[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Palmyra X5](https://spiral.ai/integrations/openclaw/palmyra-x5)

# How to Use Palmyra X5 in OpenClaw

Palmyra X5 suits document-heavy work: summarizing research, classifying feedback, and drafting reports from supplied evidence. Its 1 million token context window accommodates long inputs, while each response is capped at 8,192 tokens.

|  |  |
| --- | --- |
| Model | Palmyra X5 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.031977 per run at the default inputs. $0.78 per 1M input tokens, $7.80 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Palmyra X5 in OpenClaw

- Every weekday, use Palmyra X5 to summarize the customer comments supplied for that day. Use low randomness and return the five main themes with comment IDs and representative quotations.
- Each morning, use Palmyra X5 to classify the supplied support requests using our approved categories and urgency rules. Include a supporting excerpt for each decision and flag ambiguous requests for review.
- Every Friday, use Palmyra X5 to compare the supplied help article text against this week's approved product updates. Return proposed corrections with supporting evidence for an editor to review.
- Each week, use Palmyra X5 to summarize the supplied research abstracts into a 500-word product research brief. Group related findings, identify disagreements, and retain the source IDs.
- At month end, use Palmyra X5 to draft a report from the supplied financial commentary and results. Reference the source for every figure and list missing information separately.

## How to set up Palmyra X5 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 Palmyra X5**: 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": "writer/palmyra-x5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Palmyra X5 on Spiral, shows the price and runs it.

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

## Palmyra X5 tools and prices

- [Writer: Palmyra X5](https://spiral.ai/tools/openrouter/writer/palmyra-x5) (OpenRouter): Up to $0.031977 per run at the default inputs. $0.78 per 1M input tokens, $7.80 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 8192 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Palmyra X5 in OpenClaw?

Produce recurring feedback summaries and content review queues from newly supplied text with Palmyra X5. Define the reporting period, classification rules, and evidence requirements so each run has a clear deliverable.

### Customer feedback reports

Use Palmyra X5 to organize survey responses by theme and sentiment. Request representative quotations and response IDs so each finding can be checked.

### Research summaries

Give Palmyra X5 the text of several technical reports or research papers. Ask for shared findings, disagreements, and unanswered questions with source references.

### Contract review preparation

Ask Palmyra X5 to extract obligations, deadlines, and clauses needing review from contract text. Keep the source passage beside each extracted item for the reviewer.

### Financial reporting drafts

Use Palmyra X5 to summarize supplied annual reports and market research into an executive brief. Require a source reference for every figure and separate reported results from interpretation.

### Support request triage

Ask Palmyra X5 to classify incoming support text using your categories and urgency rules. Include an evidence excerpt and send ambiguous requests for review.

### Knowledge base refreshes

Give Palmyra X5 current product information alongside existing article text. Request proposed corrections and a reason for each edit.

### Multilingual business drafts

Use Palmyra X5 to draft support replies or product explanations in a supported language. Supply the audience, approved terminology, and examples of the desired dialect.

### Code generation

Ask Palmyra X5 to draft scripts from explicit requirements and sample inputs. Request validation cases, then run and review the generated code.

## Overview

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

## Palmyra X5 in other agents

- [Amp](https://spiral.ai/integrations/amp/palmyra-x5)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/palmyra-x5)
- [Claude](https://spiral.ai/integrations/claude-desktop/palmyra-x5)
- [Claude Code](https://spiral.ai/integrations/claude-code/palmyra-x5)
- [Cline](https://spiral.ai/integrations/cline/palmyra-x5)
- [Codex](https://spiral.ai/integrations/codex/palmyra-x5)
- [Cursor](https://spiral.ai/integrations/cursor/palmyra-x5)
- [Devin](https://spiral.ai/integrations/devin/palmyra-x5)
- [dots](https://spiral.ai/integrations/dots/palmyra-x5)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/palmyra-x5)
- [Gemini](https://spiral.ai/integrations/gemini/palmyra-x5)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/palmyra-x5)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/palmyra-x5)
- [goose](https://spiral.ai/integrations/goose/palmyra-x5)
- [Grok](https://spiral.ai/integrations/grok/palmyra-x5)
- [Grok Build](https://spiral.ai/integrations/grok-build/palmyra-x5)
- [Hermes](https://spiral.ai/integrations/hermes/palmyra-x5)
- [Instinct](https://spiral.ai/integrations/instinct/palmyra-x5)
- [Manus](https://spiral.ai/integrations/manus/palmyra-x5)
- [Muse](https://spiral.ai/integrations/muse/palmyra-x5)
- [Muse Code](https://spiral.ai/integrations/muse-code/palmyra-x5)
- [n8n](https://spiral.ai/integrations/n8n/palmyra-x5)
- [Notion](https://spiral.ai/integrations/notion/palmyra-x5)
- [opencode](https://spiral.ai/integrations/opencode/palmyra-x5)
- [Perplexity](https://spiral.ai/integrations/perplexity/palmyra-x5)
- [Raycast](https://spiral.ai/integrations/raycast/palmyra-x5)
- [VS Code](https://spiral.ai/integrations/vscode/palmyra-x5)
- [Windsurf](https://spiral.ai/integrations/windsurf/palmyra-x5)
- [Zapier](https://spiral.ai/integrations/zapier/palmyra-x5)

## More OpenClaw guides

- [Nex-N2.6](https://spiral.ai/integrations/openclaw/nex-n2-6)
- [Pareto 26.10](https://spiral.ai/integrations/openclaw/pareto-26-10)
- [Nex-N2.5-Pro](https://spiral.ai/integrations/openclaw/nex-n2-5-pro)
- [Pareto 26.10 Preview](https://spiral.ai/integrations/openclaw/pareto-26-10-preview)
- [Nex-N2.5 Mini](https://spiral.ai/integrations/openclaw/nex-n2-5-mini)
- [Pareto 26.9](https://spiral.ai/integrations/openclaw/pareto-26-9)

## Questions about Palmyra X5 in OpenClaw

**Can OpenClaw use Palmyra X5?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Palmyra X5 like any built-in tool.

**How much does Palmyra X5 cost in OpenClaw?**

Up to $0.031977 per run at the default inputs. $0.78 per 1M input tokens, $7.80 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 Palmyra X5 in OpenClaw?**

No. Spiral runs Palmyra X5 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Palmyra X5 in OpenClaw?**

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

**Does OpenClaw wait while Palmyra X5 runs?**

Palmyra X5 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Palmyra X5 best suited for?**

Use it to turn large amounts of supplied text into reports, summaries, classifications, and drafts. Documented uses include customer feedback analysis, research synthesis, financial reporting, and legal document analysis.

**How much text can Palmyra X5 handle?**

Its context window is approximately 1 million tokens, and its maximum response is 8,192 tokens. For a long deliverable, request an outline first and draft individual sections in follow-up requests.

**Can Palmyra X5 write in languages other than English?**

Yes. WRITER documents more than 30 languages, including Spanish, French, Arabic, Hindi, and Chinese. For a specific dialect, write the prompt in that language and dialect.

**Can Palmyra X5 generate code and JSON?**

Yes, it supports code generation and structured outputs. When requesting JSON, specify the expected structure and check the result before using it.

**Which temperature should I use?**

Use a lower temperature for classification, extraction, and questions about supplied evidence. Use a higher temperature when you want more varied content or ideas.

