Solar System
loads medium
Tech. quality99
UX83
Time8 s
Cost$0.00413
Compare →
Gemini 3.1 Flash-Lite
Loads without errors5/5#1 of 26
Tech. quality94/100#12 of 26
UX84/100#17 of 26
Total cost$0.021
Average time8 s#1 of 26
Total tokens16,051
API price: $0.25 / $1.5 per 1M input / output tokens · as of 17/10/2026 source ↗
What is Gemini 3.1 Flash-Lite good for?
Google's cost-efficient model for high-volume agentic tasks, translation and simple data processing.
Description based on the maker · source ↗
- Maker
- Released
- 07/05/2026
- Model weights
- closed, the model is available through the API only
- Reasoning levels
- low medium high
How did Gemini 3.1 Flash-Lite do in the AI Lab tests?
- 5 of 5 outputs load without errors.
- Its best technical result was on the “Solar System” prompt (99/100).
- In the objective perft chess test it passed 0 of 6 positions.
- Average time per prompt 8 s#1 of 26
- Average cost per prompt $0.00429#2 of 26
- Technical quality 94/100#12 of 26
- Automatic UX rating 84/100#17 of 26
Outputs
All outputs of Gemini 3.1 Flash-Lite on the 5 prompts every other model got as well.
GTA-style game
loads medium
Tech. quality97
UX100
Time8 s
Cost$0.00385
Compare →
Monitor test
loads medium
Tech. quality82
UX87
Time8 s
Cost$0.00452
Compare →
New York & Central Park map
loads medium
Tech. quality99
UX72
Time9 s
Cost$0.00544
Compare →
Chess with an engine
loads medium
Tech. quality95
UX79
Time7 s
Cost$0.00351
Compare →
Cost = tokens priced with the API price list valid on the date shown next to the cost (prices change). ≈ = estimate (only the total token count is known), no ≈ = exact from input / output tokens. “Loads” = the page opens without errors; technical quality also checks behaviour during use – judge the quality in the viewer.