[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Morph V3 Large (batch)](https://spiral.ai/integrations/openclaw/morph-v3-large-batch)

# How to Use Morph V3 Large (batch) in OpenClaw

Morph V3 Large merges prepared code edits into complete source files, including changes across several functions. Compared with Morph V3 Fast, it targets complex changes where merge accuracy matters most.

|  |  |
| --- | --- |
| Model | Morph V3 Large (batch) |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.00508 per run at the default inputs. $0.585 per 1M input tokens, $1.235 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Morph V3 Large (batch) in OpenClaw

- Every morning, use Morph V3 Large to process approved bug-fix entries in the code-update queue. For each entry, merge its complete original source and prepared update, then retain the merged result and a comparison for review.
- Each night, use Morph V3 Large to merge approved helper-renaming updates from the queue. Process each original source listing separately and preserve every section marked as existing code.
- Every weekday, use Morph V3 Large to apply approved error-handling updates supplied as original source and edit snippets. Use temperature zero and flag unexpected removals in the comparison.
- Once a week, use Morph V3 Large to merge reviewed dependency-migration entries. Each entry must include complete original source, replacement imports and calls, and markers for untouched sections.
- Each evening, use Morph V3 Large to process approved obsolete-code removals. Require surrounding context for each deletion and retain the complete merged result for review.

## How to set up Morph V3 Large (batch) 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 Morph V3 Large (batch)**: 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": "morph/morph-v3-large:batch",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Morph V3 Large (batch) on Spiral, shows the price and runs it.

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

## Morph V3 Large (batch) tools and prices

- [Morph: Morph V3 Large (batch)](https://spiral.ai/tools/openrouter/morph/morph-v3-large%3Abatch) (OpenRouter): Up to $0.00508 per run at the default inputs. $0.585 per 1M input tokens, $1.235 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| logprobs |  | — |  |
| max_tokens | 1 to 131072 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |
| temperature | 0 to 2 | — |  |
| top_logprobs | 0 to 20 | — |  |
| response_format |  | — |  |

## What can you do with Morph V3 Large (batch) in OpenClaw?

Process queued source updates on a schedule with Morph V3 Large. Give each merge the complete original source and a prepared edit, then retain the result for review.

### Apply a reviewed bug fix

Merge an approved correction into existing source, then inspect the resulting diff for unrelated changes.

### Update several functions together

Apply a prepared refactor that changes a helper and its callers in the same source file.

### Add error handling

Merge prepared checks and error branches into existing request handlers while marking untouched sections for preservation.

### Apply a dependency migration

Merge reviewed import changes and replacement method calls into the current source.

### Remove obsolete code

Apply a prepared deletion with surrounding context that identifies the obsolete function and the code to retain.

### Merge changes into repetitive code

Supply the complete source and enough local context to distinguish the intended handler from similar handlers.

## Overview

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

## Morph V3 Large (batch) in other agents

- [Amp](https://spiral.ai/integrations/amp/morph-v3-large-batch)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/morph-v3-large-batch)
- [Claude](https://spiral.ai/integrations/claude-desktop/morph-v3-large-batch)
- [Claude Code](https://spiral.ai/integrations/claude-code/morph-v3-large-batch)
- [Cline](https://spiral.ai/integrations/cline/morph-v3-large-batch)
- [Codex](https://spiral.ai/integrations/codex/morph-v3-large-batch)
- [Cursor](https://spiral.ai/integrations/cursor/morph-v3-large-batch)
- [Devin](https://spiral.ai/integrations/devin/morph-v3-large-batch)
- [dots](https://spiral.ai/integrations/dots/morph-v3-large-batch)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/morph-v3-large-batch)
- [Gemini](https://spiral.ai/integrations/gemini/morph-v3-large-batch)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/morph-v3-large-batch)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/morph-v3-large-batch)
- [goose](https://spiral.ai/integrations/goose/morph-v3-large-batch)
- [Grok](https://spiral.ai/integrations/grok/morph-v3-large-batch)
- [Grok Build](https://spiral.ai/integrations/grok-build/morph-v3-large-batch)
- [Hermes](https://spiral.ai/integrations/hermes/morph-v3-large-batch)
- [Instinct](https://spiral.ai/integrations/instinct/morph-v3-large-batch)
- [Manus](https://spiral.ai/integrations/manus/morph-v3-large-batch)
- [Muse](https://spiral.ai/integrations/muse/morph-v3-large-batch)
- [Muse Code](https://spiral.ai/integrations/muse-code/morph-v3-large-batch)
- [n8n](https://spiral.ai/integrations/n8n/morph-v3-large-batch)
- [Notion](https://spiral.ai/integrations/notion/morph-v3-large-batch)
- [opencode](https://spiral.ai/integrations/opencode/morph-v3-large-batch)
- [Perplexity](https://spiral.ai/integrations/perplexity/morph-v3-large-batch)
- [Raycast](https://spiral.ai/integrations/raycast/morph-v3-large-batch)
- [VS Code](https://spiral.ai/integrations/vscode/morph-v3-large-batch)
- [Windsurf](https://spiral.ai/integrations/windsurf/morph-v3-large-batch)
- [Zapier](https://spiral.ai/integrations/zapier/morph-v3-large-batch)

## More OpenClaw guides

- [Morph V3 Large](https://spiral.ai/integrations/openclaw/morph-v3-large)
- [Motif 3](https://spiral.ai/integrations/openclaw/motif-3)
- [Morph V3 Fast Batch](https://spiral.ai/integrations/openclaw/morph-v3-fast-batch)
- [Muse Ember](https://spiral.ai/integrations/openclaw/muse-ember)
- [Morph V3 Fast](https://spiral.ai/integrations/openclaw/morph-v3-fast)
- [Muse Glimmer 30B](https://spiral.ai/integrations/openclaw/muse-glimmer-30b)

## Questions about Morph V3 Large (batch) in OpenClaw

**Can OpenClaw use Morph V3 Large (batch)?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Morph V3 Large (batch) like any built-in tool.

**How much does Morph V3 Large (batch) cost in OpenClaw?**

Up to $0.00508 per run at the default inputs. $0.585 per 1M input tokens, $1.235 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 Morph V3 Large (batch) in OpenClaw?**

No. Spiral runs Morph V3 Large (batch) on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Morph V3 Large (batch) in OpenClaw?**

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

**Does OpenClaw wait while Morph V3 Large (batch) runs?**

Morph V3 Large (batch) runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Morph V3 Large good at?**

It applies prepared changes to existing source code and returns the complete merged result. Its intended work includes complex edits across several functions or scopes.

**How does Morph V3 Large differ from Morph V3 Fast?**

Morph positions Large for complex changes and highest merge accuracy. Fast targets quick edits.

**Can Morph V3 Large plan a feature from scratch?**

Its documented role is applying edits after a planning model decides what to change. Use a planning model to design the feature, then supply the original source and prepared update.

**How much code can Morph V3 Large handle?**

The listed batch model has a 262,144-token context window and supports up to 131,072 output tokens. Budget for the complete merged source when choosing an output limit.

**How do I keep unchanged code from being deleted?**

Place `// ... existing code ...` markers wherever an update skips code that should remain. Include enough surrounding source to identify the intended edit location.

