Skip to content
ProviderBench home

Highest Output-Speed Gemini 3 Flash Preview Inference Providers

Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.

Google Vertex currently ranks first at 70.0 tok/s via google-vertex/global.

Provider options:
6
Ranked:
2
Metric:
Output speed

Highest output speed endpoint ranking

Rank providers by
Highest Output-Speed Gemini 3 Flash Preview Inference Providers
RankProvider / routeOutput speedSpeed measurementsEndpoint details
#1Provider / route
Google Vertexgoogle-vertex/global
Output speed70.0 tok/sSpeed measurements
500-token response
8.23 s
Response starts
1.09 s
Output speed
70.0 tok/s
Endpoint details
Input price
$0.5 / 1M tokens
Output price
$3 / 1M tokens
Uptime (30 min)
97.60%
Context
1M
#2Provider / route
Google AI Studiogoogle-ai-studio
Output speed60.0 tok/sSpeed measurements
500-token response
9.28 s
Response starts
0.95 s
Output speed
60.0 tok/s
Endpoint details
Input price
$0.5 / 1M tokens
Output price
$3 / 1M tokens
Uptime (30 min)
99.80%
Context
1M
—Provider / route
Google Vertexgoogle-vertex/global/flex
Output speedInsufficient recent dataSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$0.25 / 1M tokens
Output price
$1.5 / 1M tokens
Uptime (30 min)
97.60%
Context
1M
—Provider / route
Google Vertexgoogle-vertex/global/priority
Output speedInsufficient recent dataSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$0.9 / 1M tokens
Output price
$5.4 / 1M tokens
Uptime (30 min)
97.60%
Context
1M
—Provider / route
Google AI Studiogoogle-ai-studio/flex
Output speedInsufficient recent dataSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$0.25 / 1M tokens
Output price
$1.5 / 1M tokens
Uptime (30 min)
99.80%
Context
1M
—Provider / route
Google AI Studiogoogle-ai-studio/priority
Output speedInsufficient recent dataSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$0.9 / 1M tokens
Output price
$5.4 / 1M tokens
Uptime (30 min)
99.80%
Context
1M

Endpoint data fetched .

Gemini 3 Flash Preview endpoint guide

How to interpret the Highest Output-Speed Gemini 3 Flash Preview Inference Providers

2 of 6 Gemini 3 Flash Preview endpoints currently have the published data required for this ranking. Google Vertex leads at 70.0 tok/s via google-vertex/global. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.

How generation throughput is ranked

The output-speed ranking compares recent median generated tokens per second. It favors routes that complete long generations quickly, while first-token latency remains a separate measure of how responsive the endpoint feels at the beginning.

Compare Google Vertex with the next option

Google AI Studio currently ranks second at 60.0 tok/s. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.

Use the route, not only the provider name

Gemini 3 Flash Preview has 6 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.