> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Seed 2.0 Mini

> Latency-focused multimodal model with 256K context, four reasoning effort modes, and image/video understanding for high-concurrency use.

![Seed 2.0 Mini](https://media.empiriolabs.ai/model-logos/seed-2-0-mini.png)

[ByteDance](/providers/bytedance) · Text Generation

`POST /v1/chat/completions`

Latency-focused multimodal model with 256K context, four reasoning effort modes, and image/video understanding for high-concurrency use.

## At a glance

| Field               | Value                                                                                                                       |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| Model id            | `seed-2-0-mini`                                                                                                             |
| Model release date  | 2026-02-14                                                                                                                  |
| Input modalities    | Text, Image, Video, Document                                                                                                |
| Output modalities   | Text                                                                                                                        |
| Context window      | 256K                                                                                                                        |
| Weight precision    | -                                                                                                                           |
| Max output tokens   | 128,000                                                                                                                     |
| Region              | Malaysia                                                                                                                    |
| Features            | vision, reasoning, function_calling                                                                                         |
| Native inference    | No                                                                                                                          |
| New                 | No                                                                                                                          |
| Structured output   | JSON Schema                                                                                                                 |
| Batch API           | Available                                                                                                                   |
| Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/seed-2-0-mini:generateContent` |
| Alternate model ids | `bytedance/seed-2-mini`, `doubao-seed-2-mini`, `seed-2-0-mini-260215`, `seed-2-mini`                                        |

## Pricing

| Charge | Spec                    | Rate                             |
| ------ | ----------------------- | -------------------------------- |
| Input  | per 1M prompt tokens    | \<=128K \$0.12; 128K-256K \$0.24 |
| Output | per 1M generated tokens | \<=128K \$0.50; 128K-256K \$1.00 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "seed-2-0-mini", "messages": [{"role":"user","content":"Hello"}]}'
```

## Parameters

| Parameter           | Type    | Required | Default    | Description                                                                                                                                                              |
| ------------------- | ------- | -------- | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `temperature`       | number  | no       | `0.7`      | Sampling temperature · Range: 0 – 2                                                                                                                                      |
| `top_p`             | number  | no       | `0.9`      | Nucleus sampling · Range: 0 – 1                                                                                                                                          |
| `max_tokens`        | number  | no       | -          | Maximum output tokens. When omitted, the model's own default applies. · Range: 1 – 128000                                                                                |
| `frequency_penalty` | number  | no       | `0`        | Penalty for repeated tokens. >0 reduces repetition, \<0 encourages it. Not applied when web search is on or a document is attached. · Range: -2 – 2                      |
| `presence_penalty`  | number  | no       | `0`        | Penalty for new vs. seen tokens. >0 encourages new topics, \<0 encourages staying on topic. Not applied when web search is on or a document is attached. · Range: -2 – 2 |
| `stop`              | string  | no       | -          | Comma-separated stop sequences                                                                                                                                           |
| `enable_thinking`   | boolean | no       | true       | Enable deep thinking / reasoning mode.                                                                                                                                   |
| `reasoning_effort`  | enum    | no       | `"medium"` | Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely. · Allowed: `low`, `medium`, `high`                                                       |
| `enable_web_search` | boolean | no       | false      | Enable web search: retrieves live web results and provides them to the model as additional context.                                                                      |
| `max_tool_calls`    | number  | no       | `3`        | Max number of web search rounds the model can run in one request. · Range: 1 – 10                                                                                        |
| `image_detail`      | enum    | no       | `"high"`   | Image visual quality tier for vision input. · Allowed: `low`, `high`, `xhigh`                                                                                            |
| `video_fps`         | number  | no       | -          | Frames per second extracted from video input. · Range: 0.2 – 5                                                                                                           |
| `response_format`   | enum    | no       | -          | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.                                 |

## Notes

Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.

**Per-tool billing (`usage.tool_usage`)**

When this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:

```json
"usage": {
  "prompt_tokens": 123,
  "completion_tokens": 456,
  "cost_usd": 0.0042,
  "tool_usage": {"web_search": 3, "code_interpreter": 1}
}
```

The tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/seed-2-0-mini`.