Gemini Deep Research
Googleai.google.dev/gemini-api/docs/models/deep-resear
An agentic model that autonomously plans and executes multi-step research across hundreds of sources to produce cited, interactive reports.
Updated 55 min ago · first seen 11 Sept 2026
model_01M293VBS2PZ4PYY5XP47J6XS4
Specification
- Max output
- 65.5K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- Modalities
- audio, image, pdf, text, video
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- Input modalities
- text, image, pdf, audio, video
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- Output modalities
- image
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- API model id
- deep-research-preview-04-2026
Source:Google AI for Developers (Gemini API docs)T1observed 59 min agohigh
- Official page
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- Latest update
- 2026-04
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
- Versions
- {"preview":["deep-research-preview-04-2026"]}
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
11
Source tiers
T111
Freshest observation
55 min ago
Conflicts
None
Modalities
- Modalities
- audioimagepdftextvideo
- Input
- textimagepdfaudiovideo
- Output
- image
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Yes
Google AI for Developers (Gemini API docs) · T1
Audio
Yes
Google AI for Developers (Gemini API docs) · T1
Fine-tuning available
Unavailable
- Max output
- 65.5K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 55 min agohigh
No benchmark results recorded
Current prices
No current prices recorded
Price history
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Description
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| An agentic model that autonomously plans and executes multi-step research across hundreds of sources to produce cited, interactive reports. | → current | current | Google AI for Developers (Gemini API docs)T1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Google AI for Developers (Gemini API docs) | ai.google.dev/gemini-api/docs/models/deep-research-preview-04-2026 | model_page | T1· Official | 48 min ago | 2 |
| Google AI for Developers (Gemini API docs) | ai.google.dev/gemini-api/docs/models | model_docs | T1· Official | 51 min ago | 3 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.