# Seed 1.6 (250915)

> ByteDance Seed's general-purpose model with multimodal input, adaptive deep thinking and a long context window.

## 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: 32,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, tools, vision
- Released: 2025-09-15
- Model IDs: `byteplus/seed-1-6-250915`
- Model page: https://www.realrelay.ai/model/bytedance/seed-1-6-250915

## Overview

Seed 1.6 (250915) is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking, and BytePlus lists it with deep reasoning, image understanding, video understanding, structured output and function calling, so one model covers text, image and video tasks.

It has a 256K-token context window and can generate up to 32K output tokens. It accepts text, image and video input and returns text. It was released on September 15, 2025.

## Capabilities

Seed 1.6 (250915) supports reasoning, tool calling and vision. Its documented reasoning mode is adaptive deep thinking.

BytePlus lists image understanding, video understanding and structured output, so one request can mix text, images and video and return a structured answer.

## Pricing

Seed 1.6 (250915) 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 1.6 (250915) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Seed 1.6 (250915) as a general-purpose model for question answering over images and video, such as describing what happens in a clip or reading text in a photo.

Its function calling and structured output also fit workflow automation, where the model picks a tool, fills in its arguments and returns results in a defined format.

## 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-1-6-250915", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Seed 1.6 (250915)?

Seed 1.6 (250915) is a general-purpose model from the ByteDance Seed team with multimodal capabilities and adaptive deep thinking. It accepts text, image and video input and returns text.

### How much does Seed 1.6 (250915) cost?

Seed 1.6 (250915) 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 1.6 (250915)?

Seed 1.6 (250915) has a 256K-token context window and can generate up to 32K output tokens.

### What inputs and outputs does Seed 1.6 (250915) support?

Seed 1.6 (250915) accepts text, image and video input and returns text.

### Can Seed 1.6 (250915) understand video?

Yes. BytePlus lists video understanding and image understanding for Seed 1.6 (250915), and the model accepts text, image and video input.

### When was Seed 1.6 (250915) released?

Seed 1.6 (250915) was released on September 15, 2025.

### How do I call Seed 1.6 (250915) via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID byteplus/seed-1-6-250915 to use Seed 1.6 (250915).