OpenAI Deep Research API

{
  "agent_id": "openai_deep_research",
  "name": "OpenAI Deep Research API",
  "url": "https://developers.openai.com/cookbook/examples/deep_research_api/introduction_to_deep_research_api_agents",
  "logo": "https://agentery.com/logos/CP-HS5SNE-ld256.png",
  "niche": "deep-research-agent",
  "category": "research-knowledge-work",
  "short_summary": "performs deep multi-step empirical research, synthesis, planning, and tool use via agentic research workflows",
  "task_performed": "performs deep multi-step empirical research, synthesis, planning, and tool use via agentic research workflows",
  "inputs_accepted": [
    "user research queries/prompts",
    "web search results",
    "internal files via MCP"
  ],
  "outputs_produced": [
    "research reports with citations",
    "streamed research progress",
    "structured outputs (tables",
    "headers)"
  ],
  "integrations_available": [
    "OpenAI Agents SDK",
    "OpenAI API",
    "WebSearchTool",
    "MCP",
    "GitHub"
  ],
  "protocols_or_interfaces": [
    "SDK",
    "API",
    "MCP"
  ],
  "industry_fit": [
    "general business",
    "developer tools",
    "research"
  ],
  "autonomy_level": "agentic",
  "human_approval_needed": "unclear",
  "pricing_model": "unclear",
  "price": {
    "observed": true,
    "billing": "usage",
    "currency": "USD",
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "Paid (price not published)",
    "summary": "OpenAI publishes usage-based API pricing per 1 million input and output tokens, varying by model and processing tier.",
    "confidence": "high",
    "source_url": "https://developers.openai.com/api/docs/pricing",
    "checked_at": "2026-07-28T05:59:37.028Z",
    "amount": null,
    "display": null,
    "plans": [
      {
        "name": "gpt-5.6-sol",
        "price": "$5.00 per 1M input tokens; $30.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.50 per 1M tokens",
          "Cache writes: $6.25 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.6-terra",
        "price": "$2.50 per 1M input tokens; $15.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.25 per 1M tokens",
          "Cache writes: $3.125 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.6-luna",
        "price": "$1.00 per 1M input tokens; $6.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.10 per 1M tokens",
          "Cache writes: $1.25 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.5",
        "price": "$5.00 per 1M input tokens; $30.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.50 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.5-pro",
        "price": "$30.00 per 1M input tokens; $180.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "pro",
        "highlights": [
          "Standard pricing"
        ]
      },
      {
        "name": "gpt-5.4",
        "price": "$2.50 per 1M input tokens; $15.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.25 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.4-mini",
        "price": "$0.75 per 1M input tokens; $4.50 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.075 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.4-nano",
        "price": "$0.20 per 1M input tokens; $1.25 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Standard pricing",
          "Cached input: $0.02 per 1M tokens"
        ]
      },
      {
        "name": "gpt-5.4-pro",
        "price": "$30.00 per 1M input tokens; $180.00 per 1M output tokens",
        "usage": true,
        "period": "usage",
        "persona": "pro",
        "highlights": [
          "Standard pricing"
        ]
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "Zero Data Retention support for Enterprises"
  ],
  "evidence_quality": "high",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "Zero Data Retention stated for Enterprises",
  "evidence_urls": [
    "https://developers.openai.com/cookbook/examples/deep_research_api/introduction_to_deep_research_api_agents"
  ],
  "last_checked": "2026-06-16",
  "how_to_connect": {
    "website": "https://developers.openai.com/cookbook/examples/deep_research_api/introduction_to_deep_research_api_agents",
    "docs": "https://developers.openai.com/docs",
    "mcp": null,
    "a2a": null,
    "api": {
      "docs_url": "https://developers.openai.com/api",
      "endpoint": null
    },
    "protocols": []
  },
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 452,
    "uptime_7d": 1,
    "checked_at": "2026-07-28T02:36:44.925Z",
    "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."
}