Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite is a large language model made by Google, added to the catalog on 21 Jul 2026. It has a context window of 1,048,576 tokens and costs $0.30 per 1M input tokens and $2.50 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: focused subagent tasks, processing mixed-format source material and generating structured text responses.
Price checked ยท source: OpenRouter
What Gemini 3.5 Flash Lite is
Google Gemini 3.5 Flash Lite is a high-efficiency model from Google described as suited to focused tasks within complex, multi-agent workflows. Its provider highlights upgraded agentic capabilities and describes its use as a subagent for a defined task. It accepts text, image, video, file, and audio inputs, while its listed output is text. This makes it a multimodal input model with text generation as its output; it is not listed as producing images, video, or audio. It can be used with tools and supports reasoning, structured outputs, and response formatting.
The model has a context length of 1,048,576 tokens and a maximum output of 65,536 tokens. This gives an interaction room for extensive input and a substantial text response. Its input types suit tasks that involve reading text alongside image, video, file, or audio material and returning a written result. Tool support and structured-output options also fit focused steps in workflows where a system supplies tools or expects a response in a defined format. The provider specifically positions the model for subagent work within multi-agent processes, without naming a particular industry or specialist domain. The facts do not specify supported tools, file formats, output schemas, or individual task types. Its documented profile combines multimodal inputs, long context, text output, and features for tool-assisted, formatted reasoning tasks.
Key features
- Accepts text, image, video, file, and audio inputs
- Produces text output
- Supports a context of up to 1,048,576 tokens
- Supports tools, structured outputs, response formatting, and reasoning
Typical uses
- Focused subagent tasks
- Processing mixed-format source material
- Generating structured text responses
- Reasoning within multi-agent workflows
Gemini 3.5 Flash Lite pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.30 | $0.15 |
| Output, per 1M tokens | $2.50 | $1.25 |
| Cached input read, per 1M tokens | $0.03 | $0.015 |
| Cache write, per 1M tokens | $0.0833 | n/a |
| Image input, per image | $0.00 | $0.00 |
| Web search, per search | $0.014 | $0.014 |
| Variant | Model id |
|---|---|
| Batch | google/gemini-3.5-flash-lite:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 21 Jul 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0095 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.014 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.049 |
Gemini 3.5 Flash Lite specifications
| Model id | google/gemini-3.5-flash-lite |
|---|---|
| Version | gemini-3.5-flash-lite-20260721 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 Jul 2026 |
| Input types | text, image, video, file, audio |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Gemini 3.5 Flash Lite yet.
Compare Gemini 3.5 Flash Lite
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.