Gemini 3.5 Flash
Gemini 3.5 Flash is a large language model made by Google, added to the catalog on 19 May 2026. It has a context window of 1,048,576 tokens and costs $1.50 per 1M input tokens and $9.00 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: summarising long documents, reasoning over image and video inputs and coding assistance.
Price checked ยท source: OpenRouter
What Gemini 3.5 Flash is
Google Gemini 3.5 Flash is a multimodal model that accepts text, images, video, files and audio as input, and produces text. It has a context window of 1,048,576 tokens and can generate up to 65,536 output tokens. This gives it room to process long inputs, including documents or mixed-media material, while returning text responses. The supported input and output formats make it suitable for work that combines different kinds of source material with written analysis or generation.
The model supports reasoning, tools, structured outputs and response formats. These capabilities can be used in workflows that call tools, request responses in a defined structure, or involve reasoning over supplied material. Its listed strengths include coding proficiency and reasoning, so coding assistance and problem-solving are among the work it is suited to support. It can also be used to summarize or extract information from lengthy documents and media inputs. The facts do not specify particular tools, file types, supported languages or output formats, so those details may depend on the interface in which the model is used. Gemini 3.5 Flash is a text-output model; the listed audio, image and video modalities are inputs, not generated media. Its large context window can suit tasks that benefit from keeping extensive source material available in one request, while its output limit allows for substantial text responses.
Key features
- Accepts text, image, video, file and audio inputs
- Produces text output
- Has a context window of 1,048,576 tokens
- Supports up to 65,536 output tokens
- Supports tools, reasoning, structured outputs and response formats
Typical uses
- Summarising long documents
- Reasoning over image and video inputs
- Coding assistance
- Extracting information from files
- Generating structured text responses
Gemini 3.5 Flash pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $1.50 | $0.75 |
| Output, per 1M tokens | $9.00 | $4.50 |
| Cached input read, per 1M tokens | $0.15 | $0.075 |
| Cache write, per 1M tokens | $0.0833 | n/a |
| Image input, per image | $0.000002 | $0.000001 |
| Web search, per search | $0.014 | $0.014 |
| Variant | Model id |
|---|---|
| Batch | google/gemini-3.5-flash: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 19 May 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0035 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.045 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.063 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.239 |
Gemini 3.5 Flash specifications
| Model id | google/gemini-3.5-flash |
|---|---|
| Version | gemini-3.5-flash-20260519 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | 2025-01-01 |
| Added to catalog | 19 May 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 yet.
Compare Gemini 3.5 Flash
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.