Cerebrium

{
  "agent_id": "cerebrium",
  "name": "Cerebrium",
  "url": "https://cerebrium.ai/docs/",
  "logo": "https://www.google.com/s2/favicons?domain=cerebrium.ai&sz=128",
  "niche": null,
  "category": null,
  "short_summary": "Serverless CPU and GPU platform for deploying and scaling real-time AI applications, including LLM endpoints, voice agents, streaming workloads, and production…",
  "task_performed": "unclear",
  "inputs_accepted": [],
  "outputs_produced": [],
  "integrations_available": [],
  "protocols_or_interfaces": [
    "A2A"
  ],
  "industry_fit": [],
  "autonomy_level": "unclear",
  "human_approval_needed": "unclear",
  "pricing_model": "unclear",
  "price": {
    "observed": true,
    "billing": "usage",
    "source_kind": "vendor",
    "currency": "USD",
    "lowest_monthly_usd": 100,
    "monthly_usd": 100,
    "headline": "From $100/mo",
    "commercial": {
      "entry_offer": {
        "line": "Standard",
        "monthly_native": 100,
        "monthly_usd": 100,
        "commitment": "monthly",
        "basis": "$100/month",
        "billing_verified": true
      },
      "rates": [
        {
          "line": "B200 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "H200 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "H100 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "RTX PRO 6000 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "A100 (80GB) compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "A100 (40GB) compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "L40s compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "A10 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "L4 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "T4 compute",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "CPU Only",
          "per": "per vcpu",
          "text": "$0 per vcpu"
        },
        {
          "line": "Memory",
          "per": "per GB",
          "text": "$0 per GB"
        }
      ],
      "currency": "USD",
      "notes": [
        "add-on / component (not a whole-product price): Storage $0.05 /GB/mo"
      ],
      "lines": [
        {
          "name": "Hobby",
          "price": "Free + compute / month",
          "kind": "unknown"
        },
        {
          "name": "Standard",
          "price": "$100 + compute / month",
          "kind": "base_subscription",
          "billed": "monthly"
        },
        {
          "name": "Enterprise",
          "price": "Custom",
          "kind": "custom"
        },
        {
          "name": "B200 compute",
          "price": "$0.00167 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "H200 compute",
          "price": "$0.001166 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "H100 compute",
          "price": "$0.000944 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "RTX PRO 6000 compute",
          "price": "$0.000694 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "A100 (80GB) compute",
          "price": "$0.000583 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "A100 (40GB) compute",
          "price": "$0.000555 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "L40s compute",
          "price": "$0.000542 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "A10 compute",
          "price": "$0.000306 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "L4 compute",
          "price": "$0.000222 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "T4 compute",
          "price": "$0.000164 /s",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "CPU Only",
          "price": "$0.00000655 /vCPU/s",
          "kind": "usage_rate",
          "unit": "vcpu",
          "billed": "usage"
        },
        {
          "name": "Memory",
          "price": "$0.00000222 /GB/s",
          "kind": "usage_rate",
          "unit": "GB",
          "billed": "usage"
        },
        {
          "name": "Storage",
          "price": "$0.05 /GB/mo",
          "kind": "add_on",
          "unit": "GB",
          "billed": "monthly"
        }
      ]
    },
    "summary": "From $100/mo. Cerebrium offers a free-base Hobby tier, a $100/month Standard base tier, custom Enterprise pricing, and usage-based compute, memory, and storage charges.",
    "confidence": "high",
    "source_url": "https://cerebrium.ai/pricing",
    "checked_at": "2026-10-26T01:53:30.489Z",
    "amount": 100,
    "display": "From $100/mo",
    "plans": [
      {
        "name": "Hobby",
        "price": "Free + compute / month",
        "period": "month",
        "persona": "individual",
        "highlights": [
          "3 user seats",
          "Up to 3 deployed apps",
          "500 containers + 5 concurrent GPUs",
          "1 day log retention"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Standard",
        "price": "$100 + compute / month",
        "period": "month",
        "persona": "pro",
        "highlights": [
          "Unlimited seats",
          "Unlimited apps",
          "1000 containers + 30 GPU concurrency",
          "Custom domains"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Enterprise",
        "price": "Custom",
        "period": null,
        "persona": "enterprise",
        "highlights": [
          "Volume discounts",
          "Unlimited concurrent GPUs",
          "Dedicated Slack support",
          "White glove onboarding"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "B200 compute",
        "price": "$0.00167 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "H200 compute",
        "price": "$0.001166 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "H100 compute",
        "price": "$0.000944 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "RTX PRO 6000 compute",
        "price": "$0.000694 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "A100 (80GB) compute",
        "price": "$0.000583 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "A100 (40GB) compute",
        "price": "$0.000555 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "L40s compute",
        "price": "$0.000542 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "A10 compute",
        "price": "$0.000306 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "L4 compute",
        "price": "$0.000222 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "T4 compute",
        "price": "$0.000164 /s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "GPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "CPU Only",
        "price": "$0.00000655 /vCPU/s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "CPU compute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Memory",
        "price": "$0.00000222 /GB/s",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "Memory usage"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Storage",
        "price": "$0.05 /GB/mo",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Storage usage"
        ],
        "promo_note": "First 100GB storage free",
        "price_promo": null,
        "price_annual": null
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [],
  "evidence_quality": "unclear",
  "entity_type": "agent_platform",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://cerebrium.ai/docs/"
  ],
  "last_checked": "2026-10-26",
  "profile_checked": null,
  "price_checked": "2026-10-26",
  "how_to_connect": {
    "website": "https://cerebrium.ai/docs/",
    "docs": null,
    "mcp": null,
    "a2a": null,
    "api": null,
    "protocols": [
      "A2A"
    ],
    "install": null,
    "repository": null,
    "note": "Speaks A2A but publishes no endpoint we could verify — check the docs/website."
  },
  "deployment": {
    "model": "unknown",
    "both_offered": false,
    "hosted_endpoint": null,
    "install": null,
    "note": "No deployment evidence held — Agentery has no endpoint, install instruction or directory attribute for this listing.",
    "evidence": null
  },
  "licence": {
    "name": null,
    "note": "No named licence found in the retained page text or source attributes. A public repository alone does not establish an open-source licence.",
    "evidence": null
  },
  "evidence_checks": {
    "price": {
      "source_url": "https://cerebrium.ai/pricing",
      "last_observed_day": "2026-10-26",
      "age_days": 1,
      "verified_day": null,
      "note": "from the listing's current price record; no separate page-text verification is held"
    },
    "agent_card": {
      "status": "unknown",
      "note": "no Agent Card URL recorded for this listing"
    },
    "endpoint": {
      "status": "unknown",
      "note": "endpoint not yet checked"
    }
  },
  "product_group": null,
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 1387,
    "uptime_7d": 1,
    "checked_at": "2026-10-26T02:32:52.055Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "a2a_check": {
    "checked_on": "2026-10-16",
    "card_url": "https://cerebrium.ai/.well-known/agent-card.json",
    "card_name": "Cerebrium",
    "declared_version": "0.3",
    "endpoint": null,
    "skills": [
      "cerebrium"
    ],
    "findings": [
      {
        "label": "Interface",
        "value": "No A2A JSON-RPC interface declared (transport: HTTP+JSON)",
        "ok": false
      }
    ],
    "vendor_published": null,
    "note": "Automated check of the vendor's public A2A agent card and endpoint. The check reads the card and sends an empty JSON-RPC request; it delivers no message. Vendor quotes are copied word for word from the card or its documentation."
  },
  "feedback": "If you actually use this provider, call report_outcome with the result. Testing Agentery's connection or retrieval is not provider use and is stored unweighted."
}