MODEL PROVIDER
Vertex AI
Gemini models served through Google Cloud Vertex AI, so model traffic and billing stay in your Google Cloud project.
Vertex AI has 7 models available in SteelEngine with pricing, context window, and capability details.
MODELS
7
DEFAULT MODEL
Gemini 4 Argon
PRICING
USD PER 1M TOKENS
MODELS
Vertex AI models in SteelEngine.
Recommended models come first. Open any model for its full price sheet, limits, and supported capabilities.
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
Vertex AI
Gemini 3.5 Flash Lite
The lowest-cost model in the Vertex AI lineup, for high-volume steps that still benefit from thinking. Reads up to 1.05M tokens of context in one call and writes up to 66k tokens.
IN / 1M
$0.3
OUT / 1M
$2.5
CONTEXT
1.05M
Vertex AI
Gemini 3.1 Pro Preview
Among the highest-priced models in the Vertex AI lineup, for the hardest reasoning and planning work. Reads up to 1.05M tokens of context in one call.
IN / 1M
$2
OUT / 1M
$12
CONTEXT
1.05M
Vertex AI
Gemini 3 Flash Preview
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Reads up to 1.05M tokens of context in one call.
IN / 1M
$0.5
OUT / 1M
$3
CONTEXT
1.05M
Vertex AI
Deep Research Pro Preview 12 2025
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.
IN / 1M
$2
OUT / 1M
$12
CONTEXT
1M
MORE PROVIDERS
Compare other providers.
Every provider page lists the same pricing and capability details, so you can compare like for like.
BUILD WITH STEELENGINE
Put Vertex AI models to work.
Use these models in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.