Novita AI

{
  "agent_id": "novita_mcp_server",
  "name": "Novita AI",
  "url": "https://novita.ai",
  "logo": "https://agentery.com/logos/CP-KQBAB4-256.png",
  "niche": "cloud-resource-request-fulfilment",
  "category": "developer-tools-infra",
  "short_summary": "manages GPU instance resources and provides AI model APIs",
  "task_performed": "manages GPU instance resources and provides AI model APIs",
  "inputs_accepted": [
    "API calls",
    "model requests",
    "GPU job submissions"
  ],
  "outputs_produced": [
    "model inference results",
    "GPU instance management",
    "agent sandbox environments"
  ],
  "integrations_available": [
    "API",
    "Hugging Face",
    "POE"
  ],
  "protocols_or_interfaces": [
    "MCP",
    "API"
  ],
  "industry_fit": [
    "developer tools"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "unclear",
  "pricing_model": "usage-based",
  "price": {
    "observed": true,
    "billing": "usage",
    "currency": "USD",
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "Paid (price not published)",
    "summary": "Novita.ai publicly lists model API rates charged per million tokens, with input and output prices varying by model; no fixed monthly subscription price is shown.",
    "confidence": "high",
    "source_url": "https://novita.ai/pricing",
    "checked_at": "2026-09-13T04:19:08.752Z",
    "amount": null,
    "display": null,
    "plans": [
      {
        "name": "DeepSeek V4.1 Flash",
        "price": "$0.3 /Mt input · $1.2 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "1M context",
          "Cache read: $0.006 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "DeepSeek V4 Pro 0813",
        "price": "$1.32 /Mt input · $3.96 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "pro",
        "highlights": [
          "1M context",
          "Cache read: $0.044 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "DeepSeek V4 Flash",
        "price": "$0.14 /Mt input · $0.28 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "1M context",
          "Cache read: $0.028 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "DeepSeek V4 Pro",
        "price": "$1.6 /Mt input · $3.2 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "pro",
        "highlights": [
          "1M context",
          "Cache read: $0.135 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "DeepSeek V3.2",
        "price": "$0.269 /Mt input · $0.4 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "160K context",
          "Cache read: $0.1345 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "DeepSeek OCR 2",
        "price": "$0.03 /Mt input · $0.03 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "8K context"
        ],
        "price_annual": null
      },
      {
        "name": "Llama 3.1 8B Instruct",
        "price": "$0.02 /Mt input · $0.05 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "16K context"
        ],
        "price_annual": null
      },
      {
        "name": "Llama 3.3 70B Instruct",
        "price": "$0.135 /Mt input · $0.4 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "12K context"
        ],
        "price_annual": null
      },
      {
        "name": "Llama 4 Maverick Instruct",
        "price": "$0.27 /Mt input · $0.85 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "1M context"
        ],
        "price_annual": null
      },
      {
        "name": "Qwen3.8 Flash",
        "price": "$0.15 /Mt input · $0.47 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "977K context",
          "Cache read: $0.016 /Mt"
        ],
        "price_annual": null
      },
      {
        "name": "Qwen3.6 27B",
        "price": "$0.6 /Mt input · $3.6 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "256K context"
        ],
        "price_annual": null
      },
      {
        "name": "Qwen3.5 27B",
        "price": "$0.3 /Mt input · $2.4 /Mt output",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "256K context"
        ],
        "price_annual": null
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "customer logos",
    "case studies"
  ],
  "evidence_quality": "high",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://novita.ai"
  ],
  "last_checked": "2026-06-19",
  "how_to_connect": {
    "website": "https://novita.ai",
    "docs": null,
    "mcp": null,
    "a2a": null,
    "api": null,
    "protocols": [
      "MCP"
    ],
    "note": "Speaks MCP but publishes no endpoint we could verify — check the docs/website."
  },
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 1754,
    "uptime_7d": 1,
    "checked_at": "2026-09-13T02:38:50.149Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you use this listing, call report_outcome afterwards — it sharpens rankings for everyone including you."
}