examples. The spec has no examples and documents only 400 and 401 errors with a `message` string (8 of 15). Paths are versioned v2, v3 and v4 and CLI releases are dated on GitHub, but the spec version is a fixed 1.0.0 and no platform changelog was found (8 of 15). Docs and spec per the 8 October check, not re-read on 4 November. 25 + 10 + 12 + 7 + 8 + 8 = 70.", "b": "Public OpenAPI 3.1 for /v1/compute/clusters and shared volumes, MIT, embedded in every reference page (25). llms.txt and a Markdown twin of every page (10). The docs say when to choose Kubernetes or Slurm and each capacity type, and the management page carries instructions for agents on reporting live availability and prices (18). Enums for cluster type, billing type, GPU type and status, required fields marked (13). CLI, Python, TypeScript and console steps on each task, with 402 and 403 cases documented, though no error catalogue for the clusters API (11). Versioned SDKs and a dated changelog with cluster entries (15). 25+10+18+13+11+15 = 92." }, "scores": { "a": 70, "b": 92 } }, { "by": 10, "category": "reliability", "leads": "cerebrium", "name": "Reliability", "reasons": { "a": "Graded as a hosted service. Status page at status.cerebrium.ai with 11 components and 90 days of history, per the 8 October check, not re-read on 4 November (cerebrium.ai's terms bar robots and automatic means) (20). The 8 October reading covered the window to that day. Since 6 August it held degradations of 5 hours 7 minutes on 19 August (US, upstream) and 7 hours 20 minutes on 2 September (EU, provider network), both partial; 9 October to 4 November is unread, so the line keeps its recorded award (10). No request rate limits found. Plans publish concurrency caps of 5 GPUs and 500 containers on Hobby and 30 and 1,000 on Standard (5 of 15). No 429 or backoff guidance for callers found. Webhook forwarding retries failed deliveries and the docs ask for idempotent webhook receivers, partly met, kept (3 of 15). No SLA found. The 99.9 and 99.999 per cent uptime figures on the site are claims without terms (0). Endpoints, the CLI and the REST API are GA, while multi-region deployment and checkpointing are marked beta (10). Docs and status per the 8 October check, not re-read on 4 November. 20 + 10 + 5 + 3 + 0 + 10 = 48.", "b": "Read with the hosted lines. status.together.ai lists the website, the playground and serverless models with no component for GPU clusters, and a vendor page with no component for the product takes 15 in this run, as for Together's Code Sandbox and fine-tuning listings (15). No incident history for clusters can be read (5). No rate limits for the clusters API found (0). Together's docs give 429 and 503 backoff guidance for its APIs, per the inference listing's 1 November check, and the CLI has `--non-interactive` and `--json` for scripted retries, but creation has no idempotency key (8). No SLA for clusters found; the published 99% commitment covers provisioned inference throughput only (0). Generally available since 9 September 2025 and out of the CLI's beta paths since 22 October 2026, with preemptible nodes in preview (10). 15+5+0+8+0+10 = 38." }, "scores": { "a": 48, "b": 38 } }, { "by": 10, "category": "payments", "leads": "cerebrium", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol (0). Per-second GPU, CPU and memory prices and the storage price are published without a login (20). The Hobby plan has no fee, but compute is billed from the first second, no free compute allowance is stated and the pricing page does not say whether a card is needed, partly met, kept (10 of 20). Signup and `cerebrium login` are browser flows (0). Pricing per the 8 October check, not re-read on 4 November. 0 + 20 + 10 + 0 = 30.", "b": "No machine payment protocol (0). Per GPU-hour prices for each capacity type and per GiB-month storage published without a login (20). No free trial, and creation needs credit for the full reservation or a minimum on-demand period (0). Sign-up and credit purchase are browser steps (0). 0+20+0+0 = 20." }, "scores": { "a": 30, "b": 20 } }, { "by": 10, "category": "maintenance", "leads": "together-gpu-clusters", "name": "Maintenance \u0026 community", "reasons": { "a": "CLI v2.9.0 tagged on 16 September 2026, 49 days before the check, the newest tag in the repository; commits since (20 and 21 October, licence notices and a Go 1.26.10 upgrade) are untagged (20). Five tagged releases since 6 August 2026 (v2.5.4 on 7 August, v2.6.0, v2.7.0, v2.8.0, v2.9.0) (20). Closed service with a Discord community and Slack or Intercom support by plan. No platform changelog, and we couldn't read the GitHub issue tracker (8 of 25). The CLI ships on PyPI, Homebrew and as binaries. There is no language SDK (10 of 15). The repository has lint and test workflows and now pins Go 1.26.10. CI status wasn't visible in the clone (7 of 10). 20 + 20 + 8 + 10 + 7 = 65.", "b": "Closed service. The newest cluster change is CLI and SDK 3.0 on 22 October 2026, 15 days before this check (30). Dated cluster entries in the 90 days from 8 August include 12, 18, 19, 24, 27 and 28 August, 10 September and 22 October (20). Dated changelog, a support portal and Discord, with responsiveness not tested (8). Python SDK 3.1 and TypeScript SDK 1.0 are current and cover clusters (15). SDK CI and dependencies weren't audited (2). 30+20+8+15+2 = 75." }, "scores": { "a": 65, "b": 75 } }, { "by": 8, "category": "security", "leads": "together-gpu-clusters", "name": "Security \u0026 auth", "reasons": { "a": "Service account tokens expire after up to one year (or never, if set to 0), are limited to 1 to 50 named projects and are revoked by deleting the account. Inference API keys are separate and can be deleted. No per-action scopes, and the CLI's SECURITY.md says tokens sit in plaintext in a config file with mode 0644 (20 of 30). Users have owner, member and billing roles, but tokens have no read-only form, and `disable_auth` defaults to true, so deployed endpoints answer without a token unless the owner changes it (5 of 20). Runs the owner's code and returns its output (10). Docs readings per the 8 October check, not re-read on 4 November. Audit log of 22 actions with actor, IP address and outcome, in the dashboard and over the API, on Standard (7 days) and Enterprise (30 days) only (12 of 15). SOC 2 Type II announced on 8 July 2026, HIPAA BAA on request, a trust centre, and disclosure to security@cerebrium.ai. No security.txt and no bug bounty found (13 of 20). No advisory for cerebrium on OSV on 4 November. 20 + 5 + 10 + 12 + 13 = 60.", "b": "Project-scoped API keys, revocable with optional expiry, read as Together's other listings read the same key model (30). Admin and editor roles with no read-only role. Only admins get the admin kubeconfig, which has cluster-admin rights, and OIDC lets editors use kubectl under RBAC. Deletes run without confirmation when `--non-interactive` is passed (8). The API returns cluster state, not third-party content (10). Invoices itemise reserved, on-demand and storage charges, and no audit log for cluster operations was found (5). security.txt with a HackerOne route, per the 1 November check of the inference listing (15). 30+8+10+5+15 = 68." }, "scores": { "a": 60, "b": 68 } }, { "by": 6, "category": "ergonomics", "leads": "together-gpu-clusters", "name": "Agent ergonomics", "reasons": { "a": "No field selection. A `limit` parameter on five list operations, and app and run objects are small (12 of 25). The audit log and runs page with `limit` and `nextToken` and filter by status, status code and time, though other lists use `page`, `pageSize` or `offset` (14 of 20). Errors are a `message` string with 400 or 401. Deployed endpoints return 200, 401, 403, 404 or 5xx, and a function can set its own `status_code` (10 of 20). No idempotency keys. Async calls return a `run_id` that can be listed and cancelled (5 of 20). Defaults are sensible (`min_replicas` 0, `cooldown` 60) and `cerebrium init` writes a working config, but there is a CLI only and no language SDK (8 of 15). Docs per the 8 October check, not re-read on 4 November; the CLI clone confirms `--output json` on list commands since 10 August. 12 + 14 + 10 + 5 + 8 = 49.", "b": "Cluster objects are compact, and `--json` gives machine-readable output, but list calls take no field selection (15). No pagination or filters on the clusters list (8). 402 and 403 with readable messages such as \"Insufficient credits for cluster creation\", and troubleshooting for common failures (12). Status polling until Ready is documented and deletes run non-interactively, but there is no idempotency key on creation and a duplicate create bills a second cluster (8). Official Python and TypeScript SDKs and a CLI, though a create takes GPU type, region, driver and CUDA versions, cluster type and billing type (12). 15+8+12+8+12 = 55." }, "scores": { "a": 49, "b": 55 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Cerebrium Inc.", "b": "Together AI", "name": "Vendor" }, { "a": "https://rest.cerebrium.ai", "b": "https://api.together.ai/v1/compute/clusters", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cerebrium's terms of service. The CLI is MIT", "b": "Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-16", "b": "2026-10-22", "name": "Last release" }, { "a": "no date given", "b": "no date given", "name": "Terms last updated" }, { "a": "no date given", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Together GPU Clusters scores 58.1 (C) on agent readiness against Cerebrium's 52.5 (D), and leads in 5 of 7 scored categories. Cerebrium leads on reliability and payments \u0026 pricing.", "question": "Which is better for AI agents, Cerebrium or Together GPU Clusters?" }, { "answer": "Yes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.", "question": "Can an agent call Cerebrium and Together GPU Clusters without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 48 against 38", "Payments \u0026 pricing, 30 against 20" ], "also": null, "goodFor": "Teams serving their own models as real-time endpoints (voice, LLM, image) who want per-second billing, multi-region placement and a scriptable management API.", "slug": "cerebrium", "watchFor": "`disable_auth` defaults to true, so a deployed endpoint answers without a token unless the owner changes it" }, { "aheadOn": [ "Schema \u0026 documentation, 92 against 70", "Agent ergonomics, 55 against 49", "Security \u0026 auth, 68 against 60", "Maintenance \u0026 community, 75 against 65" ], "also": null, "goodFor": "Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.", "slug": "together-gpu-clusters", "watchFor": "Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero" } ], "history": { "cerebrium": [ { "causes": [ "correction", "time" ], "date": "2026-11-04", "delta": -2.9, "from": 55.4, "fromGrade": "C", "to": 52.5, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 55.3, "fromGrade": "C", "to": 55.4, "toGrade": "C" } ], "together-gpu-clusters": null }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-cerebrium.json", "title": "Baseten vs Cerebrium", "url": "https://www.anchorterminal.com/compare/baseten-vs-cerebrium" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters.json", "title": "Baseten vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-cerebrium.json", "title": "Beam vs Cerebrium", "url": "https://www.anchorterminal.com/compare/beam-vs-cerebrium" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters.json", "title": "Beam vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.json", "title": "Cerebrium vs Cloud Run GPUs", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.json", "title": "Cerebrium vs CoreWeave", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-crusoe-cloud.json", "title": "Cerebrium vs Crusoe Cloud", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-crusoe-cloud" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-gpusmarket.json", "title": "Cerebrium vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-gpusmarket" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.json", "title": "Cerebrium vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-hyperbolic.json", "title": "Cerebrium vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-koyeb.json", "title": "Cerebrium vs Koyeb", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-lambda.json", "title": "Cerebrium vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-massed-compute.json", "title": "Cerebrium vs Massed Compute", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-modal.json", "title": "Cerebrium vs Modal", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-nebius-ai-cloud.json", "title": "Cerebrium vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-northflank.json", "title": "Cerebrium vs Northflank", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy.json", "title": "Cerebrium vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-runpod.json", "title": "Cerebrium vs Runpod", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-thunder-compute.json", "title": "Cerebrium vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.json", "title": "Cerebrium vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-verda.json", "title": "Cerebrium vs Verda", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.json", "title": "Cloud Run GPUs vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters.json", "title": "CoreWeave vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.json", "title": "Crusoe Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.json", "title": "GPUsMarket vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters.json", "title": "Hugging Face Inference Endpoints vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.json", "title": "Hyperbolic vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.json", "title": "Koyeb vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.json", "title": "Lambda Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters.json", "title": "Massed Compute vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters.json", "title": "Modal vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters.json", "title": "Nebius AI Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters.json", "title": "Northflank vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.json", "title": "Replicate Deployments vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.json", "title": "Runpod vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.json", "title": "Thunder Compute vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.json", "title": "Together GPU Clusters vs Vast.ai", "url": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda.json", "title": "Together GPU Clusters vs Verda", "url": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda" } ], "panel": null, "scores": [ { "by": 10, "cerebrium": 48, "edge": "cerebrium", "key": "reliability", "name": "Reliability", "together-gpu-clusters": 38, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 22, "cerebrium": 70, "edge": "together-gpu-clusters", "key": "schema", "name": "Schema \u0026 documentation", "together-gpu-clusters": 92, "weight": 13 }, { "by": 6, "cerebrium": 49, "edge": "together-gpu-clusters", "key": "ergonomics", "name": "Agent ergonomics", "together-gpu-clusters": 55, "weight": 13 }, { "by": 8, "cerebrium": 60, "edge": "together-gpu-clusters", "key": "security", "name": "Security \u0026 auth", "together-gpu-clusters": 68, "weight": 14 }, { "by": 10, "cerebrium": 30, "edge": "cerebrium", "key": "payments", "name": "Payments \u0026 pricing", "together-gpu-clusters": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 10, "cerebrium": 65, "edge": "together-gpu-clusters", "key": "maintenance", "name": "Maintenance \u0026 community", "together-gpu-clusters": 75, "weight": 7 }, { "by": 1, "cerebrium": 64, "edge": "together-gpu-clusters", "key": "transparency", "name": "Transparency \u0026 trust", "together-gpu-clusters": 65, "weight": 7 } ], "summary": "Together GPU Clusters scores 58.1 (C) on agent readiness against Cerebrium's 52.5 (D), and leads in 5 of 7 scored categories. Cerebrium leads on reliability and payments \u0026 pricing. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "cerebrium": "Per-second GPU prices are public, a 94-operation OpenAPI spec covers the management API, and service account tokens expire and are limited to named projects. Deployed endpoints are callable without a token unless `disable_auth = false` is set, and no request rate limits, 429 handling or SLA were found in the reviewed documentation.", "together-gpu-clusters": "Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters", "json": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.min.md" }, "markdown": "Together GPU Clusters scores 58.1 (C) on agent readiness against Cerebrium's 52.5 (D), and leads in 5 of 7 scored categories. Cerebrium leads on reliability and payments \u0026 pricing. Both do gpu compute.\n\n- Cerebrium: grade D, 52.5/100, rank #989 of 1510. Markdown https://www.anchorterminal.com/tools/cerebrium.md · JSON https://www.anchorterminal.com/api/v1/tools/cerebrium.json\n- Together GPU Clusters: grade C, 58.1/100, rank #768 of 1510. Markdown https://www.anchorterminal.com/tools/together-gpu-clusters.md · JSON https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json\n- Best GPU and serverless compute for AI workloads: https://www.anchorterminal.com/best/gpu-compute/index.md\n- All 231 gpu compute comparisons: https://www.anchorterminal.com/compare/gpu-compute/index.md\n\n## Which one, for what\n\n### Cerebrium (D)\n\nGood for: Teams serving their own models as real-time endpoints (voice, LLM, image) who want per-second billing, multi-region placement and a scriptable management API.\n\nAhead on:\n- Reliability, 48 against 38\n- Payments \u0026 pricing, 30 against 20\n\nWatch for: `disable_auth` defaults to true, so a deployed endpoint answers without a token unless the owner changes it\n\n### Together GPU Clusters (C)\n\nGood for: Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.\n\nAhead on:\n- Schema \u0026 documentation, 92 against 70\n- Agent ergonomics, 55 against 49\n- Security \u0026 auth, 68 against 60\n- Maintenance \u0026 community, 75 against 65\n\nWatch for: Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Together GPU Clusters +22\n\n- Cerebrium (70): Public OpenAPI 3.0 spec for the management API with 94 operations on 73 paths. Deployed endpoints take whatever the owner's function defines (25). llms.txt and a .md twin of every docs page (10). Operation descriptions are one line each. The guides say when to use the protected tier, async runs or a custom runtime (12 of 20). Required fields are marked, but the spec has no enums (valid values such as member and billing sit in prose) and several arrays and objects are untyped (7 of 15). The guides carry many worked examples. The spec has no examples and documents only 400 and 401 errors with a `message` string (8 of 15). Paths are versioned v2, v3 and v4 and CLI releases are dated on GitHub, but the spec version is a fixed 1.0.0 and no platform changelog was found (8 of 15). Docs and spec per the 8 October check, not re-read on 4 November. 25 + 10 + 12 + 7 + 8 + 8 = 70.\n- Together GPU Clusters (92): Public OpenAPI 3.1 for /v1/compute/clusters and shared volumes, MIT, embedded in every reference page (25). llms.txt and a Markdown twin of every page (10). The docs say when to choose Kubernetes or Slurm and each capacity type, and the management page carries instructions for agents on reporting live availability and prices (18). Enums for cluster type, billing type, GPU type and status, required fields marked (13). CLI, Python, TypeScript and console steps on each task, with 402 and 403 cases documented, though no error catalogue for the clusters API (11). Versioned SDKs and a dated changelog with cluster entries (15). 25+10+18+13+11+15 = 92.\n\n### Reliability: Cerebrium +10\n\n- Cerebrium (48): Graded as a hosted service. Status page at status.cerebrium.ai with 11 components and 90 days of history, per the 8 October check, not re-read on 4 November (cerebrium.ai's terms bar robots and automatic means) (20). The 8 October reading covered the window to that day. Since 6 August it held degradations of 5 hours 7 minutes on 19 August (US, upstream) and 7 hours 20 minutes on 2 September (EU, provider network), both partial; 9 October to 4 November is unread, so the line keeps its recorded award (10). No request rate limits found. Plans publish concurrency caps of 5 GPUs and 500 containers on Hobby and 30 and 1,000 on Standard (5 of 15). No 429 or backoff guidance for callers found. Webhook forwarding retries failed deliveries and the docs ask for idempotent webhook receivers, partly met, kept (3 of 15). No SLA found. The 99.9 and 99.999 per cent uptime figures on the site are claims without terms (0). Endpoints, the CLI and the REST API are GA, while multi-region deployment and checkpointing are marked beta (10). Docs and status per the 8 October check, not re-read on 4 November. 20 + 10 + 5 + 3 + 0 + 10 = 48.\n- Together GPU Clusters (38): Read with the hosted lines. status.together.ai lists the website, the playground and serverless models with no component for GPU clusters, and a vendor page with no component for the product takes 15 in this run, as for Together's Code Sandbox and fine-tuning listings (15). No incident history for clusters can be read (5). No rate limits for the clusters API found (0). Together's docs give 429 and 503 backoff guidance for its APIs, per the inference listing's 1 November check, and the CLI has `--non-interactive` and `--json` for scripted retries, but creation has no idempotency key (8). No SLA for clusters found; the published 99% commitment covers provisioned inference throughput only (0). Generally available since 9 September 2025 and out of the CLI's beta paths since 22 October 2026, with preemptible nodes in preview (10). 15+5+0+8+0+10 = 38.\n\n### Payments \u0026 pricing: Cerebrium +10\n\n- Cerebrium (30): No machine payment protocol (0). Per-second GPU, CPU and memory prices and the storage price are published without a login (20). The Hobby plan has no fee, but compute is billed from the first second, no free compute allowance is stated and the pricing page does not say whether a card is needed, partly met, kept (10 of 20). Signup and `cerebrium login` are browser flows (0). Pricing per the 8 October check, not re-read on 4 November. 0 + 20 + 10 + 0 = 30.\n- Together GPU Clusters (20): No machine payment protocol (0). Per GPU-hour prices for each capacity type and per GiB-month storage published without a login (20). No free trial, and creation needs credit for the full reservation or a minimum on-demand period (0). Sign-up and credit purchase are browser steps (0). 0+20+0+0 = 20.\n\n### Maintenance \u0026 community: Together GPU Clusters +10\n\n- Cerebrium (65): CLI v2.9.0 tagged on 16 September 2026, 49 days before the check, the newest tag in the repository; commits since (20 and 21 October, licence notices and a Go 1.26.10 upgrade) are untagged (20). Five tagged releases since 6 August 2026 (v2.5.4 on 7 August, v2.6.0, v2.7.0, v2.8.0, v2.9.0) (20). Closed service with a Discord community and Slack or Intercom support by plan. No platform changelog, and we couldn't read the GitHub issue tracker (8 of 25). The CLI ships on PyPI, Homebrew and as binaries. There is no language SDK (10 of 15). The repository has lint and test workflows and now pins Go 1.26.10. CI status wasn't visible in the clone (7 of 10). 20 + 20 + 8 + 10 + 7 = 65.\n- Together GPU Clusters (75): Closed service. The newest cluster change is CLI and SDK 3.0 on 22 October 2026, 15 days before this check (30). Dated cluster entries in the 90 days from 8 August include 12, 18, 19, 24, 27 and 28 August, 10 September and 22 October (20). Dated changelog, a support portal and Discord, with responsiveness not tested (8). Python SDK 3.1 and TypeScript SDK 1.0 are current and cover clusters (15). SDK CI and dependencies weren't audited (2). 30+20+8+15+2 = 75.\n\n### Security \u0026 auth: Together GPU Clusters +8\n\n- Cerebrium (60): Service account tokens expire after up to one year (or never, if set to 0), are limited to 1 to 50 named projects and are revoked by deleting the account. Inference API keys are separate and can be deleted. No per-action scopes, and the CLI's SECURITY.md says tokens sit in plaintext in a config file with mode 0644 (20 of 30). Users have owner, member and billing roles, but tokens have no read-only form, and `disable_auth` defaults to true, so deployed endpoints answer without a token unless the owner changes it (5 of 20). Runs the owner's code and returns its output (10). Docs readings per the 8 October check, not re-read on 4 November. Audit log of 22 actions with actor, IP address and outcome, in the dashboard and over the API, on Standard (7 days) and Enterprise (30 days) only (12 of 15). SOC 2 Type II announced on 8 July 2026, HIPAA BAA on request, a trust centre, and disclosure to security@cerebrium.ai. No security.txt and no bug bounty found (13 of 20). No advisory for cerebrium on OSV on 4 November. 20 + 5 + 10 + 12 + 13 = 60.\n- Together GPU Clusters (68): Project-scoped API keys, revocable with optional expiry, read as Together's other listings read the same key model (30). Admin and editor roles with no read-only role. Only admins get the admin kubeconfig, which has cluster-admin rights, and OIDC lets editors use kubectl under RBAC. Deletes run without confirmation when `--non-interactive` is passed (8). The API returns cluster state, not third-party content (10). Invoices itemise reserved, on-demand and storage charges, and no audit log for cluster operations was found (5). security.txt with a HackerOne route, per the 1 November check of the inference listing (15). 30+8+10+5+15 = 68.\n\n### Agent ergonomics: Together GPU Clusters +6\n\n- Cerebrium (49): No field selection. A `limit` parameter on five list operations, and app and run objects are small (12 of 25). The audit log and runs page with `limit` and `nextToken` and filter by status, status code and time, though other lists use `page`, `pageSize` or `offset` (14 of 20). Errors are a `message` string with 400 or 401. Deployed endpoints return 200, 401, 403, 404 or 5xx, and a function can set its own `status_code` (10 of 20). No idempotency keys. Async calls return a `run_id` that can be listed and cancelled (5 of 20). Defaults are sensible (`min_replicas` 0, `cooldown` 60) and `cerebrium init` writes a working config, but there is a CLI only and no language SDK (8 of 15). Docs per the 8 October check, not re-read on 4 November; the CLI clone confirms `--output json` on list commands since 10 August. 12 + 14 + 10 + 5 + 8 = 49.\n- Together GPU Clusters (55): Cluster objects are compact, and `--json` gives machine-readable output, but list calls take no field selection (15). No pagination or filters on the clusters list (8). 402 and 403 with readable messages such as \"Insufficient credits for cluster creation\", and troubleshooting for common failures (12). Status polling until Ready is documented and deletes run non-interactively, but there is no idempotency key on creation and a duplicate create bills a second cluster (8). Official Python and TypeScript SDKs and a CLI, though a create takes GPU type, region, driver and CUDA versions, cluster type and billing type (12). 15+8+12+8+12 = 55.\n\n## Score by category\n\n| Category | Weight | Cerebrium | Together GPU Clusters | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 38 | Cerebrium +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 92 | Together GPU Clusters +22 |\n| Agent ergonomics | 13% (16.2 this run) | 49 | 55 | Together GPU Clusters +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 68 | Together GPU Clusters +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 20 | Cerebrium +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 75 | Together GPU Clusters +10 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 65 | Together GPU Clusters +1 |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **52.5 · D** | **58.1 · C** | |\n\n## Facts side by side\n\n| Fact | Cerebrium | Together GPU Clusters |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Cerebrium Inc. | Together AI |\n| Hosted endpoint | `https://rest.cerebrium.ai` | `https://api.together.ai/v1/compute/clusters` |\n| Transports | HTTP | |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under Cerebrium's terms of service. The CLI is MIT | Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-16 | 2026-10-22 |\n| Terms last updated | no date given | no date given |\n| Privacy policy last updated | no date given | no date given |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n\n## How the scores have moved\n\n### Cerebrium\n\n- -2.9 on 4 November 2026 (C to D): correction, time\n- +0.1 on 27 October 2026: checklist\n\n### Together GPU Clusters\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Cerebrium.** Per-second GPU prices are public, a 94-operation OpenAPI spec covers the management API, and service account tokens expire and are limited to named projects. Deployed endpoints are callable without a token unless `disable_auth = false` is set, and no request rate limits, 429 handling or SLA were found in the reviewed documentation.\n\n**Together GPU Clusters.** Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create.\n\n## Before you call either\n\n### Cerebrium\n\n1. Set `disable_auth = false` in `cerebrium.toml` before deploying. The default leaves the endpoint callable by anyone with the URL\n2. Authenticate headless with `CEREBRIUM_SERVICE_ACCOUNT_TOKEN`. `cerebrium login` opens a browser\n3. Raise `response_grace_period` for long work. It defaults to 15 minutes and async runs stop at 12 hours\n4. Send `?async=true` to get a `run_id` with HTTP 202, and add `webhookEndpoint` because async calls return no result to the caller\n5. Check the plan before choosing hardware. A100, H100, H200, B200 and RTX PRO 6000 need Standard, and `protected` compute bills at twice the listed rate\n\n### Together GPU Clusters\n\n1. Use `tg clusters`, not `tg beta clusters`, which stopped working with CLI 3.0 on 22 October 2026\n2. Pass `--json` and `--non-interactive`, poll `tg clusters retrieve` until status is Ready, and delete the cluster in a cleanup step\n3. Check for an existing cluster by name before retrying a create, since creation has no idempotency key\n4. Read live availability from the regions API and prices from the pricing page; the regions response has no prices\n5. Use a project admin's key when the task needs the kubeconfig, since other roles get none\n\n## Questions\n\n### Which is better for AI agents, Cerebrium or Together GPU Clusters?\n\nTogether GPU Clusters scores 58.1 (C) on agent readiness against Cerebrium's 52.5 (D), and leads in 5 of 7 scored categories. Cerebrium leads on reliability and payments \u0026 pricing.\n\n### Can an agent call Cerebrium and Together GPU Clusters without installing anything?\n\nYes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cerebrium\", \"b\": \"together-gpu-clusters\"}`. From a terminal: `anchor compare cerebrium together-gpu-clusters`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cerebrium.json and https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json\n\n## Other comparisons with Cerebrium or Together GPU Clusters\n\n- [Baseten vs Cerebrium](https://www.anchorterminal.com/compare/baseten-vs-cerebrium.md)\n- [Baseten vs Together GPU Clusters](https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters.md)\n- [Beam vs Cerebrium](https://www.anchorterminal.com/compare/beam-vs-cerebrium.md)\n- [Beam vs Together GPU Clusters](https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters.md)\n- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)\n- [Cerebrium vs CoreWeave](https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.md)\n- [Cerebrium vs Crusoe Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-crusoe-cloud.md)\n- [Cerebrium vs GPUsMarket](https://www.anchorterminal.com/compare/cerebrium-vs-gpusmarket.md)\n- [Cerebrium vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.md)\n- [Cerebrium vs Hyperbolic](https://www.anchorterminal.com/compare/cerebrium-vs-hyperbolic.md)\n- [Cerebrium vs Koyeb](https://www.anchorterminal.com/compare/cerebrium-vs-koyeb.md)\n- [Cerebrium vs Lambda Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-lambda.md)\n- [Cerebrium vs Massed Compute](https://www.anchorterminal.com/compare/cerebrium-vs-massed-compute.md)\n- [Cerebrium vs Modal](https://www.anchorterminal.com/compare/cerebrium-vs-modal.md)\n- [Cerebrium vs Nebius AI Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-nebius-ai-cloud.md)\n- [Cerebrium vs Northflank](https://www.anchorterminal.com/compare/cerebrium-vs-northflank.md)\n- [Cerebrium vs Replicate Deployments](https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy.md)\n- [Cerebrium vs Runpod](https://www.anchorterminal.com/compare/cerebrium-vs-runpod.md)\n- [Cerebrium vs Thunder Compute](https://www.anchorterminal.com/compare/cerebrium-vs-thunder-compute.md)\n- [Cerebrium vs Vast.ai](https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.md)\n- [Cerebrium vs Verda](https://www.anchorterminal.com/compare/cerebrium-vs-verda.md)\n- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md)\n- [CoreWeave vs Together GPU Clusters](https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters.md)\n- [Crusoe Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.md)\n- [GPUsMarket vs Together GPU Clusters](https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.md)\n- [Hugging Face Inference Endpoints vs Together GPU Clusters](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters.md)\n- [Hyperbolic vs Together GPU Clusters](https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.md)\n- [Koyeb vs Together GPU Clusters](https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.md)\n- [Lambda Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.md)\n- [Massed Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters.md)\n- [Modal vs Together GPU Clusters](https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters.md)\n- [Nebius AI Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters.md)\n- [Northflank vs Together GPU Clusters](https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters.md)\n- [Replicate Deployments vs Together GPU Clusters](https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.md)\n- [Runpod vs Together GPU Clusters](https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.md)\n- [Thunder Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.md)\n- [Together GPU Clusters vs Vast.ai](https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.md)\n- [Together GPU Clusters vs Verda](https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cerebrium vs Together GPU Clusters", "url": "" } ], "description": "Together GPU Clusters scores 58.1 (C) to Cerebrium's 52.5 (D) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cerebrium D 52.5", "Together GPU Clusters C 58.1", "scores" ], "h1": "Cerebrium vs Together GPU Clusters", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cerebrium-vs-together-gpu-clusters", "published": "2026-10-01", "section": "tools", "title": "Cerebrium vs Together GPU Clusters for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters" }, "tokens": { "markdown": 5250, "slim": 2930 }, "version": 1 }