How to Use Qwen3 Next 80B A3B Instruct in Devin
Use Qwen3 Next 80B A3B Instruct to work through long text, draft content, and generate code. Unlike Qwen3 Next 80B A3B Thinking, it operates only in non-thinking mode and produces no thinking blocks.
Prompts to try with Qwen3 Next 80B A3B Instruct in Devin
Copy an example into Devin, or ask in your own words.
Use Qwen3 Next 80B A3B Instruct to trace authentication through this project's source files. Return a table of entry points, validation functions, and error paths, with file references for each.
Use Qwen3 Next 80B A3B Instruct to investigate the failing test output and relevant source files. Propose the smallest fix, add a regression test, and run the relevant checks.
Use Qwen3 Next 80B A3B Instruct to compare this project's implementation with its specification. List discrepancies with file references and specification passages; separate confirmed differences from open questions.
Use Qwen3 Next 80B A3B Instruct to draft documentation for the public functions in this module. Include parameter descriptions, return values, and examples supported by the existing tests.
Use Qwen3 Next 80B A3B Instruct with temperature 0.7, top_p 0.8, and top_k 20 to review this patch. Return only actionable findings with a file reference, failure scenario, and suggested test.
How to set up Qwen3 Next 80B A3B Instruct in Devin
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add a custom MCP
Open Customize › MCPs. Click + and choose New MCP. Fill in:
- Sign in to Spiral and approve
In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.
- Check it
On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.
Use the Spiral skill
- Send Devin 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 Next 80B A3B Instruct
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-next-80b-a3b-instruct", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Devin finds Qwen3 Next 80B A3B Instruct on Spiral, shows the price and runs it.
Qwen3 Next 80B A3B Instruct providers and prices
Spiral runs Qwen3 Next 80B A3B Instruct through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.005863 per run at the default inputs. $0.13 per 1M input tokens, $1.43 per 1M output tokens.
Settings you can ask for
Ask Devin 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 16384 | 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 Next 80B A3B Instruct is on its tool page: open its card above.
What can you do with Qwen3 Next 80B A3B Instruct in Devin?
Turn project code and lengthy specifications into explanations, proposed patches, and review notes with Qwen3 Next 80B A3B Instruct. Give it a bounded task and a clear response format, then verify proposed changes with the project's checks.
Compare lengthy specifications
Ask Qwen3 Next 80B A3B Instruct to compare supplied specifications, identify conflicting requirements, and return a table with supporting passages.
Explain unfamiliar code
Give Qwen3 Next 80B A3B Instruct related source files and ask it to trace a request through the code, naming the functions involved and questions that need investigation.
Draft focused code changes
Ask Qwen3 Next 80B A3B Instruct for a small bug fix with regression tests, then review the patch and run the tests.
Turn research notes into a brief
Have Qwen3 Next 80B A3B Instruct organize supplied notes into a brief with findings, supporting evidence, and unanswered questions.
Rewrite technical explanations
Ask Qwen3 Next 80B A3B Instruct to rewrite a technical passage for a specific audience while preserving terminology, numbers, and stated limitations.
Review multilingual support text
Use Qwen3 Next 80B A3B Instruct to draft summaries of multilingual support conversations, preserving product names and flagging uncertain interpretations for review.
Summarize tool results
Ask Qwen3 Next 80B A3B Instruct to combine retrieved passages or tool results into an answer that identifies its evidence and missing information.
More on Qwen3 Next 80B A3B Instruct and Devin
Overview
Qwen3 Next 80B A3B Instruct in other agents
Questions about Qwen3 Next 80B A3B Instruct in Devin
Can Devin use Qwen3 Next 80B A3B Instruct?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Qwen3 Next 80B A3B Instruct like any built-in tool.
How much does Qwen3 Next 80B A3B Instruct cost in Devin?
Up to $0.005862 per run at the default inputs. $0.117 per 1M input tokens, $1.43 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Devin plan is separate.
Do I need an OpenRouter account to use Qwen3 Next 80B A3B Instruct in Devin?
No. Spiral runs Qwen3 Next 80B A3B Instruct 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 Next 80B A3B Instruct in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Qwen3 Next 80B A3B Instruct runs?
Qwen3 Next 80B A3B Instruct runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3 Next 80B A3B Instruct useful for?
Consider it for analyzing long text, drafting and rewriting content, generating code, and multilingual text work. Those are suggested applications based on its documented context capacity and published evaluations.
Does Qwen3 Next 80B A3B Instruct have a thinking mode?
No. It operates only in non-thinking mode and does not generate thinking blocks.
How much text can Qwen3 Next 80B A3B Instruct handle?
Its native context capacity is 262,144 tokens. The documentation recommends an output length of 16,384 tokens for most queries; that is separate from the context capacity.
Which generation settings should I start with?
The published generation configuration uses temperature 0.7, top-p 0.8, and top-k 20. Use these as a starting point when comparing results on your own tasks.
How should I ask for a consistent response format?
State the required structure in the prompt, such as a table with named columns or JSON with specified keys. Qwen recommends using prompts to standardize outputs when benchmarking.
Start using Qwen3 Next 80B A3B Instruct in Devin
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Devin:
set up https://spiral.ai/SKILL.md


