OpenAI: o3 Deep Research

Server-rendered model summary page for indexing/share previews. Use the interactive explorer for full filtering and comparison.

Match confidence: UnmatchedSource type: openrouter_only

Context window

200K

Arena overall rank

—

Input price

$0.000 / 1M

Output price

$0.000 / 1M

Identifiers & provenance

Primary ID: openai/o3-deep-research
OpenRouter ID: openai/o3-deep-research
Canonical slug: openai/o3-deep-research-2025-06-26

Source semantics

Arena rank is a human-preference leaderboard signal, not a universal truth metric.
OpenRouter usage/popularity reflects adoption/traffic, not benchmark quality.
Pricing fields may differ by provider and can include extra modes beyond prompt/completion.

Read more on Methodology & data sources.

Description

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Raw fields snapshot

{
  "id": "openai/o3-deep-research",
  "name": "OpenAI: o3 Deep Research",
  "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.",
  "created": 1760129661,
  "canonical_slug": "openai/o3-deep-research-2025-06-26",
  "hugging_face_id": "",
  "source_type": "openrouter_only",
  "context_length": 200000,
  "max_completion_tokens": 100000,
  "is_moderated": true,
  "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
      "image",
      "text",
      "file"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
  },
  "input_modalities": [
    "image",
    "text",
    "file"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text+image+file->text",
  "tokenizer": "GPT",
  "instruct_type": null,
  "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
  ],
  "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
  },
  "per_request_limits": null,
  "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
  },
  "pricing": {
    "prompt": "0.00001",
    "completion": "0.00004",
    "web_search": "0.01",
    "input_cache_read": "0.0000025"
  },
  "PPM": {
    "prompt": 10,
    "completion": 40,
    "web_search": 10000,
    "input_cache_read": 2.5
  },
  "openrouter_raw": {
    "id": "openai/o3-deep-research",
    "canonical_slug": "openai/o3-deep-research-2025-06-26",
    "hugging_face_id": "",
    "name": "OpenAI: o3 Deep Research",
    "created": 1760129661,
    "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.",
    "context_length": 200000,
    "architecture": {
      "modality": "text+image+file->text",
      "input_modalities": [
        "image",
        "text",
        "file"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "GPT",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.00001",
      "completion": "0.00004",
      "web_search": "0.01",
      "input_cache_read": "0.0000025"
    },
    "top_provider": {
      "context_length": 200000,
      "max_completion_tokens": 100000,
      "is_moderated": true
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "include_reasoning",
      "logit_bias",
      "logprobs",
      "max_tokens",
      "presence_penalty",
      "reasoning",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_logprobs",
      "top_p"
    ],
    "default_parameters": {
      "temperature": null,
      "top_p": null,
      "frequency_penalty": null
    },
    "expiration_date": null
  }
}