# Seed 1.6 Flash (250715)

> ByteDance Seed's multimodal deep-thinking model for text, image and video understanding.

## Key facts

- Model author: ByteDance
- Input: $0.075 per 1M tokens (starting tier)
- Output: $0.30 per 1M tokens (starting tier)
- Cached input: $0.015 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: 2025-07-15
- Model IDs: `byteplus/seed-1-6-flash-250715`
- Model page: https://www.realrelay.ai/model/bytedance/seed-1-6-flash-250715

## Overview

Seed 1.6 Flash (250715) is a multimodal deep-thinking model from the ByteDance Seed team, which describes it as supporting both text and visual understanding. BytePlus lists it with deep reasoning, image understanding, video understanding, structured output and function calling. It handles text, image and video input in a single request.

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 July 15, 2025.

## Capabilities

Seed 1.6 Flash (250715) supports reasoning, tool calling and vision. images and video can accompany a text prompt, and the reply comes back as text.

Structured output and function calling are listed as supported, so it can return answers in a fixed format and call tools.

## Pricing

Seed 1.6 Flash (250715) is priced from $0.075 per 1M input tokens and from $0.30 per 1M output tokens. Pricing is tiered, so these figures are the starting tier. Cache reads are billed from $0.015 per 1M tokens.

Seed 1.6 Flash (250715) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Seed 1.6 Flash (250715) for responsive features that need visual understanding, such as captioning images, answering questions about video clips or routing requests with tool calls.

Its deep thinking mode is available when a task needs step-by-step reasoning, and structured output makes the results easy to pass to other services.

## 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-flash-250715", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Seed 1.6 Flash (250715)?

Seed 1.6 Flash (250715) is a multimodal deep-thinking model from the ByteDance Seed team that supports text and visual understanding. It accepts text, image and video input and returns text.

### How much does Seed 1.6 Flash (250715) cost?

Seed 1.6 Flash (250715) is priced from $0.075 per 1M input tokens and from $0.30 per 1M output tokens, and the figures are the starting tier of tiered pricing. Cache reads are billed from $0.015 per 1M tokens.

### What is the context window of Seed 1.6 Flash (250715)?

Seed 1.6 Flash (250715) has a 256K-token context window and can generate up to 32K output tokens.

### What inputs and outputs does Seed 1.6 Flash (250715) support?

Seed 1.6 Flash (250715) accepts text, image and video input and returns text.

### Does Seed 1.6 Flash (250715) support function calling?

Yes. BytePlus lists function calling and structured output for Seed 1.6 Flash (250715), in addition to deep reasoning and image and video understanding.

### When was Seed 1.6 Flash (250715) released?

Seed 1.6 Flash (250715) was released on July 15, 2025.

### How do I call Seed 1.6 Flash (250715) via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID byteplus/seed-1-6-flash-250715 to use Seed 1.6 Flash (250715).