Home/Models/gemini-3-flash-pre

gemini-3-flash-pre

NEWGoogleText + Vision + AudioProprietary

Use with your agent

Context

Input

$0.30/M

Output

$1.20/M

Throughput

182tok/s

Latency

230ms

Popularity

64%

Overview

Gemini 3 Flash (Preview) is built for volume. It streams multimodal output at very high throughput for a fraction of the cost of a flagship, and its million-token window means you rarely have to chunk inputs. The pick for routers, summarisers and anything you run at scale.

Capabilities

REASONINGStrong multi-step reasoning and planning.

MID CONTEXTBalanced context window for everyday work.

VISIONUnderstands images, screenshots and PDFs.

Routing & endpoints

Endpoint	Context	Price	Latency	Status
claws-edge · us-east	1M	$0.30 / $1.20 /M	230ms	Operational
claws-edge · eu-west	1M	$0.30 / $1.20 /M	252ms	Operational
Google · direct	1M	$0.30 / $1.20 /M	278ms	Operational

Sample request

curl https://api.claws.io/v1/chat/completions \
  -H "Authorization: Bearer $CLAWS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-flash-pre",
    "messages": [{"role": "user", "content": "Hello"}]
  }'