> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tess.im/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini Flash

Gemini Flash models from Google DeepMind are available in Tess for fast, cost-efficient chat and agent workflows. This page covers **Gemini 3.6 Flash** (production workhorse) and **Gemini 3.5 Flash-Lite** (highest throughput / lowest cost in the 3.5 Flash class).

| **Family**<br /><br />Gemini Flash                                                           | **Provider**<br /><br />Google DeepMind | **Context**<br /><br />Up to 1M input | **Keys**<br /><br />`gemini-3.6-flash` · `gemini-3.5-flash-lite` |
| :------------------------------------------------------------------------------------------- | :-------------------------------------- | :------------------------------------ | :--------------------------------------------------------------- |
| **Capabilities**<br /><br /><Icon icon="brain" /><Icon icon="image" /><Icon icon="wrench" /> | **Speed**<br /><br />High               | **Cost**<br /><br />Low–Medium        | **Intelligence**<br /><br />Text + multimodal                    |

## When to use which

| Need                                                       | Recommended model         |
| ---------------------------------------------------------- | ------------------------- |
| Agentic coding and multi-step production workflows         | **Gemini 3.6 Flash**      |
| Knowledge work with better token efficiency                | **Gemini 3.6 Flash**      |
| Multimodal tasks (text + image + audio + video)            | **Gemini 3.6 Flash**      |
| High-volume search, extraction, translation, summarization | **Gemini 3.5 Flash-Lite** |
| Lowest cost / maximum response speed                       | **Gemini 3.5 Flash-Lite** |

### Gemini 3.6 Flash

* Stronger coding and knowledge-work quality with **lower verbosity** than 3.5 Flash (up to \~17% fewer output tokens on comparable tasks)
* Native multimodal: text, image, audio, and video
* Reasoning, tools (function calling / MCP), and computer-use support
* Large context for long-horizon agent workflows (1M input / up to 64K output)

### Gemini 3.5 Flash-Lite

* Fastest and most economical option in the Gemini 3.5 Flash class (up to \~350 output tokens/s)
* Configurable thinking levels: prioritize latency/cost or deeper reasoning
* Ideal as a cheap worker model in multi-agent pipelines

## Pricing (Tess credits)

Values follow [Models and Costs](/en/models-and-cost) (credits per 100 tokens):

| Model                 | Input / 100 tokens | Output / 100 tokens |
| --------------------- | ------------------ | ------------------- |
| Gemini 3.6 Flash      | 0.072              | 0.360               |
| Gemini 3.5 Flash-Lite | 0.0144             | 0.120               |

> **Screenshot placeholder — model picker:** Capture the chat model selector with **Gemini 3.6 Flash** and **Gemini 3.5 Flash-Lite** visible (and selected once each).

<Tip>
  **Best practices**

  * Prefer **3.6 Flash** for coding agents and complex multimodal jobs.
  * Prefer **3.5 Flash-Lite** for high-volume extraction, classification, and summarization.
  * Keep prompts tight — Flash models reward clear, scoped instructions and burn fewer tokens when you constrain output length.
</Tip>

See also: [Models and Costs](/en/models-and-cost) · Google DeepMind [Gemini Flash](https://deepmind.google/models/gemini/flash/).