> ## Documentation Index
> Fetch the complete documentation index at: https://api-tools.memories.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Video Model Selection

> Choose the right video understanding model for your workload

Use this page when your request includes **video**. Memories.ai currently documents three video understanding providers: Gemini, Nova, and Qwen.

<Info>
  This is a selection guide for real API usage in Memories.ai. It focuses on request shape, output controls, and cost tradeoffs instead of benchmark leaderboards.
</Info>

## Quick Picks

<CardGroup cols={2}>
  <Card title="Best default" icon="brain" href="/visual-intelligence/gemini/gemini-vlm">
    Start with **Gemini Video** if you want one strong default for reasoning-heavy video analysis and structured extraction.
  </Card>

  <Card title="Lowest-cost batch" icon="bolt" href="/visual-intelligence/qwen/qwen-vlm">
    Start with **Qwen Video** if cost is the main constraint and you need large-scale or long-running video jobs.
  </Card>

  <Card title="Tool-first extraction" icon="wrench" href="/visual-intelligence/nova/nova-vlm">
    Start with **Nova Video** if your pipeline is designed around tool-style extraction via `toolConfig`.
  </Card>

  <Card title="Image-only task?" icon="code" href="/visual-intelligence/image-model-selection">
    If the task does not contain video, use the dedicated **Image Model Selection** guide instead.
  </Card>
</CardGroup>

## Choose By Workflow

| If your goal is...                                  | Start here                                                                                                 | Why                                                                                          |
| --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
| General-purpose video understanding                 | [Gemini Video](/visual-intelligence/gemini/gemini-vlm)                                                     | Best default for reasoning-heavy summaries, extraction, and mixed multimodal prompts         |
| Lowest-cost video analysis                          | [Qwen Video](/visual-intelligence/qwen/qwen-vlm)                                                           | Cheapest published starting price among the documented video providers                       |
| Tool-driven extraction pipeline                     | [Nova Video](/visual-intelligence/nova/nova-vlm)                                                           | The docs explicitly expose `toolConfig` for structured extraction through tool specs         |
| Schema-based structured output without tool calling | [Gemini Video](/visual-intelligence/gemini/gemini-vlm) or [Qwen Video](/visual-intelligence/qwen/qwen-vlm) | Both pages document schema-like structured output controls directly in the request body      |
| A single provider to try first before tuning        | [Gemini Video](/visual-intelligence/gemini/gemini-vlm)                                                     | Strongest default choice when you do not yet know the quality/cost boundary of your workload |

## Provider Differences That Matter

| Provider                                               | Documented input shape                                                       | Structured output path                            | Thinking control                      | When it usually fits best                                                         |
| ------------------------------------------------------ | ---------------------------------------------------------------------------- | ------------------------------------------------- | ------------------------------------- | --------------------------------------------------------------------------------- |
| [Gemini Video](/visual-intelligence/gemini/gemini-vlm) | `input_file` with `mime_type`; video does not support base64                 | `extra_body.metadata.responseSchema`              | `thinking_config.thinking_budget`     | Reasoning-heavy video analysis and multimodal prompts with image + video together |
| [Nova Video](/visual-intelligence/nova/nova-vlm)       | `video_url` plus text; tool config lives in `extra_body.metadata.toolConfig` | Tool-based extraction via `toolConfig`            | Not documented on this page           | Operational workflows that already expect tool-style outputs                      |
| [Qwen Video](/visual-intelligence/qwen/qwen-vlm)       | `video`, `image`, and `text` blocks in the same content array                | `extra_body.metadata.response_format.json_schema` | `enable_thinking` + `thinking_budget` | Lowest-cost batch analysis and explicit thinking toggles                          |

## Suggested Starting Models

| Scenario                                  | Recommended model               |
| ----------------------------------------- | ------------------------------- |
| Default video summary / extraction        | `gemini:gemini-3-flash-preview` |
| Cheapest first pass on large video volume | `qwen:qwen3-vl-flash`           |
| Tool-oriented extraction workflow         | `nova:us.amazon.nova-lite-v1:0` |

<Note>
  Qwen source pricing is documented per `1K` tokens on its provider pages. This guide converts the lowest published tier into `1M` token terms for faster cross-provider comparison.
</Note>

## How To Evaluate On Your Own Data

Before standardizing on a video model, compare at least these cases:

* short clips vs long videos
* narration-heavy videos vs mostly visual videos
* free-form summaries vs strict field extraction
* low-volume interactive requests vs batch processing

The winner often changes depending on whether you optimize for quality, cost, or output control.

## Not In Scope

* GPT is not currently documented as a video understanding endpoint in Memories.ai, so it is intentionally excluded from this page.
* This page does not freeze benchmark scores, RPM limits, or uptime claims because those numbers age quickly and may differ by provider account or region.

## Detailed Video Model Pages

* [Gemini Video](/visual-intelligence/gemini/gemini-vlm)
* [Nova Video](/visual-intelligence/nova/nova-vlm)
* [Qwen Video](/visual-intelligence/qwen/qwen-vlm)