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

# Seed 2.0 Lite

> Balanced Seed 2.0 omnimodal model for production chat, video understanding, and lower-cost multimodal reasoning.

Seed 2.0 Lite 260428 is the current omnimodal Lite model for Chat Completions and Responses APIs.

It supports text, image, audio, and video input with text output, including video understanding through the Responses API.

## Model ID

```text theme={"dark"}
seed-2-0-lite-260428
```

Pass this exact public ID in the top-level `model` field. Do not substitute an upstream provider alias.

## Supported modes

* `chat_completions`
* `text_generation`
* `responses_api`
* `visual_understanding`

## Inputs

* `Text`
* `Image`
* `Audio`
* `Video`

## Outputs

* `Text`

## Capabilities

* `Chat completions`
* `Visual understanding`
* `Text generation`

### Additional capabilities

* `Model experience`
* `Structured output`
* `Online inference`
* `Streaming output`
* `Context caching`
* `Deep thinking`
* `Function call`
* `Web search`

## Technical details

| Property             | Value                             |
| -------------------- | --------------------------------- |
| Provider             | `byteplus-modelark`               |
| Modality             | `reasoning`                       |
| Processing           | `Synchronous response`            |
| Endpoint             | `/api/gengen/v1/chat/completions` |
| Rate limit           | `30K`                             |
| Context window       | `256K`                            |
| Max input tokens     | `224K`                            |
| Max output tokens    | `128K`                            |
| Max reasoning tokens | `128K`                            |
| Token rate limit     | `1500K`                           |

<Note>
  Availability and final customer prices can change. Check the [Dashboard model catalog](https://gengen.farm/dashboard?section=models) before production use.
</Note>

See the [API reference overview](/api-reference/introduction) for authentication, request conventions, and response schemas.