Gemini 3.5 Flash Lite
Summary
Gemini 3.5 Flash Lite is a proprietary language model from Google DeepMind, released on 21 Jul 2026. It accepts text, images, video, audio and PDFs and generates text, with a 1M-token context window and up to 66K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.30 per million input tokens and $2.50 per million output tokens (Gemini API), across 4 providers we track.
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 21 Jul 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 1M (1,048,576 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Knowledge cutoff | Mar 2026 [models.dev] |
| Input | Text, images, video, audio and PDFs [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
Gemini 3.5 Flash Lite API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Gemini API gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | 1M | models.dev, 4 Oct 2026 |
| Google Vertex AI gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | 1M | models.dev, 4 Oct 2026 |
| OpenRouter google/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | 1M | OpenRouter, 4 Oct 2026 |
| Vercel AI Gateway google/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | 1M | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite has a context window of 1,048,576 tokens (1M) and can generate up to 65,536 tokens in a single response, according to models.dev.
How much does the Gemini 3.5 Flash Lite API cost?
Through Gemini API, Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 per million output tokens. Prices last verified 4 Oct 2026.
Is Gemini 3.5 Flash Lite open source?
No. Gemini 3.5 Flash Lite is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API, Google Vertex AI, OpenRouter, Vercel AI Gateway.
When was Gemini 3.5 Flash Lite released?
Google DeepMind released Gemini 3.5 Flash Lite on 21 Jul 2026, according to models.dev.
Which providers offer Gemini 3.5 Flash Lite?
We track Gemini 3.5 Flash Lite on 4 providers: Gemini API, Google Vertex AI, OpenRouter, Vercel AI Gateway.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.5-flash-lite.toml
- https://github.com/sst/models.dev/blob/dev/providers/google-vertex/models/gemini-3.5-flash-lite.toml
- https://openrouter.ai/google/gemini-3.5-flash-lite
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/google/gemini-3.5-flash-lite.toml