How to Use Qwen3.5-9B in Manus
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.
Prompts to try with Qwen3.5-9B in Manus
Copy an example into Manus, or ask in your own words.
Use Qwen3.5-9B to compare the two policies pasted above. Make a table of changed obligations, quote the relevant passages, and flag anything the text leaves unclear.
Use Qwen3.5-9B to translate the support reply above into Mexican Spanish. Preserve product names, dates, and policy conditions, and use a polite, direct tone.
Use Qwen3.5-9B to turn the meeting transcript above into decisions, action items, and open questions. Include owners and deadlines only when explicitly stated.
Use Qwen3.5-9B to compare the three rollout plans above against the stated staffing and deadline constraints. Recommend one in under 300 words and identify the assumption most likely to change your recommendation.
Use Qwen3.5-9B to explain the code pasted above. Show one normal input and one boundary case, trace their results, and distinguish observed behavior from guesses about intent.
How to set up Qwen3.5-9B in Manus
Pick the way that suits you. Each takes about two minutes.
Use the Manus connector
- Add a custom MCP connector
In Manus open Settings › Connectors (or the connectors icon under the chat box), then Add connectors › Custom MCP and Add MCP by URL. Name it Spiral, set Transport to HTTP and paste this Server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Manus asks you to sign in the first time it uses Spiral. Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Manus never sees it, and you can remove it under Settings › Connected apps in the console.
Use the Spiral skill
- Send Manus this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Qwen3.5-9B
One request; the result comes back by polling or a webhook.
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: Manus finds Qwen3.5-9B on Spiral, shows the price and runs it.
Qwen3.5-9B providers and prices
Spiral runs Qwen3.5-9B through OpenRouter. Open a card for today's price, with every fee included.
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
Ask Manus for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 235929 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Qwen: Qwen3.5-9B is on its tool page: open its card above.
What can you do with Qwen3.5-9B in Manus?
Qwen3.5-9B can help you question supplied text, compare decisions, and draft across languages. State your audience and desired format so the answer has a clear purpose.
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.
More on Qwen3.5-9B and Manus
Overview
Qwen3.5-9B in other agents
Questions about Qwen3.5-9B in Manus
Can Manus use Qwen3.5-9B?
Yes. Add Spiral to Manus as an MCP server, and Manus can find and run Qwen3.5-9B like any built-in tool.
How much does Qwen3.5-9B cost in Manus?
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 Manus plan is separate.
Do I need an OpenRouter account to use Qwen3.5-9B in Manus?
No. Spiral runs Qwen3.5-9B on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen3.5-9B in Manus?
About two minutes: add a custom MCP connector, then sign in to Spiral and approve.
Does Manus wait while Qwen3.5-9B runs?
Qwen3.5-9B runs in the background. Manus 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.
Start using Qwen3.5-9B in Manus
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Manus:
set up https://spiral.ai/SKILL.md


