{ "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", "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": 920, "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": 55.3, "grade": "C", "agentReady": false, "rank": 454, "ranked": true, "rankOf": 629, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 49, "maintenance": 75, "payments": 30, "reliability": 48, "schema": 70, "security": 60, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "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", "Several multi-hour degradations of the Inference API between 15 July and 2 September 2026, and a 10-minute outage on 21 July", "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": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.3 } ], "editorialScores": { "ergonomics": 49, "maintenance": 75, "payments": 30, "reliability": 48, "schema": 70, "security": 60, "transparency": 45 }, "provenanceScore": 80 }, "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": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cerebrium.json", "live": { "slug": "cerebrium", "probe": { "target": "https://rest.cerebrium.ai", "method": "get", "lastAt": "2026-10-08T19:08:42.947721656Z", "lastOk": true, "lastStatus": 403, "lastMs": 326, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 251, "p95ms24h": 326, "samples24h": 19, "samples30d": 19, "days": [ { "date": "2026-10-08", "probes": 19, "ok": 19 } ] }, "vendorStatus": { "page": "https://status.cerebrium.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-08T17:50:27.054213755Z" }, "pages": [ { "url": "https://www.cerebrium.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:26:57.20274404Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "be1ada48db42" }, { "url": "https://www.cerebrium.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:26:59.281048683Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "017a8d228768" }, { "url": "https://www.cerebrium.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:27:01.554163635Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a99804810a11" } ], "updatedAt": "2026-10-08T19:08:42.947721656Z" } }, "answer": "CoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing.", "b": { "slug": "coreweave", "name": "CoreWeave", "vendor": "CoreWeave, Inc.", "vendorUrl": "https://www.coreweave.com", "kind": "http-api", "category": "gpu-compute", "summary": "CoreWeave is a GPU cloud that rents NVIDIA GPU nodes through a managed Kubernetes service (CKS), with REST and gRPC platform APIs, a Terraform provider and a hosted MCP server for observability.", "url": "https://www.anchorterminal.com/tools/coreweave", "markdownUrl": "https://www.anchorterminal.com/tools/coreweave.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/coreweave.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/coreweave.json", "repo": "https://github.com/coreweave/terraform-provider-coreweave", "license": "Proprietary service under CoreWeave's Terms of Service. The Terraform provider on GitHub is MIT", "transports": [ "http" ], "remoteUrl": "https://api.coreweave.com", "packages": [], "auth": "pat", "authNotes": "Access starts with sales approval. CoreWeave's sales team approves an organisation and emails an activation link, then a user with the Access Token User role creates an API access token at console.coreweave.com/tokens with a name and an expiry. The token is user-scoped, shown once, revocable in the console and sent as `Authorization: Bearer` to api.coreweave.com, to a CKS cluster's Kubernetes API (through a kubeconfig) and to the Mission Control MCP server. What it can do follows the user's IAM roles, which include a Viewer and an Admin role per service. CKS workloads can also use OIDC workload identity federation. Serverless Inference takes a separate Forge API key.", "pricing": "usage", "pricingNotes": "Per instance-hour, published without a login. On demand in North America, HGX H100 (8 GPUs) $49.24, HGX H200 $50.44, HGX B200 $68.80, A100 $21.60, L40S $18.00, L40 $10.00, GB200 NVL72 (4 GPUs) $42.00 and GH200 (1 GPU) $6.50, with spot rates on most. GB300 NVL72 and HGX B300 on demand are quoted by sales. Reserved capacity is discounted by up to 60 per cent through sales. AI Object Storage is $0.06 a GB-month hot, $0.03 warm and $0.015 cold, distributed file storage $0.07, and egress, VPC and the CKS control plane are free. No free tier or self-serve trial was found, and the terms treat any trial as part of the sales-run ARENA programme (https://www.coreweave.com/pricing, https://docs.coreweave.com/policies/terms-of-service).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the API references or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 38, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.coreweave.com/", "llmsTxt": "https://docs.coreweave.com/llms.txt", "openapi": "https://docs.coreweave.com/products/cks/reference/cks-api", "capabilities": [ "compute.gpu", "compute.containers", "compute.endpoints", "compute.batch" ], "tags": [ "hosted", "usage-priced", "enterprise", "sales-led", "mcp", "openapi", "llms-txt", "terraform", "status-page", "soc2" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 61.5, "grade": "C", "agentReady": false, "rank": 323, "ranked": true, "rankOf": 629, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 80, "payments": 20, "reliability": 50, "schema": 79, "security": 74, "transparency": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Per-hour prices for 8-GPU H100, H200 and B200 nodes are public, the docs ship as Markdown with llms.txt and embedded OpenAPI specs, and IAM has read-only roles per service. An organisation must be approved by CoreWeave's sales team before any token exists, and no request rate limits were found in the reviewed documentation.", "bestFor": "Teams that already run Kubernetes and need whole multi-GPU nodes or clusters for training and dedicated inference, with a contract and IAM.", "strengths": [ "On-demand and spot prices per instance-hour are public, for example HGX H100 at $49.24 on demand and $19.71 spot for 8 GPUs", "Docs are served as Markdown with an llms.txt index, and OpenAPI 3.0 specs for CKS, VPC, storage and inference are embedded in the reference pages", "IAM has Viewer and Admin roles per service, API tokens carry an expiry, and Kubernetes audit logs can be forwarded with Telemetry Relay", "Terms carry a service level objective of 99.9 per cent across multiple regions and 99 per cent in one, with financial credits", "Dated changelog with 18 entries between 10 July and 2 October 2026, and a Terraform provider tagged v0.24.0 on 11 September 2026" ], "weaknesses": [ "No self-serve route. CoreWeave's sales team approves an organisation and emails the activation link before a token can be created", "No request rate limits, 429 guidance or idempotency keys found for api.coreweave.com in the reviewed documentation", "The CKS API is versioned v1beta1 and the Node Pool resource and Dedicated Inference API v1alpha1", "Three incidents between 26 September and 6 October 2026, including a US-CENTRAL-09A network outage of over two hours on 5 October", "The MCP tool `coreweave_kubectl_apply` ignores its `dry_run` parameter and applies the manifest, per the tool reference" ], "agentNotes": [ "Create an API access token at console.coreweave.com/tokens with an expiry and send it as `Authorization: Bearer` to https://api.coreweave.com", "Add GPUs by applying a NodePool resource (`compute.coreweave.com/v1alpha1`) to a CKS cluster with `instanceType` and `targetNodes`. `instanceType` can't be changed afterwards", "Set `targetNodes` to 0 or delete the Node Pool when a job ends. Nodes are whole 8-GPU machines billed by the hour", "Never pass `dry_run` to the MCP tool `coreweave_kubectl_apply` expecting a preview. The reference says the parameter is ignored and the manifest is applied", "Use a separate Forge API key and https://api.inference.wandb.ai/v1 for Serverless Inference. A CoreWeave API access token doesn't work there" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.5 } ], "editorialScores": { "ergonomics": 58, "maintenance": 80, "payments": 20, "reliability": 50, "schema": 79, "security": 74, "transparency": 71 }, "provenanceScore": 83 }, "connect": { "http": "curl \"https://api.coreweave.com/v1beta1/cks/clusters\" -H \"Authorization: Bearer $COREWEAVE_API_TOKEN\"", "claudeCode": "claude mcp add --transport http mission-control https://mc.coreweave.com/mcp --header \"Authorization: Bearer [YOUR-COREWEAVE-API-TOKEN]\"", "config": { "mcpServers": { "mission-control": { "headers": { "Authorization": "Bearer [YOUR-COREWEAVE-API-TOKEN]" }, "url": "https://mc.coreweave.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/coreweave" }, "area": "models", "unitPrices": [ { "item": "HGX H100 80 GB", "unit": "gpu-hour", "usd": 6.16, "note": "Published single-GPU rate. Sold as an 8-GPU node at $49.24 an hour on demand, $19.71 spot" }, { "item": "HGX H200 141 GB", "unit": "gpu-hour", "usd": 6.31, "note": "8-GPU node at $50.44 an hour on demand, $20.93 spot" }, { "item": "HGX B200 180 GB", "unit": "gpu-hour", "usd": 8.6, "note": "8-GPU node at $68.80 an hour on demand, $34.11 spot" }, { "item": "GB200 NVL72 186 GB", "unit": "gpu-hour", "usd": 10.5, "note": "4-GPU instance at $42.00 an hour on demand" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 2.7, "note": "8-GPU node at $21.60 an hour on demand, $9.65 spot" }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 2.25, "note": "8-GPU node at $18.00 an hour on demand, $7.88 spot" }, { "item": "AI Object Storage, hot tier", "unit": "gb-month", "usd": 0.06, "note": "Warm $0.03, cold $0.015. No egress fee" } ], "provenance": { "legalEntity": "CoreWeave, Inc.", "domain": "coreweave.com", "domainRegistered": "2019-04-01", "endpointOnVendorDomain": true, "terms": "https://docs.coreweave.com/policies/terms-of-service", "privacy": "https://docs.coreweave.com/policies/terms-of-service/privacy-policy", "statusPage": "https://status.coreweave.com", "changelog": "https://docs.coreweave.com/release-notes/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Terms of Service on docs.coreweave.com govern the CoreWeave Cloud Platform and were last modified on 30 June 2022. They are under New York law. The separate Terms of Use page covers the websites only.", "The privacy policy names CoreWeave, Inc. and its affiliates and was last updated on 24 February 2026.", "www.coreweave.com/.well-known/security.txt and coreweave.com/.well-known/security.txt return 404. A vulnerability disclosure policy is published in the docs.", "The APIs run on api.coreweave.com and mc.coreweave.com. Serverless Inference runs on api.inference.wandb.ai.", "coreweave.com was registered on 2019-04-01 per Verisign RDAP." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/coreweave.json", "live": { "slug": "coreweave", "probe": { "target": "https://api.coreweave.com", "method": "get", "lastAt": "2026-10-08T19:08:44.196236462Z", "lastOk": true, "lastStatus": 404, "lastMs": 146, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 139, "p95ms24h": 256, "samples24h": 19, "samples30d": 19, "days": [ { "date": "2026-10-08", "probes": 19, "ok": 19 } ] }, "vendorStatus": { "page": "https://status.coreweave.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-08T17:50:32.247487356Z" }, "pages": [ { "url": "https://docs.coreweave.com/release-notes/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:18:37.275927892Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "526831cd5f7a" }, { "url": "https://www.coreweave.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:27:14.115245132Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "b92d2fed4434" }, { "url": "https://docs.coreweave.com/policies/terms-of-service/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:18:35.381020121Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "92c4d55f1382" }, { "url": "https://docs.coreweave.com/policies/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:18:32.98309125Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6f16ddc8984a" } ], "updatedAt": "2026-10-08T19:08:44.196236462Z" } }, "facts": [ { "a": "Model platform", "b": "HTTP API", "name": "Kind" }, { "a": "Cerebrium Inc.", "b": "CoreWeave, Inc.", "name": "Vendor" }, { "a": "https://rest.cerebrium.ai", "b": "https://api.coreweave.com", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "Token", "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 CoreWeave's Terms of Service. The Terraform provider on GitHub is MIT", "name": "Licence" }, { "a": "none", "b": "38", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-16", "b": "2026-10-02", "name": "Last release" }, { "a": "no date given", "b": "2022-06-30", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-02-24", "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": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "yes", "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" }, { "a": "920 PyPI/wk", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "CoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Cerebrium or CoreWeave?" }, { "answer": "Yes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and CoreWeave at https://api.coreweave.com.", "question": "Can an agent call Cerebrium and CoreWeave without installing anything?" } ], "goodFor": [ { "aheadOn": [ "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, 79 against 70", "Agent ergonomics, 58 against 49", "Security \u0026 auth, 74 against 60", "Maintenance \u0026 community, 80 against 75", "Transparency \u0026 trust, 77 against 63" ], "also": null, "goodFor": "Teams that already run Kubernetes and need whole multi-GPU nodes or clusters for training and dedicated inference, with a contract and IAM.", "slug": "coreweave", "watchFor": "No self-serve route. CoreWeave's sales team approves an organisation and emails the activation link before a token can be created" } ], "job": { "capability": "compute.gpu", "name": "Compute gpu" }, "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-coreweave.json", "title": "Baseten vs CoreWeave", "url": "https://www.anchorterminal.com/compare/baseten-vs-coreweave" }, { "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-coreweave.json", "title": "Beam vs CoreWeave", "url": "https://www.anchorterminal.com/compare/beam-vs-coreweave" }, { "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-modal.json", "title": "Cerebrium vs Modal", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-modal" }, { "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-vast-ai.json", "title": "Cerebrium vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-koyeb.json", "title": "CoreWeave vs Koyeb", "url": "https://www.anchorterminal.com/compare/coreweave-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-lambda.json", "title": "CoreWeave vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/coreweave-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-modal.json", "title": "CoreWeave vs Modal", "url": "https://www.anchorterminal.com/compare/coreweave-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-northflank.json", "title": "CoreWeave vs Northflank", "url": "https://www.anchorterminal.com/compare/coreweave-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.json", "title": "CoreWeave vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-runpod.json", "title": "CoreWeave vs Runpod", "url": "https://www.anchorterminal.com/compare/coreweave-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.json", "title": "CoreWeave vs Vast.ai", "url": "https://www.anchorterminal.com/compare/coreweave-vs-vast-ai" } ], "scores": [ { "by": 2, "cerebrium": 48, "coreweave": 50, "edge": "coreweave", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "cerebrium": 70, "coreweave": 79, "edge": "coreweave", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 9, "cerebrium": 49, "coreweave": 58, "edge": "coreweave", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 14, "cerebrium": 60, "coreweave": 74, "edge": "coreweave", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "cerebrium": 30, "coreweave": 20, "edge": "cerebrium", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "cerebrium": 75, "coreweave": 80, "edge": "coreweave", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 14, "cerebrium": 63, "coreweave": 77, "edge": "coreweave", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "CoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing. Both do compute gpu.", "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.", "coreweave": "Per-hour prices for 8-GPU H100, H200 and B200 nodes are public, the docs ship as Markdown with llms.txt and embedded OpenAPI specs, and IAM has read-only roles per service. An organisation must be approved by CoreWeave's sales team before any token exists, and no request rate limits were found in the reviewed documentation." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave", "json": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.md", "slim": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.min.md" }, "markdown": "CoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing. Both do compute gpu.\n\n- Cerebrium: grade C, 55.3/100, rank #454 of 629. Markdown https://www.anchorterminal.com/tools/cerebrium.md · JSON https://www.anchorterminal.com/api/v1/tools/cerebrium.json\n- CoreWeave: grade C, 61.5/100, rank #323 of 629. Markdown https://www.anchorterminal.com/tools/coreweave.md · JSON https://www.anchorterminal.com/api/v1/tools/coreweave.json\n\n## Which one, for what\n\n### Cerebrium (C)\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- 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### CoreWeave (C)\n\nGood for: Teams that already run Kubernetes and need whole multi-GPU nodes or clusters for training and dedicated inference, with a contract and IAM.\n\nAhead on:\n- Schema \u0026 documentation, 79 against 70\n- Agent ergonomics, 58 against 49\n- Security \u0026 auth, 74 against 60\n- Maintenance \u0026 community, 80 against 75\n- Transparency \u0026 trust, 77 against 63\n\nWatch for: No self-serve route. CoreWeave's sales team approves an organisation and emails the activation link before a token can be created\n\n\n## Score by category\n\n| Category | Weight | Cerebrium | CoreWeave | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 50 | CoreWeave +2 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 79 | CoreWeave +9 |\n| Agent ergonomics | 13% (16.2 this run) | 49 | 58 | CoreWeave +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 74 | CoreWeave +14 |\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) | 75 | 80 | CoreWeave +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 63 | 77 | CoreWeave +14 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **55.3 · C** | **61.5 · C** | |\n\n## Facts side by side\n\n| Fact | Cerebrium | CoreWeave |\n| --- | --- | --- |\n| Kind | Model platform | HTTP API |\n| Vendor | Cerebrium Inc. | CoreWeave, Inc. |\n| Hosted endpoint | `https://rest.cerebrium.ai` | `https://api.coreweave.com` |\n| Transports | HTTP | HTTP |\n| Auth | API key | Token |\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 CoreWeave's Terms of Service. The Terraform provider on GitHub is MIT |\n| Tools exposed | none | 38 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-16 | 2026-10-02 |\n| Terms last updated | no date given | 2022-06-30 |\n| Privacy policy last updated | no date given | 2026-02-24 |\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 | not found in the text |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 920 PyPI/wk | none |\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**CoreWeave.** Per-hour prices for 8-GPU H100, H200 and B200 nodes are public, the docs ship as Markdown with llms.txt and embedded OpenAPI specs, and IAM has read-only roles per service. An organisation must be approved by CoreWeave's sales team before any token exists, and no request rate limits were found in the reviewed documentation.\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### CoreWeave\n\n1. Create an API access token at console.coreweave.com/tokens with an expiry and send it as `Authorization: Bearer` to https://api.coreweave.com\n2. Add GPUs by applying a NodePool resource (`compute.coreweave.com/v1alpha1`) to a CKS cluster with `instanceType` and `targetNodes`. `instanceType` can't be changed afterwards\n3. Set `targetNodes` to 0 or delete the Node Pool when a job ends. Nodes are whole 8-GPU machines billed by the hour\n4. Never pass `dry_run` to the MCP tool `coreweave_kubectl_apply` expecting a preview. The reference says the parameter is ignored and the manifest is applied\n5. Use a separate Forge API key and https://api.inference.wandb.ai/v1 for Serverless Inference. A CoreWeave API access token doesn't work there\n\n## Questions\n\n### Which is better for AI agents, Cerebrium or CoreWeave?\n\nCoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing.\n\n### Can an agent call Cerebrium and CoreWeave without installing anything?\n\nYes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and CoreWeave at https://api.coreweave.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cerebrium\", \"b\": \"coreweave\"}`. From a terminal: `anchor compare cerebrium coreweave`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cerebrium.json and https://www.anchorterminal.com/api/v1/tools/coreweave.json\n\n## Other comparisons with Cerebrium or CoreWeave\n\n- [Baseten vs Cerebrium](https://www.anchorterminal.com/compare/baseten-vs-cerebrium.md)\n- [Baseten vs CoreWeave](https://www.anchorterminal.com/compare/baseten-vs-coreweave.md)\n- [Beam vs Cerebrium](https://www.anchorterminal.com/compare/beam-vs-cerebrium.md)\n- [Beam vs CoreWeave](https://www.anchorterminal.com/compare/beam-vs-coreweave.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 Modal](https://www.anchorterminal.com/compare/cerebrium-vs-modal.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 Vast.ai](https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.md)\n- [CoreWeave vs Koyeb](https://www.anchorterminal.com/compare/coreweave-vs-koyeb.md)\n- [CoreWeave vs Lambda Cloud](https://www.anchorterminal.com/compare/coreweave-vs-lambda.md)\n- [CoreWeave vs Modal](https://www.anchorterminal.com/compare/coreweave-vs-modal.md)\n- [CoreWeave vs Northflank](https://www.anchorterminal.com/compare/coreweave-vs-northflank.md)\n- [CoreWeave vs Replicate Deployments](https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.md)\n- [CoreWeave vs Runpod](https://www.anchorterminal.com/compare/coreweave-vs-runpod.md)\n- [CoreWeave vs Vast.ai](https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cerebrium vs CoreWeave", "url": "" } ], "description": "CoreWeave scores 61.5 (C) on agent readiness against Cerebrium's 55.3 (C), and leads in 6 of 7 scored categories. Cerebrium leads on payments \u0026 pricing. Both do compute gpu. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Cerebrium C 55.3", "CoreWeave C 61.5", "scores" ], "h1": "Cerebrium vs CoreWeave", "image": "https://www.anchorterminal.com/assets/og/compare-cerebrium-vs-coreweave.png", "path": "/compare/cerebrium-vs-coreweave", "published": "2026-10-01", "section": "tools", "title": "Cerebrium vs CoreWeave for AI agents, C 55.3 vs C 61.5", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-coreweave" }, "tokens": { "markdown": 2250, "slim": 630 }, "version": 1 }