OpenRating is an independent, open-source AI rating platform. Join the community

OOpenRating
All models

Google · Released Jan 10, 2026

Gemini 3.5 Flash-Lite

Google's ultra-lightweight high-speed model with 312 tok/s throughput, 1M context, and sub-10 cent task economics.

Proprietary

OpenRating Index

12.0

0–100 composite

Reasoning Index

16.2

0–100 composite

Cost / Task

$0.69

benchmark run

Output speed

311 tok/s

blended tok/s

Time to first token

4.7s

median latency

Input price

$0.3

per 1M tokens

Output price

$2.5

per 1M tokens

Context window

1M

tokens

Strengths

  • Lightning 312+ tok/s output speed with 0.26s TTFT

  • 1,000,000 token context window at ultra-low prices

  • Cost-effective workhorse for bulk data parsing

How we rate Gemini 3.5 Flash-Lite

OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.

OpenRating Index

12.0

Reasoning Index

16.2

Token Pricing

Input per 1M tokens

$0.3

Output per 1M tokens

$2.5

Cost of 1M input + 1M output

$2.8

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.69 total).

Reasoning (Chain of Thought)
$0.33
Answer generation
$0.11
Cache write overhead
$0.12
Cache hit queries
$0.062
Input payload
$0.063