[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Qwen3 14B](https://spiral.ai/integrations/openclaw/qwen3-14b)

# How to Use Qwen3 14B in OpenClaw

Qwen3 14B suits coding, math, and multilingual text work. It combines thinking for harder problems with a direct-answer mode for everyday conversation in one model.

|  |  |
| --- | --- |
| Model | Qwen3 14B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001285 per run at the default inputs. $0.156 per 1M input tokens, $0.312 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 14B in OpenClaw

- Each morning, use Qwen3 14B to organize the supplied customer messages by issue. Return the issue, supporting message IDs, and a draft reply under 80 words; flag missing details.
- Every weekday, use Qwen3 14B to translate the supplied English service announcement into Spanish and French. Preserve product names and dates, and flag phrases with ambiguous meaning.
- Each evening, use Qwen3 14B to extract decisions and assigned actions from the supplied meeting transcripts. Return one record per action and mark unstated owners or deadlines as unknown.
- Every Monday, use Qwen3 14B in thinking mode to check the supplied arithmetic word problems and answer keys. Report discrepancies with a corrected answer and a brief verification.
- Each afternoon, use Qwen3 14B in direct-answer mode to condense the supplied project updates into a 200-word brief. Include completed work, blockers, and unanswered questions, using only the supplied text.

## How to set up Qwen3 14B 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 Qwen3 14B**: 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": "qwen/qwen3-14b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Qwen3 14B on Spiral, shows the price and runs it.

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

## Qwen3 14B tools and prices

- [Qwen: Qwen3 14B](https://spiral.ai/tools/openrouter/qwen/qwen3-14b) (OpenRouter): Up to $0.001285 per run at the default inputs. $0.156 per 1M input tokens, $0.312 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with Qwen3 14B in OpenClaw?

Turn recurring batches of supplied text into structured records, translations, and concise briefs with Qwen3 14B. Keep each run focused by defining the evidence to use, the output length, and what to do when details are absent.

### Debug a failing function

Use Qwen3 14B to examine code and an error trace, propose a correction, and identify a test that would catch the defect.

### Check a mathematical solution

Give Qwen3 14B the problem and proposed solution. Ask it to check assumptions, recompute the result, and explain any discrepancy.

### Translate customer-facing text

Ask Qwen3 14B to translate a support reply while preserving product names, technical terms, and the requested tone.

### Extract structured records

Turn supplied messages into records with a defined structure. Specify which values to extract and how to represent missing information.

### Practice a difficult conversation

Have Qwen3 14B play a customer or interviewer, respond one turn at a time, and provide feedback after the exercise.

### Draft short creative scenes

Give Qwen3 14B a character, setting, and word limit. Request a scene with concrete constraints on dialogue, tone, and ending.

### Answer questions from supplied passages

Use Qwen3 14B to answer a focused question from text provided in the prompt. Require supporting excerpts and an explicit response when evidence is missing.

## Overview

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

## Qwen3 14B in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-14b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-14b)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-14b)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-14b)
- [Cline](https://spiral.ai/integrations/cline/qwen3-14b)
- [Codex](https://spiral.ai/integrations/codex/qwen3-14b)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-14b)
- [Devin](https://spiral.ai/integrations/devin/qwen3-14b)
- [dots](https://spiral.ai/integrations/dots/qwen3-14b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-14b)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-14b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-14b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-14b)
- [goose](https://spiral.ai/integrations/goose/qwen3-14b)
- [Grok](https://spiral.ai/integrations/grok/qwen3-14b)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-14b)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-14b)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-14b)
- [Manus](https://spiral.ai/integrations/manus/qwen3-14b)
- [Muse](https://spiral.ai/integrations/muse/qwen3-14b)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-14b)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-14b)
- [Notion](https://spiral.ai/integrations/notion/qwen3-14b)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-14b)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-14b)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-14b)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-14b)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-14b)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-14b)

## More OpenClaw guides

- [Qwen2.5-VL 72B Instruct](https://spiral.ai/integrations/openclaw/qwen2-5-vl-72b-instruct)
- [Qwen3 235B A22B Instruct 2507](https://spiral.ai/integrations/openclaw/qwen3-235b-a22b-instruct-2507)
- [Qwen2.5 Coder 32B Instruct](https://spiral.ai/integrations/openclaw/qwen2-5-coder-32b-instruct)
- [Qwen3 235B A22B Thinking 2507](https://spiral.ai/integrations/openclaw/qwen3-235b-a22b-thinking-2507)
- [Qwen2.5 72B Instruct](https://spiral.ai/integrations/openclaw/qwen2-5-72b-instruct)
- [Qwen3 30B A3B](https://spiral.ai/integrations/openclaw/qwen3-30b-a3b)

## Questions about Qwen3 14B in OpenClaw

**Can OpenClaw use Qwen3 14B?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Qwen3 14B like any built-in tool.

**How much does Qwen3 14B cost in OpenClaw?**

Up to $0.001285 per run at the default inputs. $0.156 per 1M input tokens, $0.312 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 Qwen3 14B in OpenClaw?**

No. Spiral runs Qwen3 14B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen3 14B in OpenClaw?**

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

**Does OpenClaw wait while Qwen3 14B runs?**

Qwen3 14B runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen3 14B useful for?**

Use it for coding, mathematical reasoning, multilingual text, and conversations with detailed instructions. It also supports creative writing and role-play.

**When should I use thinking mode?**

Choose thinking for problems with several reasoning steps, such as debugging or mathematical analysis. Use non-thinking mode for straightforward conversation and routine text work.

**How much context can Qwen3 14B handle?**

The model card specifies 32,768 tokens natively and 131,072 with YaRN extension. Treat the larger number as conditional on that extension being enabled.

**Can Qwen3 14B work across languages?**

Qwen reports support for 119 languages and dialects. Specify the target language, intended audience, and terms that should stay unchanged when requesting a translation.

**What can cause repetitive answers?**

Qwen warns that greedy decoding in thinking mode can cause performance degradation and endless repetition. Its recommended thinking settings use temperature 0.6, top-p 0.95, top-k 20, and min-p 0.

