[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Seed 2.0 Mini](https://spiral.ai/integrations/openclaw/seed-2-0-mini)

# How to Use Seed 2.0 Mini in OpenClaw

Seed 2.0 Mini suits repeated tasks such as classifying requests, extracting details, and drafting short responses. Compared with Seed 2.0 Pro, it emphasizes throughput over long-chain reasoning and complex workflows.

|  |  |
| --- | --- |
| Model | Seed 2.0 Mini |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.002135 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seed 2.0 Mini in OpenClaw

- Every morning, use Seed 2.0 Mini to summarize the status updates received since the previous run. Return completed work, blockers, and next actions, with a source reference for each.
- Every hour, use Seed 2.0 Mini with light reasoning to label new support requests as access, billing question, product issue, or unclear. Include the request ID and send unclear cases to the review queue.
- Each afternoon, use Seed 2.0 Mini to extract promised follow-up dates from today's customer conversations. Include the conversation reference and exact supporting sentence; mark unstated dates as missing.
- Each Friday, use Seed 2.0 Mini to organize the week's customer feedback into the approved topic categories. Include comment counts and representative excerpts, and keep uncategorized feedback separate.
- Each evening, use Seed 2.0 Mini to draft responses to unanswered product questions using the supplied help-center excerpts. Keep each draft under 100 words and flag questions without enough evidence.

## How to set up Seed 2.0 Mini in OpenClaw

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send OpenClaw this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Seed 2.0 Mini**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "bytedance-seed/seed-2.0-mini",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Seed 2.0 Mini on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/openclaw

## Seed 2.0 Mini tools and prices

- [ByteDance Seed: Seed-2.0-Mini](https://spiral.ai/tools/openrouter/bytedance-seed/seed-2.0-mini) (OpenRouter): Up to $0.002135 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 131072 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Seed 2.0 Mini in OpenClaw?

Process recurring batches of updates, requests, and comments with Seed 2.0 Mini. Keep the categories and output format consistent, and route uncertain results to review.

### Support request triage

Use Seed 2.0 Mini to assign incoming requests to a fixed set of categories. Include labeled examples and send ambiguous requests to review.

### Extract details from text

Ask Seed 2.0 Mini to pull dates, organizations, commitments, and requested actions from supplied messages. Require a supporting excerpt for each value.

### Daily activity summaries

Turn a batch of status updates into completed work, blockers, and next actions with Seed 2.0 Mini. Preserve the source reference beside each item.

### Grounded support drafts

Give Seed 2.0 Mini a customer question and relevant policy excerpts to draft a short reply. Require human review when the policy leaves a gap.

### Consistent text rewrites

Use Seed 2.0 Mini to rewrite short descriptions to a defined length and tone. Supply an approved example and require it to preserve factual details.

### Small code maintenance tasks

Try Seed 2.0 Mini on a narrowly scoped bug fix, helper function, or test update. Require verification against the project's existing tests.

### Document comparison

Ask Seed 2.0 Mini to compare supplied document text and list changed requirements, deadlines, and responsibilities. Request excerpts from both versions for each difference.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All OpenClaw guides](https://spiral.ai/integrations/openclaw)

## Seed 2.0 Mini in other agents

- [Amp](https://spiral.ai/integrations/amp/seed-2-0-mini)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/seed-2-0-mini)
- [Claude](https://spiral.ai/integrations/claude-desktop/seed-2-0-mini)
- [Claude Code](https://spiral.ai/integrations/claude-code/seed-2-0-mini)
- [Cline](https://spiral.ai/integrations/cline/seed-2-0-mini)
- [Codex](https://spiral.ai/integrations/codex/seed-2-0-mini)
- [Cursor](https://spiral.ai/integrations/cursor/seed-2-0-mini)
- [Devin](https://spiral.ai/integrations/devin/seed-2-0-mini)
- [dots](https://spiral.ai/integrations/dots/seed-2-0-mini)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/seed-2-0-mini)
- [Gemini](https://spiral.ai/integrations/gemini/seed-2-0-mini)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/seed-2-0-mini)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/seed-2-0-mini)
- [goose](https://spiral.ai/integrations/goose/seed-2-0-mini)
- [Grok](https://spiral.ai/integrations/grok/seed-2-0-mini)
- [Grok Build](https://spiral.ai/integrations/grok-build/seed-2-0-mini)
- [Hermes](https://spiral.ai/integrations/hermes/seed-2-0-mini)
- [Instinct](https://spiral.ai/integrations/instinct/seed-2-0-mini)
- [Manus](https://spiral.ai/integrations/manus/seed-2-0-mini)
- [Muse](https://spiral.ai/integrations/muse/seed-2-0-mini)
- [Muse Code](https://spiral.ai/integrations/muse-code/seed-2-0-mini)
- [n8n](https://spiral.ai/integrations/n8n/seed-2-0-mini)
- [Notion](https://spiral.ai/integrations/notion/seed-2-0-mini)
- [opencode](https://spiral.ai/integrations/opencode/seed-2-0-mini)
- [Perplexity](https://spiral.ai/integrations/perplexity/seed-2-0-mini)
- [Raycast](https://spiral.ai/integrations/raycast/seed-2-0-mini)
- [VS Code](https://spiral.ai/integrations/vscode/seed-2-0-mini)
- [Windsurf](https://spiral.ai/integrations/windsurf/seed-2-0-mini)
- [Zapier](https://spiral.ai/integrations/zapier/seed-2-0-mini)

## More OpenClaw guides

- [Seed 2.0 Lite](https://spiral.ai/integrations/openclaw/seed-2-0-lite)
- [Seed 2.1 Turbo](https://spiral.ai/integrations/openclaw/seed-2-1-turbo)
- [Schematron V2 Turbo](https://spiral.ai/integrations/openclaw/schematron-v2-turbo)
- [Skyfall 36B V2](https://spiral.ai/integrations/openclaw/skyfall-36b-v2)
- [Schematron V2 Small](https://spiral.ai/integrations/openclaw/schematron-v2-small)
- [Solar Mini 4](https://spiral.ai/integrations/openclaw/solar-mini-4)

## Questions about Seed 2.0 Mini in OpenClaw

**Can OpenClaw use Seed 2.0 Mini?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Seed 2.0 Mini like any built-in tool.

**How much does Seed 2.0 Mini cost in OpenClaw?**

Up to $0.002135 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

**Do I need an OpenRouter account to use Seed 2.0 Mini in OpenClaw?**

No. Spiral runs Seed 2.0 Mini on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Seed 2.0 Mini in OpenClaw?**

About two minutes: add the server, then sign in, then reload and check.

**Does OpenClaw wait while Seed 2.0 Mini runs?**

Seed 2.0 Mini runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Seed 2.0 Mini best suited for?**

Start with repeated, bounded tasks: sorting requests, extracting details, summarizing text, and drafting short replies. These are suggested applications of its emphasis on throughput and batch generation.

**When should I consider Seed 2.0 Pro instead?**

Consider Seed 2.0 Pro when long-chain reasoning and complex workflow reliability matter most. ByteDance positions Seed 2.0 Mini around throughput, so evaluate it on representative difficult cases before assigning it those tasks.

**How much text can Seed 2.0 Mini handle?**

The published 260215 specifications list a 256K-token context window, a 224K-token input limit, and up to 128K output tokens. The output allowance includes reasoning tokens, so it is not a promise of a 128K-token final answer.

**Which reasoning setting should I use?**

Start with low effort for straightforward extraction or labeling, and try medium or high for ambiguous decisions. Compare results on the same examples: higher effort is intended for deeper analysis, rather than quicker responses.

**How should I prompt Seed 2.0 Mini?**

State the task, supply the relevant context, and specify the answer format. Include examples for repeated tasks; with reasoning enabled, describe the goal and constraints and let the model choose its approach.

