# gemini-3.5-flash — API, Pricing & Context Window

gemini-3.5-flash on Vivgrid: Google's fast multimodal model with a 1M-token context window across text, image, video, audio and PDF.

`gemini-3.5-flash` is Google's fast, fully multimodal model, accepting **text, image, video, audio, and PDF** inputs within a **1M-token context window**. It's a strong agent model for workflows that mix media types at scale.

On Vivgrid, `gemini-3.5-flash` runs as a globally centralized model reachable through the same OpenAI-compatible endpoint and unified key as every other model in the catalog.

## Specifications

|     |     |
| --- | --- |
| **Provider** | Google |
| **Model ID** | `gemini-3.5-flash` |
| **Best for** | General-purpose |
| **Context window** | 1,000,000 tokens |
| **Max output** | 65,536 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 |
| --- | --- | --- |
| $1.50 | $0.15 | $9.00 |

## Quick start

Call `gemini-3.5-flash` 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-3.5-flash",
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

## Ideal use cases

- Multimodal agents combining video, audio, images, and PDFs
- Long-context understanding up to 1M tokens
- Fast, high-volume reasoning and summarization
- Media-heavy ingestion and analysis pipelines

## Related models

- [gemini-3.1-pro-preview](/content/docs/models/gemini-3.1-pro-preview/index.html) — higher-end Gemini for coding
- [gemini-3-flash-preview](/content/docs/models/gemini-3-flash-preview/index.html) — prior flash generation
- [gpt-5.4-mini](/content/docs/models/gpt-5.4-mini/index.html) — comparable fast multimodal option

[gpt-4o on Vivgrid: OpenAI's multimodal GPT-4o with a 128K context window and image input, accessible through one unified API key.](/content/docs/models/gpt-4o/index.html) [gemini-3.1-pro-preview on Vivgrid: Google's high-end multimodal coding model with a ~1M-token context window across text, image, video, audio and PDF.](/content/docs/models/gemini-3.1-pro-preview/index.html)