o3-deep-research

Tool callingReasoningImage input

Launch post Website Docs

Research model for long-horizon investigation, synthesis, and analytical reports

Context: 200K
Released: 2y ago

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: OpenAI
Model family: o-series
Type: Language model
Predecessor: —
Successor: —
Released: June 26, 2024
Model ID: openai/o3-deep-research
Openness: Closed
License: —
Input modalities: text, image
Output modalities: text
Modality: text+image->text
Max output tokens: 100K
Knowledge cutoff: 2024-05
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: openai/o3-deep-research
Source family: o
Last updated: 2024-06-26
Knowledge cutoff: 2024-05
Model context: 200K
Model output limit: 100K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature control: No

Complete source record (JSON)

{
  "id": "openai/o3-deep-research",
  "name": "o3-deep-research",
  "description": "Research model for long-horizon investigation, synthesis, and analytical reports",
  "family": "o",
  "last_updated": "2024-06-26",
  "knowledge": "2024-05",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": false,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 200000,
    "output": 100000
  },
  "release_date": "2024-06-26",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider endpoint data will appear after this model's first OpenRouter endpoint sync.

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation