Gemini Deep Research Pro Preview is Google's language model with a 66K context window and up to 33K output tokens, available from 2 providers, starting at $2.00 / 1M input and $12.00 / 1M output. Preview release of the Gemini-based Deep Research Pro model, designed for in-depth multi-step research synthesis and report generation.
Specifications
Canonical IDgoogle-deep-research-pro-preview
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window66K tokens
Max Output33K tokens
Input ModalitiesAudioImagePdfTextVideo
Output ModalitiesText
Reasoning Effortsdefault

Capabilities

Input5/5
Text
Image
Audio
Video
PDF
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs
Native JSON Schema·
Web Search
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Google Gemini logo
Google Gemini
gemini/deep-research-pro-preview-12-2025
$2.00$12.00$1.00$6.00
Google Vertex AI logo
Google Vertex AI
vertex_ai/deep-research-pro-preview-12-2025
$2.00$12.00$1.00$6.00

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemini 3 Pro Image Preview66K$2.00$12.00Available
Qwen Image 2 ProAvailable
Gemini Deep Research Pro Preview66K$2.00$12.00Current
Nano Banana ProAvailable

Other models

ModelTierReleasedContextInput / 1MOutput / 1M
Imagen 4 FastFast480
Imagen 4 UltraUltra480
Imagen 4480
Gen-4 Image
Gen-4 Image Turbo
Imagen 4 Preview
Gemini 3.1 Flash Image PreviewFlash131K$0.250$1.50
Stable Diffusion 3.5 Large77
Recraft V3
BRIA 3.2

Model IDs