# gemini-3-flash-preview — API, Pricing & Context Window

gemini-3-flash-preview on Vivgrid: Google's fast multimodal Gemini 3 model with a 1M-token context window and very low cached pricing.

`gemini-3-flash-preview` is the fast, cost-efficient member of the Gemini 3 family, accepting **text, image, video, audio, and PDF** within a **~1.05M-token context window**. Its very low cached-input pricing makes it attractive for repeated-context workloads.

On Vivgrid it runs as a globally centralized model, reachable through the same unified API key as every other model in the catalog.

## Specifications

|     |     |
| --- | --- |
| **Provider** | Google |
| **Model ID** | `gemini-3-flash-preview` |
| **Best for** | General-purpose |
| **Context window** | 1,048,576 tokens |
| **Max output** | 64,000 tokens |
| **Modalities** | Text, Image, Video, Audio, Pdf |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2025-01 |
| **Acceleration** | 🌐 Global (Centralized) |

## Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.50 | $0.005 | $3.00 |

## Quick start

Call `gemini-3-flash-preview` through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the [Vivgrid Console](https://console.vivgrid.com/).

```
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

## Ideal use cases

- High-volume multimodal agents
- Repeated-context workflows that benefit from cheap cached input
- Media ingestion and summarization at scale
- Fast assistants needing large context

## Related models

- [gemini-3.5-flash](/content/docs/models/gemini-3.5-flash/index.html) — the newer flash generation
- [gemini-3-pro-preview](/content/docs/models/gemini-3-pro-preview/index.html) — the pro-tier sibling
- [gemini-2.5-flash](/content/docs/models/gemini-2.5-flash/index.html) — prior flash model

### On this page

[Ideal use cases](/content/docs/models/gemini-3-flash-preview#ideal-use-cases/index.html) [Related models](/content/docs/models/gemini-3-flash-preview#related-models/index.html)