Model
Gemini 3.5 Flash Lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
9 providersreleased knowledge cutoff 2026-03closed weights
$0.3
best input /M · NanoGPT
$2.50
best output /M
1.05M
context window
66K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| NanoGPT google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | $0.083 | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Google gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | — | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Impossibl google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | — | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| OpenRouter google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | $0.083 | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Merge Gateway google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | — | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Ofox google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | $0.083 | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Vercel AI Gateway google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | — | 1M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Eden AI google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | $0.083 | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 | |
| Kilo Gateway google/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | $0.083 | 1.05M | reasoningtoolsstructuredvision | Jul 21, 2026 |
Price badge
https://models.sutraworks.ai/badge/google/gemini-3.5-flash-lite.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- SWE-Bench Pro ↗(resolve rate)report ↗54.2
- Terminal-Bench ↗(accuracy)report ↗54
- MLE-Bench(average position score)report ↗39.2
- GDPval-AA(Elo)report ↗1140
- OSWorld-Verified ↗(success rate)report ↗74
- CharXiv Reasoning(accuracy)report ↗74.5
- CharXiv Reasoning(accuracy)report ↗76.5
- GDM-MRCR(accuracy)report ↗72.2
- GDM-MRCR(accuracy)report ↗21.3
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.