Identity
- Status
- preview
- Developer ID
deep-research-preview-04-2026- Released
- Not reported
- Version
- Gemini Deep Research
- License
- Unknown
Gemini Deep Research is a managed agentic model that plans and executes multi-step research and produces cited reports.
At a Glance
deep-research-preview-04-2026This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
Gemini Deep ResearchGoogle DeepMind | vs | Gemini 2.5 ProGoogle DeepMind | family variantstext |
Gemini Deep ResearchGoogle DeepMind | vs | Gemini 3.1 ProGoogle DeepMind | family variantstext |
Gemini Deep ResearchGoogle DeepMind | vs | Gemini 3.6 FlashGoogle DeepMind | family variantstext |
Gemini Deep ResearchGoogle DeepMind | vs | Gemini 3.7 FlashGoogle DeepMind | family variantstext |
Gemini Deep ResearchGoogle DeepMind | vs | Gemini 3.5 Flash-LiteGoogle DeepMind | family variantstext |
Gemini Deep ResearchGoogle DeepMind | vs | cross-developer peerstext | |
Gemini Deep ResearchGoogle DeepMind | vs | Qwen3.7-PlusQwen | cross-developer peerstext |
Gemini Deep ResearchGoogle DeepMind | vs | Pixtral LargeMistral AI | cross-developer peerstext |
Gemini Deep ResearchGoogle DeepMind | vs | Claude Sonnet 5Anthropic | cross-developer peerstext |
Gemini Deep ResearchGoogle DeepMind | vs | GPT-4o MiniOpenAI | cross-developer peerstext |
Gemini Deep ResearchGoogle DeepMind | vs | Sonar Deep ResearchPerplexity | cross-developer peerstext |
Gemini Deep ResearchGoogle DeepMind | vs | DeepSeek-V4-Pro-BaseDeepSeek | cross-developer peerstext |
Questions
Gemini Deep Research is a managed agentic model that plans and executes multi-step research and produces cited reports. It is developed by Google DeepMind and its current sourced lifecycle status is preview.
Gemini Deep Research's current record lists Text, Image, Video, Audio, and Document as input and Text and Image as output.
The current record lists a 1,048,576-token context window and a maximum output of 65,536 tokens.
Gemini Deep Research is marked as API-available. The directly sourced provider records currently include Google AI.
No directly sourced token price is currently attached to Gemini Deep Research. Missing prices remain unknown rather than being inferred from another model or provider.
Gemini Deep Research's recorded capabilities are generation, reasoning, research, and tools. Its supported tasks are research and text.
Gemini Deep Research is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are deep-research-preview-04-2026.
The current compatible peer set includes Gemini 2.5 Pro, Gemini 3.1 Pro, Gemini 3.6 Flash, Gemini 3.7 Flash, and Gemini 3.5 Flash-Lite. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
Gemini Deep Research was last verified Aug 29, 2026 from Google DeepMind's primary source, “Gemini Deep Research | Gemini API.” The evidence is classified as official fact.