Gemini 3.8 Flash
Gemini 3.8 Flash is a Google model available in SteelEngine. It supports a 1.05M token context window. Pricing starts at $0.75/1M input tokens and $3.75/1M output tokens. Key capabilities include Tool choice, Structured outputs, Thinking low, medium, high.
Mid-priced, latency-focused reasoning model for interactive agent steps. A recommended default among SteelEngine’s Google models. Released Sep 2, 2026.
INPUT / 1M
$0.75
CACHED INPUT / 1M
$0.075
OUTPUT / 1M
$3.75
CONTEXT WINDOW
1.05M
MAX OUTPUT
66k
RELEASED
PRICING
What Gemini 3.8 Flash 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
$0.75
per 1M input tokens
02 / CACHED INPUT
$0.075
per 1M cached input tokens
03 / OUTPUT
$3.75
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What Gemini 3.8 Flash 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, Structured outputs, Thinking low, medium, high, Max output 66k, Image input
CONTEXT WINDOW
1.05M
MAX OUTPUT TOKENS
66k
MODEL ID
gemini-3.8-flash
PROVIDER
MORE MODELS
More from Google
Compare nearby options from the same provider before you pick a default for your workflow.
RECOMMENDED
Gemini 4 Argon
Higher-priced reasoning model for complex planning and multi-step agent work. A recommended default among SteelEngine’s Google models.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
RECOMMENDED
Gemini 3.5 Flash
Mid-priced, latency-focused reasoning model for interactive agent steps. A recommended default among SteelEngine’s Google models. Released May 19, 2026.
IN / 1M
$1.5
OUT / 1M
$9
CONTEXT
1.05M
Gemini 3.5 Flash Lite
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 and writes up to 66k tokens. Released Jul 21, 2026.
IN / 1M
$0.3
OUT / 1M
$2.5
CONTEXT
1.05M
BUILD WITH STEELENGINE
Put Gemini 3.8 Flash to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.