How to Use Nemotron 3.5 Lightning in Devin
Nemotron 3.5 Lightning handles routine coding tasks, tool-result checks, and structured text extraction. Unlike Nemotron 3.5 Super, it works with text rather than images or video.
Prompts to try with Nemotron 3.5 Lightning in Devin
Copy an example into Devin, or ask in your own words.
Use Nemotron 3.5 Lightning to inspect the failing test and relevant source files, make the smallest justified fix, and run the affected tests.
Use Nemotron 3.5 Lightning to read the latest build log, identify the first actionable failure, and run one targeted diagnostic.
Use Nemotron 3.5 Lightning to compare this branch's code changes with the acceptance criteria and list unmet requirements with file references.
Use Nemotron 3.5 Lightning to extract the public functions from this module into JSON containing each function's name, arguments, and documented return value.
Use Nemotron 3.5 Lightning to compare the project's documentation with the current implementation and correct claims contradicted by the code.
How to set up Nemotron 3.5 Lightning 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 Nemotron 3.5 Lightning
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": "nvidia/nemotron-3.5-lightning", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Devin finds Nemotron 3.5 Lightning on Spiral, shows the price and runs it.
Nemotron 3.5 Lightning providers and prices
Spiral runs Nemotron 3.5 Lightning through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.001069 per run at the default inputs. $0.091 per 1M input tokens, $0.26 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 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of NVIDIA: Nemotron 3.5 Lightning is on its tool page: open its card above.
What can you do with Nemotron 3.5 Lightning in Devin?
Turn repository code, build logs, and tool results into focused fixes with Nemotron 3.5 Lightning. Use it for bounded implementation tasks with explicit checks.
Fix a reproducible bug
Use the failure report and relevant source code to draft a focused patch with a regression check.
Check tool results
Compare returned values with acceptance criteria and identify missing evidence before the next action.
Extract structured records
Turn support messages or operational notes into JSON with explicit rules for missing values.
Answer from retrieved passages
Draft answers from supplied knowledge-base excerpts and include the passage IDs supporting each conclusion.
Compare document revisions
Find changed requirements across text revisions and report the affected sections.
Prepare recurring operational digests
Summarize supplied status updates into completed work, blockers, and unresolved questions.
Draft multilingual support replies
Use supplied policy text to draft replies in English, Spanish, French, German, Italian, or Japanese.
Triage build failures
Read text logs, identify the first relevant failure, and suggest a targeted diagnostic check.
More on Nemotron 3.5 Lightning and Devin
Overview
Nemotron 3.5 Lightning in other agents
Questions about Nemotron 3.5 Lightning in Devin
Can Devin use Nemotron 3.5 Lightning?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Nemotron 3.5 Lightning like any built-in tool.
How much does Nemotron 3.5 Lightning cost in Devin?
Up to $0.001069 per run at the default inputs. $0.091 per 1M input tokens, $0.26 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 Nemotron 3.5 Lightning in Devin?
No. Spiral runs Nemotron 3.5 Lightning on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Nemotron 3.5 Lightning in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Nemotron 3.5 Lightning runs?
Nemotron 3.5 Lightning runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.
What is Nemotron 3.5 Lightning best suited for?
NVIDIA positions it for repeated execution tasks such as checking tool results and formatting responses. Give it a specific job with a clear completion condition.
How much context can Nemotron 3.5 Lightning handle?
NVIDIA documents up to 1 million tokens of context. For long material, ask a focused question and request references to the supporting passages.
Can Nemotron 3.5 Lightning analyze images or video?
Nemotron 3.5 Lightning is a text model. For visual source material, provide extracted text or a written description.
Which languages does Nemotron 3.5 Lightning support?
NVIDIA lists English, Spanish, French, German, Italian, and Japanese, alongside coding languages. State the desired response language in your prompt.
Which sampling settings should I start with?
NVIDIA recommends temperature 1.0 and top-p 0.95. Use those as a starting point when evaluating your task.
Start using Nemotron 3.5 Lightning 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


