How to Use Qwen3.8 27B in Devin
Qwen3.8 27B suits code changes, research synthesis, and tasks that require several rounds of decisions. Its 27-billion-parameter dense design combines adjustable thinking with a native 262,144-token context.
Prompts to try with Qwen3.8 27B in Devin
Copy an example into Devin, or ask in your own words.
Use Qwen3.8 27B to investigate the failing tests in this repository. Trace the failure through the relevant code, make the smallest justified fix, and run the affected tests.
Use Qwen3.8 27B to review the current diff for correctness bugs. For each finding, identify the file, triggering input, and resulting failure; omit style preferences.
Use Qwen3.8 27B to turn the requirements in this project's README into an implementation plan. Identify dependencies and missing acceptance criteria before proposing edits.
Use Qwen3.8 27B to examine this repository's request validation. Find one concrete case where invalid input reaches business logic, then propose a fix and a regression test.
Use Qwen3.8 27B to explain the authentication flow in this project. Follow the actual call path and cite the relevant files; mark any behavior you cannot establish from the code.
How to set up Qwen3.8 27B 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 Qwen3.8 27B
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/qwen3.8-27b", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Devin finds Qwen3.8 27B on Spiral, shows the price and runs it.
Qwen3.8 27B providers and prices
Spiral runs Qwen3.8 27B through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.60115 per run at the default inputs. $0.078 per 1M input tokens, $2.548 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 235929 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | none, low, medium, or xhigh | xhigh | How much the model reasons. |
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Qwen: Qwen3.8 27B is on its tool page: open its card above.
What can you do with Qwen3.8 27B in Devin?
Turn repository context into targeted fixes, reviews, and implementation plans with Qwen3.8 27B. Give the agent a reproducible failure or acceptance criteria so it has a concrete result to check.
Bug diagnosis
Give Qwen3.8 27B the failing behavior, relevant code, and error messages. Request a likely cause, a minimal correction, and a regression check.
Code review
Ask Qwen3.8 27B to review a proposed change for concrete failure paths. Require each finding to include the triggering condition and affected code.
Research comparison
Supply research excerpts and ask Qwen3.8 27B to compare claims, methods, and disagreements, with a source reference for each conclusion.
Requirements analysis
Have Qwen3.8 27B turn a product brief into acceptance criteria, dependencies, and unresolved questions.
Document synthesis
Use Qwen3.8 27B to combine supplied reports into a decision brief that separates evidence, assumptions, and missing information.
Incident review
Give Qwen3.8 27B a text timeline and logs. Request an evidence-based sequence of events and follow-up actions.
Recurring change reports
Ask Qwen3.8 27B to compare current and previous updates, identify material changes, and list decisions that need attention.
Technical explanations
Have Qwen3.8 27B explain supplied code or technical notes for a specific audience, using examples drawn from the source material.
More on Qwen3.8 27B and Devin
Overview
Qwen3.8 27B in other agents
Questions about Qwen3.8 27B in Devin
Can Devin use Qwen3.8 27B?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Qwen3.8 27B like any built-in tool.
How much does Qwen3.8 27B cost in Devin?
Up to $0.009992 per run at the default inputs. $0.195 per 1M input tokens, $2.4375 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 Qwen3.8 27B in Devin?
No. Spiral runs Qwen3.8 27B on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen3.8 27B in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Qwen3.8 27B runs?
Qwen3.8 27B runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3.8 27B useful for?
Consider it for code changes, research synthesis, and work that requires several decisions. Qwen highlights improvements in coding, professional work, research, and extended agent tasks.
How much context does Qwen3.8 27B support?
Its native context is 262,144 tokens. The documented extension to 1,000,000 tokens requires additional configuration, so treat that as an extended capability rather than the native limit.
When should I use thinking?
Use thinking for debugging, comparing evidence, or planning work with dependencies. Try direct answers for straightforward extraction and rewriting; Qwen3.8 27B supports both approaches.
What sampling settings should I start with?
The shipped configuration provides a starting point: temperature 1.0, top-p 0.95, and top-k 20. Compare results on representative tasks before changing several settings at once.
What weakness should I watch for when reducing repetition?
Aggressive repetition suppression can introduce mixed-language output and reduce quality. If that happens, reduce the repetition penalty before rewriting the whole prompt.
Start using Qwen3.8 27B 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


