Deep Research Pro Preview 12 2025
Deep Research Pro Preview 12 2025 is a Vertex AI model available in SteelEngine. It supports a 1M token context window. Pricing starts at $2/1M input tokens and $12/1M output tokens. Key capabilities include Tool choice, Deep research, Memory off.
Runs long, multi-step research tasks that search, read, and synthesize sources on their own. Reads up to 1M tokens of context in one call.
INPUT / 1M
$2
CACHED INPUT / 1M
$0.2
OUTPUT / 1M
$12
CONTEXT WINDOW
1M
MAX OUTPUT
Not published
PRICING
What Deep Research Pro Preview 12 2025 costs to run.
List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.
01 / INPUT
$2
per 1M input tokens
02 / CACHED INPUT
$0.2
per 1M cached input tokens
03 / OUTPUT
$12
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What Deep Research Pro Preview 12 2025 supports.
Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.
CAPABILITIES
Tool choice, Deep research, Memory off, Image input
CONTEXT WINDOW
1M
MAX OUTPUT TOKENS
Not published
MODEL ID
vertex/deep-research-pro-preview-12-2025
PROVIDER
Vertex AI
MORE MODELS
More from Vertex AI
Compare nearby options from the same provider before you pick a default for your workflow.
Vertex AI
RECOMMENDED
Gemini 4 Argon
Higher-priced reasoning model for complex planning and multi-step agent work. A recommended default among SteelEngine’s Vertex AI models.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
Vertex AI
RECOMMENDED
Gemini 3.8 Flash
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. A recommended default among SteelEngine’s Vertex AI models.
IN / 1M
$0.75
OUT / 1M
$3.75
CONTEXT
1.05M
Vertex AI
RECOMMENDED
Gemini 3.5 Flash
Mid-priced, latency-focused reasoning model for interactive agent steps. A recommended default among SteelEngine’s Vertex AI models.
IN / 1M
$1.5
OUT / 1M
$9
CONTEXT
1.05M
BUILD WITH STEELENGINE
Put Deep Research Pro Preview 12 2025 to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.