{ "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": 593, "ranked": true, "rankOf": 842, "categoryRank": 12, "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": "2026-10-09T10:42:39.32547788Z", "lastOk": true, "lastStatus": 403, "lastMs": 254, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 252, "p95ms24h": 274, "samples24h": 184, "samples30d": 184, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "date": "2026-10-09", "probes": 114, "ok": 114 } ] }, "vendorStatus": { "page": "https://status.cerebrium.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:57:41.246107011Z" }, "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": "2026-10-09T10:42:39.32547788Z" } }, "answer": "Hugging Face Inference Endpoints scores 64.5 (B) 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": "hugging-face-inference-endpoints", "name": "Hugging Face Inference Endpoints", "vendor": "Hugging Face, Inc.", "vendorUrl": "https://huggingface.co", "kind": "http-api", "category": "gpu-compute", "summary": "Managed Hugging Face service that deploys a Hub model as a dedicated, autoscaling HTTPS endpoint on AWS, Azure or Google Cloud, using vLLM, TGI, SGLang, llama.cpp, TEI or a custom container. Managed by REST API, Python client, CLI or MCP.", "url": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints", "markdownUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-endpoints.json", "repo": "https://github.com/huggingface/hf-endpoints-documentation", "license": "Proprietary service under the Hugging Face Terms of Service. The `huggingface_hub` Python client and CLI are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.endpoints.huggingface.cloud", "packages": [ { "registry": "pypi", "name": "huggingface_hub" } ], "auth": "mixed", "authNotes": "Hugging Face access token sent as `Authorization: Bearer $HF_TOKEN` to the management API and to each endpoint. Tokens are created in the account settings in a browser and can be fine-grained, read or write. The MCP server uses OAuth through huggingface.co (authorisation code with PKCE, device code, dynamic client registration) with `read-endpoints` and `write-endpoints` scopes. `GET /v2/provider` and the catalogue list need no token. Access is self-serve, with quota requests for larger instances.", "pricing": "usage", "pricingNotes": "Usage priced by instance hour, billed per minute while a replica is initialising or running. GPUs run from $0.50 an hour (T4) to $10 (H100 on GCP), CPUs from $0.033. No free tier or trial was found. The docs require a payment method and credits before deploying, and the pricing page says an active subscription. Paused endpoints and endpoints at zero replicas aren't billed for compute (https://huggingface.co/docs/inference-endpoints/support/pricing).", "priceSummary": "$0.033 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Inference Endpoints docs, the two OpenAPI documents or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 19, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": 60014944, "asOf": "2026-10-08" }, "docsUrl": "https://huggingface.co/docs/inference-endpoints/index", "llmsTxt": "https://huggingface.co/docs/inference-endpoints/llms.txt", "openapi": "https://api.endpoints.huggingface.cloud/openapi.json", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.containers" ], "tags": [ "hosted", "usage-priced", "python", "cli", "mcp", "oauth", "openapi", "llms-txt", "status-page", "soc2", "enterprise" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 64.5, "grade": "B", "agentReady": false, "rank": 314, "ranked": true, "rankOf": 842, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 80, "payments": 20, "reliability": 63, "schema": 73, "security": 83, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "OAuth scopes separate reading endpoints from writing them, both OpenAPI documents are public, and the unauthenticated `/v2/provider` route lists every instance with its hourly price. An account needs a payment method and credits before the first deployment, no rate limits or SLA were found for the management API, and the docs price table disagrees with the live list in places.", "bestFor": "Teams whose models already live on the Hugging Face Hub and who want a dedicated endpoint on a named cloud and region with standard open-source engines.", "strengths": [ "Public OpenAPI 3.1 documents for the management API (46 operations) and the catalogue API (3), plus llms.txt and a Markdown twin of every docs page", "The MCP server at endpoints.huggingface.co/mcp uses OAuth with `read-endpoints` and `write-endpoints` scopes, PKCE and dynamic client registration", "`GET /v2/provider` needs no token and returns each instance type by cloud and region with status and price per hour", "The MCP `delete_endpoint` tool returns a preview and deletes only on a second call with `confirm: true`", "The Inference Endpoints API component on status.huggingface.co shows 100 per cent uptime over the 90 days to 8 October 2026" ], "weaknesses": [ "No free tier. The docs require a payment method and credits, and replicas are billed while initialising as well as running", "No rate limits, SLA or idempotency keys were found for the management API, and its OpenAPI document lists only 200 responses on 43 of 46 operations", "The docs price table and the live provider list disagree. Inferentia2 x1 is $0.75 in the docs and $1.95 in the API, and AWS H200 is listed in the docs and marked deprecated in the API", "A start from zero replicas takes minutes by the docs' own account, and the proxy answers 503 until a replica is ready", "The Hub outage of 16 July 2026 took the Inference Endpoints UI down for 1 hour 37 minutes" ], "agentNotes": [ "Call `GET https://api.endpoints.huggingface.cloud/v2/provider` first and pick an instance whose `status` is `available`. The docs table lists types the API marks deprecated or not available", "Send `X-Scale-Up-Timeout: 600` on requests to an endpoint that scales to zero, or handle 503 while the first replica starts", "Set `scaleToZeroTimeout` yourself. The docs give a default of 1 hour and the OpenAPI document says 15 minutes", "Pause or delete an endpoint when the job is done. Billing covers every minute a replica is initialising or running", "Give the agent a fine-grained token or the `read-endpoints` scope unless it must deploy. Endpoints are private by default and take the same Hugging Face token as a bearer" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.5 } ], "editorialScores": { "ergonomics": 62, "maintenance": 80, "payments": 20, "reliability": 63, "schema": 73, "security": 83, "transparency": 68 }, "provenanceScore": 67 }, "connect": { "install": "pip install huggingface_hub", "http": "curl \"https://api.endpoints.huggingface.cloud/v2/endpoint/$NAMESPACE\" \\\n -H \"Authorization: Bearer $HF_TOKEN\"" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/hugging-face-inference-endpoints" }, "area": "models", "unitPrices": [ { "item": "NVIDIA T4 16 GB x1 (AWS, GCP)", "unit": "gpu-hour", "usd": 0.5, "note": "Billed per minute while initialising or running" }, { "item": "NVIDIA L4 24 GB x1 (AWS)", "unit": "gpu-hour", "usd": 0.8, "note": "$0.70 on GCP us-east4" }, { "item": "NVIDIA A10G 24 GB x1 (AWS)", "unit": "gpu-hour", "usd": 1, "note": "us-east-1 and eu-west-1" }, { "item": "NVIDIA L40S 48 GB x1 (AWS)", "unit": "gpu-hour", "usd": 1.8, "note": "us-east-1" }, { "item": "NVIDIA A100 80 GB x1 (AWS)", "unit": "gpu-hour", "usd": 2.5, "note": "$3.60 on GCP us-east4" }, { "item": "NVIDIA RTX PRO 6000 Blackwell 96 GB x1 (AWS)", "unit": "gpu-hour", "usd": 2.75, "note": "us-east-2, in the live provider list and absent from the docs table" }, { "item": "NVIDIA H200 141 GB x1 (GCP)", "unit": "gpu-hour", "usd": 5, "note": "us-south1. The AWS H200 in us-west-2 is marked deprecated in the API" }, { "item": "NVIDIA H100 80 GB x1 (GCP)", "unit": "gpu-hour", "usd": 10, "note": "us-east4. The AWS H100 at $4.50 is deprecated from December 2025" }, { "item": "Intel Sapphire Rapids x1, 1 vCPU and 2 GB (AWS)", "unit": "vcpu-hour", "usd": 0.033, "note": "$0.050 on GCP and $0.060 on Azure Intel Xeon" } ], "provenance": { "legalEntity": "Hugging Face, Inc.", "domain": "huggingface.co", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://huggingface.co/terms-of-service", "privacy": "https://huggingface.co/privacy", "statusPage": "https://status.huggingface.co", "changelog": "https://huggingface.co/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The Terms of Service (effective 15 September 2022) name Hugging Face, Inc., a Delaware corporation, list Inference Endpoints among the services they cover and are governed by New York law. They link Supplemental Terms (effective 28 April 2025) as a PDF, of which our reader extracted only the first page.", "The privacy policy (effective 28 March 2023) names Hugging Face, Inc. and its EU establishment Hugging Face, SAS, 9 rue des Colonnes, 75002 Paris, and lists 11 subprocessors with countries. The Inference Endpoints security page points to it.", "The management API answers at api.endpoints.huggingface.cloud and deployed endpoints at subdomains of endpoints.huggingface.cloud, a second domain of the vendor's. The catalogue API and the MCP server are on endpoints.huggingface.co.", "huggingface.co/.well-known/security.txt gives security@huggingface.co and expires on 1 July 2030. endpoints.huggingface.co/.well-known/security.txt returns 404.", "status.huggingface.co is a Better Stack page with separate components for the Inference Endpoints UI and API.", "The changelog at huggingface.co/changelog covers the whole Hub. Inference Endpoints has no changelog of its own. Dated changes are in the docs repository's commit history.", "rdap.org returned 404 for huggingface.co, so the registration date is unrecorded." ], "score": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.json", "live": { "slug": "hugging-face-inference-endpoints", "probe": { "target": "https://api.endpoints.huggingface.cloud", "method": "get", "lastAt": "2026-10-09T10:42:45.525175216Z", "lastOk": true, "lastStatus": 200, "lastMs": 266, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 255, "p95ms24h": 295, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "vendorStatus": { "page": "https://status.huggingface.co", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:58:03.654181492Z" }, "updatedAt": "2026-10-09T10:42:45.525175216Z" } }, "facts": [ { "a": "Model platform", "b": "HTTP API", "name": "Kind" }, { "a": "Cerebrium Inc.", "b": "Hugging Face, Inc.", "name": "Vendor" }, { "a": "https://rest.cerebrium.ai", "b": "https://api.endpoints.huggingface.cloud", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or 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 the Hugging Face Terms of Service. The `huggingface_hub` Python client and CLI are Apache-2.0", "name": "Licence" }, { "a": "none", "b": "19", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-16", "b": "2026-10-08", "name": "Last release" }, { "a": "no date given", "b": "2022-09-15", "name": "Terms last updated" }, { "a": "no date given", "b": "2023-03-28", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "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": "60M PyPI/wk", "name": "Popularity" } ], "faq": [ { "answer": "Hugging Face Inference Endpoints scores 64.5 (B) 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 Hugging Face Inference Endpoints?" }, { "answer": "Yes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and Hugging Face Inference Endpoints at https://api.endpoints.huggingface.cloud.", "question": "Can an agent call Cerebrium and Hugging Face Inference Endpoints 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": [ "Reliability, 63 against 48", "Agent ergonomics, 62 against 49", "Security \u0026 auth, 83 against 60", "Maintenance \u0026 community, 80 against 75", "Transparency \u0026 trust, 68 against 63" ], "also": null, "goodFor": "Teams whose models already live on the Hugging Face Hub and who want a dedicated endpoint on a named cloud and region with standard open-source engines.", "slug": "hugging-face-inference-endpoints", "watchFor": "No free tier. The docs require a payment method and credits, and replicas are billed while initialising as well as running" } ], "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-hugging-face-inference-endpoints.json", "title": "Baseten vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/baseten-vs-hugging-face-inference-endpoints" }, { "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-hugging-face-inference-endpoints.json", "title": "Beam vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/beam-vs-hugging-face-inference-endpoints" }, { "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-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-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/coreweave-vs-hugging-face-inference-endpoints.json", "title": "CoreWeave vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/coreweave-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic.json", "title": "Hugging Face Inference Endpoints vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb.json", "title": "Hugging Face Inference Endpoints vs Koyeb", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda.json", "title": "Hugging Face Inference Endpoints vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-modal.json", "title": "Hugging Face Inference Endpoints vs Modal", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-nebius-ai-cloud.json", "title": "Hugging Face Inference Endpoints vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-northflank.json", "title": "Hugging Face Inference Endpoints vs Northflank", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-northflank" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.json", "title": "Hugging Face Inference Endpoints vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod.json", "title": "Hugging Face Inference Endpoints vs Runpod", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute.json", "title": "Hugging Face Inference Endpoints vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai.json", "title": "Hugging Face Inference Endpoints vs Vast.ai", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-verda.json", "title": "Hugging Face Inference Endpoints vs Verda", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-verda" } ], "scores": [ { "by": 15, "cerebrium": 48, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 63, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "cerebrium": 70, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 73, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 13, "cerebrium": 49, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 62, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 23, "cerebrium": 60, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 83, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "cerebrium": 30, "edge": "cerebrium", "hugging-face-inference-endpoints": 20, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "cerebrium": 75, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 5, "cerebrium": 63, "edge": "hugging-face-inference-endpoints", "hugging-face-inference-endpoints": 68, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Hugging Face Inference Endpoints scores 64.5 (B) 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.", "hugging-face-inference-endpoints": "OAuth scopes separate reading endpoints from writing them, both OpenAPI documents are public, and the unauthenticated `/v2/provider` route lists every instance with its hourly price. An account needs a payment method and credits before the first deployment, no rate limits or SLA were found for the management API, and the docs price table disagrees with the live list in places." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints", "json": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.md", "slim": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.min.md" }, "markdown": "Hugging Face Inference Endpoints scores 64.5 (B) 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 #593 of 842. Markdown https://www.anchorterminal.com/tools/cerebrium.md · JSON https://www.anchorterminal.com/api/v1/tools/cerebrium.json\n- Hugging Face Inference Endpoints: grade B, 64.5/100, rank #314 of 842. Markdown https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.md · JSON https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-endpoints.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### Hugging Face Inference Endpoints (B)\n\nGood for: Teams whose models already live on the Hugging Face Hub and who want a dedicated endpoint on a named cloud and region with standard open-source engines.\n\nAhead on:\n- Reliability, 63 against 48\n- Agent ergonomics, 62 against 49\n- Security \u0026 auth, 83 against 60\n- Maintenance \u0026 community, 80 against 75\n- Transparency \u0026 trust, 68 against 63\n\nWatch for: No free tier. The docs require a payment method and credits, and replicas are billed while initialising as well as running\n\n\n## Score by category\n\n| Category | Weight | Cerebrium | Hugging Face Inference Endpoints | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 63 | Hugging Face Inference Endpoints +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 73 | Hugging Face Inference Endpoints +3 |\n| Agent ergonomics | 13% (16.2 this run) | 49 | 62 | Hugging Face Inference Endpoints +13 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 83 | Hugging Face Inference Endpoints +23 |\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 | Hugging Face Inference Endpoints +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 63 | 68 | Hugging Face Inference Endpoints +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **55.3 · C** | **64.5 · B** | |\n\n## Facts side by side\n\n| Fact | Cerebrium | Hugging Face Inference Endpoints |\n| --- | --- | --- |\n| Kind | Model platform | HTTP API |\n| Vendor | Cerebrium Inc. | Hugging Face, Inc. |\n| Hosted endpoint | `https://rest.cerebrium.ai` | `https://api.endpoints.huggingface.cloud` |\n| Transports | HTTP | HTTP |\n| Auth | API key | OAuth or 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 the Hugging Face Terms of Service. The `huggingface_hub` Python client and CLI are Apache-2.0 |\n| Tools exposed | none | 19 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-16 | 2026-10-08 |\n| Terms last updated | no date given | 2022-09-15 |\n| Privacy policy last updated | no date given | 2023-03-28 |\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 | 60M PyPI/wk |\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**Hugging Face Inference Endpoints.** OAuth scopes separate reading endpoints from writing them, both OpenAPI documents are public, and the unauthenticated `/v2/provider` route lists every instance with its hourly price. An account needs a payment method and credits before the first deployment, no rate limits or SLA were found for the management API, and the docs price table disagrees with the live list in places.\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### Hugging Face Inference Endpoints\n\n1. Call `GET https://api.endpoints.huggingface.cloud/v2/provider` first and pick an instance whose `status` is `available`. The docs table lists types the API marks deprecated or not available\n2. Send `X-Scale-Up-Timeout: 600` on requests to an endpoint that scales to zero, or handle 503 while the first replica starts\n3. Set `scaleToZeroTimeout` yourself. The docs give a default of 1 hour and the OpenAPI document says 15 minutes\n4. Pause or delete an endpoint when the job is done. Billing covers every minute a replica is initialising or running\n5. Give the agent a fine-grained token or the `read-endpoints` scope unless it must deploy. Endpoints are private by default and take the same Hugging Face token as a bearer\n\n## Questions\n\n### Which is better for AI agents, Cerebrium or Hugging Face Inference Endpoints?\n\nHugging Face Inference Endpoints scores 64.5 (B) 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 Hugging Face Inference Endpoints without installing anything?\n\nYes. Cerebrium has a hosted endpoint at https://rest.cerebrium.ai and Hugging Face Inference Endpoints at https://api.endpoints.huggingface.cloud.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cerebrium\", \"b\": \"hugging-face-inference-endpoints\"}`. From a terminal: `anchor compare cerebrium hugging-face-inference-endpoints`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cerebrium.json and https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-endpoints.json\n\n## Other comparisons with Cerebrium or Hugging Face Inference Endpoints\n\n- [Baseten vs Cerebrium](https://www.anchorterminal.com/compare/baseten-vs-cerebrium.md)\n- [Baseten vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/baseten-vs-hugging-face-inference-endpoints.md)\n- [Beam vs Cerebrium](https://www.anchorterminal.com/compare/beam-vs-cerebrium.md)\n- [Beam vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/beam-vs-hugging-face-inference-endpoints.md)\n- [Cerebrium vs CoreWeave](https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.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 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- [CoreWeave vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/coreweave-vs-hugging-face-inference-endpoints.md)\n- [Hugging Face Inference Endpoints vs Hyperbolic](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-hyperbolic.md)\n- [Hugging Face Inference Endpoints vs Koyeb](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-koyeb.md)\n- [Hugging Face Inference Endpoints vs Lambda Cloud](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-lambda.md)\n- [Hugging Face Inference Endpoints vs Modal](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-modal.md)\n- [Hugging Face Inference Endpoints vs Nebius AI Cloud](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-nebius-ai-cloud.md)\n- [Hugging Face Inference Endpoints vs Northflank](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-northflank.md)\n- [Hugging Face Inference Endpoints vs Replicate Deployments](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.md)\n- [Hugging Face Inference Endpoints vs Runpod](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod.md)\n- [Hugging Face Inference Endpoints vs Thunder Compute](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-thunder-compute.md)\n- [Hugging Face Inference Endpoints vs Vast.ai](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-vast-ai.md)\n- [Hugging Face Inference Endpoints vs Verda](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-verda.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "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 Hugging Face Inference Endpoints", "url": "" } ], "description": "Hugging Face Inference Endpoints scores 64.5 (B) 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", "Hugging Face Inference Endpoints B 64.5", "scores" ], "h1": "Cerebrium vs Hugging Face Inference Endpoints", "image": "https://www.anchorterminal.com/assets/og/compare-cerebrium-vs-hugging-face-inference-endpoints.png", "path": "/compare/cerebrium-vs-hugging-face-inference-endpoints", "published": "2026-10-01", "section": "tools", "title": "Cerebrium vs Hugging Face Inference Endpoints for AI agents", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-hugging-face-inference-endpoints" }, "tokens": { "markdown": 2800, "slim": 680 }, "version": 1 }