[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Qwen3.5-9B](https://spiral.ai/integrations/instinct/qwen3-5-9b)

# How to Use Qwen3.5-9B in Instinct

Use Qwen3.5-9B for coding, document questions, and multilingual drafts. Artificial Analysis's March 2026 evaluation gave it an Intelligence Index score of 32, compared with 27 for Qwen3.5-4B.

|  |  |
| --- | --- |
| Model | Qwen3.5-9B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.000172 per run at the default inputs. $0.0286 per 1M input tokens, $0.0416 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Qwen3.5-9B in Instinct

- Each morning, use Qwen3.5-9B to summarize the supplied release announcements from the previous day. Group changes by product, retain source links, and omit claims without supporting text.
- Every hour, use Qwen3.5-9B to classify newly supplied support messages as access, billing, bug, feature request, or unclear. Include a short evidence excerpt and flag ambiguous cases for review.
- Each weekday, use Qwen3.5-9B to draft English summaries of the supplied Spanish and French customer feedback. Preserve named products and separate reported problems from requested features.
- Every Friday, use Qwen3.5-9B to compare this week's supplied project updates with last week's. Report changed deadlines, blockers, and decisions with supporting excerpts in fewer than 500 words.
- Each night, use Qwen3.5-9B to review newly supplied incident reports. Extract the stated cause, affected service, mitigation, and unresolved questions; mark absent details as unknown.

## How to set up Qwen3.5-9B in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

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

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Qwen3.5-9B**: 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/qwen3.5-9b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Qwen3.5-9B on Spiral, shows the price and runs it.

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

## Qwen3.5-9B tools and prices

- [Qwen: Qwen3.5-9B](https://spiral.ai/tools/openrouter/qwen/qwen3.5-9b) (OpenRouter): Up to $0.001339 per run at the default inputs. $0.221 per 1M input tokens, $0.325 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 Qwen3.5-9B in Instinct?

Qwen3.5-9B can turn recurring batches of text into reviewable summaries, classifications, and drafts. Define the evidence and output rules once so each run follows the same brief.

### Fix a reproducible bug

Ask Qwen3.5-9B to inspect the failing behavior, propose a small patch, and identify a regression test. Supply the relevant code and error output.

### Turn requirements into tests

Give Qwen3.5-9B a function contract and ask for normal cases, boundary cases, and invalid inputs with expected results.

### Answer questions about long documents

Ask Qwen3.5-9B to compare supplied policies or specifications and cite the passages behind each conclusion.

### Draft localized support replies

Ask Qwen3.5-9B to rewrite a supplied response for a named language and locale while preserving product terms and policy details.

### Extract records from text

Give Qwen3.5-9B messages or notes and request structured records with evidence excerpts and explicit missing values.

### Compare operational plans

Ask Qwen3.5-9B to compare proposed schedules or rollout plans against explicit constraints, then explain conflicts and unresolved assumptions.

## Overview

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

## Qwen3.5-9B in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-5-9b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-5-9b)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-5-9b)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-5-9b)
- [Cline](https://spiral.ai/integrations/cline/qwen3-5-9b)
- [Codex](https://spiral.ai/integrations/codex/qwen3-5-9b)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-5-9b)
- [Devin](https://spiral.ai/integrations/devin/qwen3-5-9b)
- [dots](https://spiral.ai/integrations/dots/qwen3-5-9b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-5-9b)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-5-9b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-5-9b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-5-9b)
- [goose](https://spiral.ai/integrations/goose/qwen3-5-9b)
- [Grok](https://spiral.ai/integrations/grok/qwen3-5-9b)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-5-9b)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-5-9b)
- [Manus](https://spiral.ai/integrations/manus/qwen3-5-9b)
- [Muse](https://spiral.ai/integrations/muse/qwen3-5-9b)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-5-9b)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-5-9b)
- [Notion](https://spiral.ai/integrations/notion/qwen3-5-9b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-5-9b)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-5-9b)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-5-9b)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-5-9b)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-5-9b)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-5-9b)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-5-9b)

## More Instinct guides

- [Qwen3.5-35B-A3B](https://spiral.ai/integrations/instinct/qwen3-5-35b-a3b)
- [Qwen3.5-Flash](https://spiral.ai/integrations/instinct/qwen3-5-flash)
- [Qwen3.5-27B](https://spiral.ai/integrations/instinct/qwen3-5-27b)
- [Qwen3.6 27B](https://spiral.ai/integrations/instinct/qwen3-6-27b)
- [Qwen3.5-122B-A10B](https://spiral.ai/integrations/instinct/qwen3-5-122b-a10b)
- [Qwen3.6 35B A3B](https://spiral.ai/integrations/instinct/qwen3-6-35b-a3b)

## Questions about Qwen3.5-9B in Instinct

**Can Instinct use Qwen3.5-9B?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Qwen3.5-9B like any built-in tool.

**How much does Qwen3.5-9B cost in Instinct?**

Up to $0.000172 per run at the default inputs. $0.0286 per 1M input tokens, $0.0416 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an OpenRouter account to use Qwen3.5-9B in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Qwen3.5-9B on its own OpenRouter account.

**How long does it take to set up Qwen3.5-9B in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Qwen3.5-9B runs?**

Qwen3.5-9B runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What should I use Qwen3.5-9B for?**

Try bounded coding tasks, questions about supplied documents, and multilingual drafts. Give it the relevant source material and a clear definition of the finished answer.

**How much context can Qwen3.5-9B handle?**

Qwen documents a native context window of 262,144 tokens. Its documented extension to 1,010,000 tokens is separate from the native limit.

**How long should I let Qwen3.5-9B generate?**

Qwen recommends a 32,768-token output budget for most queries. That budget is guidance, not a required answer length or a stated maximum.

**Can Qwen3.5-9B work across languages?**

Alibaba reports support for 201 languages and dialects across Qwen3.5. For translation or localization, specify the target locale, audience, and terms to preserve.

**How does Qwen3.5-9B compare with Qwen3.5-4B?**

Artificial Analysis's March 2026 evaluation scored Qwen3.5-9B at 32 and Qwen3.5-4B at 27 on its Intelligence Index. Treat that as an overall benchmark comparison and test both on your actual task.

