Gemini 2.5 Flash Lite

by Google

Cheapest option with huge context via Vertex AI. Optimized for high-throughput tasks.

VisionStructured outputFiles
Context window
1.0M
Max output
66K
Input price
$0.10 /1M
Output price
$0.40 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#372 of 505 LLMs
TierEfficient
Output speed264 tok/s
First token0.70s
Intelligence Index12.7
Coding Index7.4
Math Index35.3
MMLU-Pro
72%
GPQA Diamond
47%
Humanity's Last Exam
4%
LiveCodeBench
40%
SciCode
18%
AIME 2025
35%
IFBench
32%
Long-context reasoning
31%
Terminal-Bench Hard
2%
τ²-Bench Telecom
19%

Available routes

The same Gemini 2.5 Flash Lite runs on 2 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
Google CloudEUOpt-inNo
Abuse-monitoring logs (window not stated) + 24h in-memory cache. Search/Maps grounding adds 30-day retention with no opt-out.
PAYG$0.10$0.40
Google CloudEUOpt-inNo
Abuse-monitoring logs (window not stated) + 24h in-memory cache. Search/Maps grounding adds 30-day retention with no opt-out.
PAYG$0.10$0.40

Human review: Abuse-flagged only

Other models from Google

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Gemini 2.5 Flash Lite by Google — pricing, benchmarks, hosting routes | Opper AI