Gemini 3.7 Flash
Gemini 3.7 Flash is a large language model made by Google, added to the catalog on 13 Aug 2026. It has a context window of 1,048,576 tokens and costs $0.75 per 1M input tokens and $3.75 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: coding tasks, complex multi-step reasoning and agentic workflows with tools.
Price checked · source: OpenRouter
What Gemini 3.7 Flash is
Google Gemini 3.7 Flash is a multimodal model from Google designed for responsive agentic workflows, coding and complex multi-step reasoning. It accepts text, images, video, files and audio as input, and produces text. This means it can take different kinds of supplied material while returning text responses. It supports reasoning, tools, structured outputs and response-format controls. Its catalog description emphasizes tasks that involve multiple stages or tool use, rather than limiting it to a single type of text prompt.
The model has a context window of 1,048,576 tokens and a maximum output length of 65,536 tokens. This gives it room to process long inputs or several supplied materials in a single request, subject to the model’s token limits. The output allowance also accommodates longer text responses. These capacities make it suitable for summarising extensive material, examining inputs across supported modalities, and producing longer formatted responses. For coding work, it can assist with tasks that require reasoning through multiple steps, and tool support can be used in workflows that call for tools. Structured outputs and response-format controls provide options when generated text needs a defined structure. It generates text only; the listed image, video and audio capabilities refer to inputs it accepts. Combined with its stated focus on responsive agentic workflows, these features fit tasks that bring together substantial context, coding, multimodal input or multi-step reasoning.
Key features
- Accepts text, images, video, files and audio; produces text.
- Has a context window of 1,048,576 tokens.
- Supports up to 65,536 output tokens.
- Supports tools, structured outputs and response-format controls.
- Includes support for reasoning.
Typical uses
- Coding tasks
- Complex multi-step reasoning
- Agentic workflows with tools
- Working with image and video inputs
- Generating structured text responses
Gemini 3.7 Flash pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.75 | $0.375 |
| Output, per 1M tokens | $3.75 | $1.875 |
| Cached input read, per 1M tokens | $0.075 | $0.0375 |
| Cache write, per 1M tokens | $0.0417 | $0.0417 |
| Image input, per image | $0.000001 | $0.00 |
| Web search, per search | $0.014 | $0.014 |
| Variant | Model id |
|---|---|
| Batch | google/gemini-3.7-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 13 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0015 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.030 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.118 |
Gemini 3.7 Flash specifications
| Model id | google/gemini-3.7-flash |
|---|---|
| Version | gemini-3.7-flash-20260813 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 13 Aug 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 3.7 Flash yet.
Compare Gemini 3.7 Flash
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.