Skip to content
ProviderBench home

Highest Output-Speed Gemini 3.5 Flash-Lite Inference Providers

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

Median input price:
$0.3 / 1M
Median output price:
$2.5 / 1M
Median cache price:
$0.03 / 1M

Highest output speed endpoint ranking

Rank providers by
Highest Output-Speed Gemini 3.5 Flash-Lite Inference Providers
RankProvider / routePricingBenchmarksAPI support
#1Provider / route
Google Vertex(0)
1M contextunknown65.5K max output
Pricing
Input
$0.3 / 1M
Output
$2.5 / 1M
Cache
$0.03 / 1M
Blended
$1.0333 / 1M
Benchmarks
Speed— Best comparable value
3.29 s
TTFT— Worst comparable value
0.56 s
TPS— Best comparable value
183.0 tok/s
Uptime— Best comparable value
99.97%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
#2Provider / route
Google AI Studio(0)
1M contextunknown65.5K max output
Pricing
Input
$0.3 / 1M
Output
$2.5 / 1M
Cache
$0.03 / 1M
Blended
$1.0333 / 1M
Benchmarks
Speed— Worst comparable value
3.99 s
TTFT— Best comparable value
0.49 s
TPS— Worst comparable value
143.0 tok/s
Uptime— Worst comparable value
99.73%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
—Provider / route
Google AI Studio(0)
1M contextunknown65.5K max output
Pricing
Input
$0.15 / 1M
Output
$1.25 / 1M
Cache
$0.015 / 1M
Blended— Best comparable value
$0.5167 / 1M
Benchmarks
Speed
N/a
TTFT
N/a
TPS
N/a
Uptime— Worst comparable value
99.73%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
—Provider / route
Google AI Studio(0)
1M contextunknown65.5K max output
Pricing
Input
$0.54 / 1M
Output
$4.5 / 1M
Cache
$0.054 / 1M
Blended— Worst comparable value
$1.86 / 1M
Benchmarks
Speed
N/a
TTFT
N/a
TPS
N/a
Uptime— Worst comparable value
99.73%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
—Provider / route
Google Vertex(0)
1M contextunknown65.5K max output
Pricing
Input
$0.15 / 1M
Output
$1.25 / 1M
Cache
$0.015 / 1M
Blended— Best comparable value
$0.5167 / 1M
Benchmarks
Speed
N/a
TTFT
N/a
TPS
N/a
Uptime— Best comparable value
99.97%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
—Provider / route
Google Vertex(0)
1M contextunknown65.5K max output
Pricing
Input
$0.54 / 1M
Output
$4.5 / 1M
Cache
$0.054 / 1M
Blended— Worst comparable value
$1.86 / 1M
Benchmarks
Speed
N/a
TTFT
N/a
TPS
N/a
Uptime— Best comparable value
99.97%
API support
  • Tool calling
  • Tool choice
  • Structured output
  • Parallel calls
Green value Best comparable resultRed value Worst comparable result

Endpoint data fetched .

Gemini 3.5 Flash-Lite endpoint guide

How to interpret the Highest Output-Speed Gemini 3.5 Flash-Lite Inference Providers

2 of 6 Gemini 3.5 Flash-Lite endpoints currently have the published data required for this ranking. Google Vertex leads at 183.0 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 143.0 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 3.5 Flash-Lite 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.