Gemini 3.5 Flash-Lite is Google's fastest and most cost-effective model in the Gemini 3.5 family, aimed at high-throughput, low-cost execution. The Gemini API model id is gemini-3.5-flash-lite, and Google lists it as Stable. Google's deprecations page shows a July 21, 2026 release date and no shutdown date, and names it as the recommended replacement for gemini-3.1-flash-lite.
Key features
- Multimodal input: text, image, video, audio and PDF in, text out.
- Large limits: a 1,048,576-token input window and 65,536 output tokens, according to the model page.
- Agent-friendly tools: function calling, structured outputs, code execution, search grounding, grounding with Google Maps, URL context, file search, caching and thinking are supported, with computer use in Preview.
- Consumption options: Batch API, Flex inference and Priority inference are all supported.
- Not supported: audio generation, image generation and the Live API.
Model specs
| Spec | Gemini 3.5 Flash-Lite |
|---|---|
| API model id | gemini-3.5-flash-lite |
| Status | Stable |
| Inputs | Text, image, video, audio, PDF |
| Output | Text |
| Input / output limit | 1,048,576 / 65,536 tokens |
| Release date | July 21, 2026 (per the deprecations page) |
Pricing
Google's pricing page, last updated October 28, 2026 and checked on October 29, 2026, lists Standard paid-tier prices of $0.30 per 1M input tokens (text, image, video, audio) and $2.50 per 1M output tokens, including thinking tokens. Check that page before budgeting, because prices change.
Use cases
- Subagent tasks inside larger agent systems.
- Document parsing and simple data extraction.
- High-volume agentic workflows where cost per call matters.
Getting started
- Create a key in Google AI Studio and set the model to
gemini-3.5-flash-litein the Gemini API. - Choose Batch or Flex consumption if latency is not critical and you want lower cost.
- Compare output quality with Gemini 3.5 Flash on your own data before standardizing on the Lite tier.
FAQ
What is the Gemini 3.5 Flash-Lite model id?
gemini-3.5-flash-lite, listed as a Stable version.
How much does Gemini 3.5 Flash-Lite cost?
$0.30 per 1M input tokens and $2.50 per 1M output tokens on the Standard paid tier, as shown on Google's pricing page on October 29, 2026.
What is its context window?
Input up to 1,048,576 tokens, with up to 65,536 output tokens.
What does it replace?
Google's deprecations page names it as the recommended replacement for gemini-3.1-flash-lite, which has a May 7, 2027 shutdown date.
Alternatives
- Gemini 3.5 Flash: the larger 3.5 Flash model.
- Gemini 3.1 Flash-Lite: the previous Flash-Lite generation.
- Gemini 3.7 Flash: a more capable Flash model for agentic work.
Conclusion
Gemini 3.5 Flash-Lite is the cheap, fast end of Google's current lineup, with a million-token input window and broad tool support. See Google's model page for the full spec, and browse more options in the models category.
Sources
- Websitehttps://ai.google.dev/gemini-api/docs/models
- Social Mediahttps://x.com/GoogleAI
Comments
No comments yet. Be the first to comment!