# Seed 2.0 Lite (260228)

> ByteDance Seed's enterprise multimodal and agent model, described by BytePlus as a practical default for production.

## Key facts

- Model author: ByteDance
- Input: $0.25 per 1M tokens (starting tier)
- Output: $2.00 per 1M tokens (starting tier)
- Cached input: $0.05 per 1M tokens
- Context window: 256,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, tools, vision
- Released: 2026-02-28
- Model IDs: `byteplus/seed-2-0-lite-260228`
- Model page: https://www.realrelay.ai/model/bytedance/seed-2-0-lite-260228

## Overview

Seed 2.0 Lite (260228) is a multimodal reasoning model from the ByteDance Seed team. BytePlus describes it as an enterprise workhorse that pairs strong multimodal and agent capabilities with noticeably lower latency, and as a practical default choice for most production workloads. It supports deep reasoning, tool calling and structured output.

It has a 256K-token context window and can generate up to 128K output tokens. It accepts text and image input and returns text. It was released on February 28, 2026.

## Capabilities

Seed 2.0 Lite (260228) supports reasoning, tool calling and vision. images can accompany a text prompt, and the reply comes back as text.

BytePlus also lists structured output, so responses can follow a defined format that downstream code can parse, alongside multimodal understanding and deep reasoning.

## Pricing

Seed 2.0 Lite (260228) is priced from $0.25 per 1M input tokens and from $2.00 per 1M output tokens. Pricing is tiered, so these figures are the starting tier. Cache reads are billed from $0.05 per 1M tokens.

Seed 2.0 Lite (260228) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Seed 2.0 Lite (260228) as the default model behind production assistants and agents that call tools, where its lower latency keeps multi-step interactions responsive.

Its image input and structured output also fit extraction jobs, such as reading an invoice or a screenshot and returning the fields as structured data for other systems.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "byteplus/seed-2-0-lite-260228", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Seed 2.0 Lite (260228)?

Seed 2.0 Lite (260228) is a multimodal reasoning model from the ByteDance Seed team, described by BytePlus as an enterprise workhorse with lower latency. It accepts text and image input and returns text.

### How much does Seed 2.0 Lite (260228) cost?

Seed 2.0 Lite (260228) is priced from $0.25 per 1M input tokens and from $2.00 per 1M output tokens, and the figures are the starting tier of tiered pricing. Cache reads are billed from $0.05 per 1M tokens.

### What is the context window of Seed 2.0 Lite (260228)?

Seed 2.0 Lite (260228) has a 256K-token context window and can generate up to 128K output tokens.

### What inputs and outputs does Seed 2.0 Lite (260228) support?

Seed 2.0 Lite (260228) accepts text and image input and returns text.

### Does Seed 2.0 Lite (260228) support structured output?

Yes. BytePlus lists structured output for Seed 2.0 Lite (260228), along with deep reasoning, multimodal understanding and tool calling.

### When was Seed 2.0 Lite (260228) released?

Seed 2.0 Lite (260228) was released on February 28, 2026.

### How do I call Seed 2.0 Lite (260228) via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID byteplus/seed-2-0-lite-260228 to use Seed 2.0 Lite (260228).