Gemini 3.5 Flash Lite
- Context
- 1.05M
- 66K max output
- Input price
- $0.30
- per 1M tokens · Gemini API
- Output price
- $2.50
- per 1M tokens
- Epoch Capabilities Index
- 145.1
- #60 of 71 listed
- LMArena Text
- 1,456
- #38 of 79 listed
Where to run it
1 offering · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Audio tokens | $0.30 / 1M tokens |
| Image tokens | $0.30 / 1M tokens | |
| Text tokens | $0.30 / 1M tokens | |
| Video tokens | $0.30 / 1M tokens | |
| Audio tokens · Batch | $0.15 / 1M tokens | |
| Audio tokens · Flex tier | $0.15 / 1M tokens | |
| Image tokens · Batch | $0.15 / 1M tokens | |
| Image tokens · Flex tier | $0.15 / 1M tokens | |
| Text tokens · Batch | $0.15 / 1M tokens | |
| Text tokens · Flex tier | $0.15 / 1M tokens | |
| Video tokens · Batch | $0.15 / 1M tokens | |
| Video tokens · Flex tier | $0.15 / 1M tokens | |
| Audio tokens · Priority tier | $0.54 / 1M tokens | |
| Image tokens · Priority tier | $0.54 / 1M tokens | |
| Text tokens · Priority tier | $0.54 / 1M tokens | |
| Video tokens · Priority tier | $0.54 / 1M tokens | |
| Output | Standard | $2.50 / 1M tokens |
| Batch | $1.25 / 1M tokens | |
| Flex tier | $1.25 / 1M tokens | |
| Priority tier | $4.50 / 1M tokens | |
| Cache read | Standard | $0.030 / 1M tokens |
| Batch | $0.020 / 1M tokens | |
| Flex tier | $0.020 / 1M tokens | |
| Priority tier | $0.050 / 1M tokens | |
Vendor-reported scores
Published by Google, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| SWE-bench Pro | public set, internal Antigravity harness, thinking high | 54.2% |
| Terminal-Bench 2.1 | Terminus-2 harness, thinking high | 54% |
| OSWorld-Verified | average of 5 runs, single attempt, max 100 steps, thinking high | 74% |
| CharXiv Reasoning | no tools, thinking high | 74.5% |
| with tools (search + code execution), thinking high | 76.5% |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 145.1
#60 of 71 listed models · CI 142.3–146.7
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,456
#38 of 79 listed models · CI 1,451–1,461 · 33,501 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 26%
#50 of 56 listed models · high effort · ±2.6
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 83.3%
#52 of 64 listed models · high effort · ±2.66
Also listed: low effort 75.8% · minimal effort 74.2%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,484
#45 of 79 listed models · CI 1,471–1,496 · 2,584 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,503
#39 of 79 listed models · CI 1,496–1,510 · 9,343 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,268
#26 of 49 listed models · CI 1,259–1,278 · 5,254 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made