Gemini 3 Flash (Preview)

Preview of next-generation Gemini 3 Flash built for speed, combining frontier intelligence with superior search and grounding.

gemini-3-flash-preview
STABLE
1,000,000 context
Starting at $0.40/M (20% off) input tokens
Starting at $2.40/M (20% off) output tokens
Streaming
Vision
Tools
Reasoning
JSON Output

Providers for Gemini 3 Flash (Preview)

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Google AI Studio

google-ai-studio/gemini-3-flash-preview
Context Size
1M
Stability
STABLE
Pricing
Input
$0.50$0.40
/M
Cached
—
Output
$3.00$2.40
/M
-20% off
Tiered Pricing
≤200K tokens$0.50 in / $3.00 out$0.40 in / $2.40 out
>200K tokens$1.00 in / $6.00 out$0.80 in / $4.80 out
Capabilities
Streaming
Vision
Tools
Reasoning
JSON Output
Try in Playground

Google Vertex AI

google-vertex/gemini-3-flash-preview
Context Size
1M
Stability
STABLE
Pricing
Input
$0.50$0.40
/M
Cached
—
Output
$3.00$2.40
/M
-20% off
Tiered Pricing
≤200K tokens$0.50 in / $3.00 out$0.40 in / $2.40 out
>200K tokens$1.00 in / $6.00 out$0.80 in / $4.80 out
Capabilities
Streaming
Vision
Tools
Reasoning
JSON Output
Try in Playground
    Gemini 3 Flash (Preview) – AI Model on LLM Gateway