Gemini 3.5 Flash-Lite
Explore benchmark scores, genre strengths, weaknesses, and recent examples for Gemini 3.5 Flash-Lite on Orivel.
Model Overview
Released
2026-07-21
Input
$0.30 / 1M
Output
$2.50 / 1M
Max output
66k tokens
The balanced Google option on Orivel, and the odd one out in its own generation: Gemini 3.5 Flash-Lite costs less per token than Gemini 3.5 Flash, which is what you would expect, but it also costs less than nothing else in the 3.x Lite family charges. It replaces Gemini 2.5 Flash at exactly the same list price.
Specs and pricing
| Item | Gemini 3.5 Flash-Lite |
|---|---|
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Input / 1M | $0.30 |
| Output / 1M | $2.50 |
The version numbers do not run the way you expect
Gemini 3.5 Flash lists at $1.50 / $9.00 — double what the newer 3.6, 3.7 and 3.8 Flash models charge. Google's numbering is not a price ladder and is not reliably a capability ladder either, so reading a Gemini model's position from its version number will mislead you in both directions.
What this model is for on this site is the middle: identical pricing to the Gemini 2.5 Flash it replaces, so the balanced slot changes generation without changing what it costs to run.
What changed
- Takes the Google balanced slot on Orivel from Gemini 2.5 Flash on September 9, 2026
- Context window 1,048,576 tokens; max output 65,536 tokens
- Pricing: $0.30 input / $2.50 output per 1M tokens — identical to Gemini 2.5 Flash
- Cheaper than Gemini 3.5 Flash ($1.50 / $9.00) despite sharing its version number
- Accepts temperature and structured output on the Gemini Developer API (verified 2026-09-09)
Specs across the current lineup
Published specs and pricing, comparable before any benchmark data exists.
| Model | Context | Max output | Input / 1M | Output / 1M |
|---|---|---|---|---|
| openai GPT-6 Astra | — | 128k | $10.00 | $50.00 |
| google Gemini 3.8 Flash | — | 66k | $0.75 | $3.75 |
| anthropic Claude Fable 5.1 | 1M | 128k | $10.00 | $50.00 |
| google Gemini 3.5 Flash-Lite | — | 66k | $0.30 | $2.50 |
| openai GPT-5.6 | 1M | 128k | $4.00 | $20.00 |
| anthropic Claude Opus 5 | 1M | 128k | $5.00 | $25.00 |
| openai GPT-5 mini | 400k | 128k | $0.25 | $2.00 |
| google Gemini 3.1 Flash-Lite | — | 66k | $0.25 | $1.50 |
| anthropic Claude Sonnet 5 | 1M | 128k | $2.00 | $10.00 |
Overall Performance
Overall Rank
#7
Overall win rate
Average Score
Wins
1
Sample Count
2
Win Rate by Model
| Model | Wins | Losses | Draws | Win Rate | Detail |
|---|---|---|---|---|---|
| OpenAI GPT-5 mini | 1 | 0 | 0 |
100%
|
View Gemini 3.5 Flash-Lite vs GPT-5 mini Comparison & Evaluation |
| OpenAI GPT-5.6 | 0 | 1 | 0 |
0%
|
View Gemini 3.5 Flash-Lite vs GPT-5.6 Comparison & Evaluation |
Compare by Genre
Strength by Evaluation Criteria
Average score by criterion (out of 10)
Latest Tasks
Empathy
Supporting a Friend Who Was Just Laid Off and Feels Ashamed
Write a realistic text-message conversation in which you support a close friend who has just been laid off. Situation: Your friend Maya, 34, was laid off yeste...
Counseling
Supporting a Friend Who Feels Left Behind by Their Peers
You are responding as a warm, thoughtful peer supporter (not a licensed therapist) in a text-message conversation. Here is the message you received from your f...