Spiral gives your agent every tool with one account. Browse the tools →

Devin · LLMReleased 2026-07-09

How to Use GPT-5.6 Luna in Devin

GPT-5.6 Luna fits document extraction, code retrieval, and routine implementation. Choose it over GPT-5.6 Luna Pro for everyday work that does not need extra model work on difficult problems.

Prompts to try with GPT-5.6 Luna in Devin

Copy an example into Devin, or ask in your own words.

Use GPT-5.6 Luna to trace how this project handles an expired session. Identify the relevant functions and tests, cite file paths, and explain the flow in under 300 words.

GPT-5.6 LunaDevin
Try asking
  • Use GPT-5.6 Luna to fix the failing test in this project. Keep the change limited to the demonstrated bug, run the relevant tests, and report the result.

  • Use GPT-5.6 Luna to implement pagination for the existing list endpoint using the project's conventions. Add tests for the first page, an empty result, and an invalid cursor.

  • Ask GPT-5.6 Luna through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.

  • Get a second opinion from GPT-5.6 Luna on this function, then tell me what the call cost.

How to set up GPT-5.6 Luna in Devin

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

Use Spiral's MCP server

  1. Add a custom MCP

    Open Customize › MCPs. Click + and choose New MCP. Fill in:

  2. 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.

  3. Check it

    On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.

Use the Spiral skill

  1. Send Devin 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 the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run GPT-5.6 Luna

    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": "openai",
        "model": "openai/gpt-5.6-luna",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Devin finds GPT-5.6 Luna on Spiral, shows the price and runs it.

GPT-5.6 Luna providers and prices

Spiral runs GPT-5.6 Luna through OpenAI. Open a card for today's price, with every fee included.

OpenAILLM
GPT-5.6 Luna
openai/gpt-5.6-luna

Settings you can ask for

Ask Devin for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Top pa number up to 1

Taken only with reasoning effort "none".

Logprobson or off

Taken only with reasoning effort "none".

Max tokens16 to 128000

The most output tokens to generate.

Temperature0 to 2

Taken only with reasoning effort "none".

Top logprobs0 to 20

Taken only with reasoning effort "none".

Presence penalty-2 to 2

Taken only with reasoning effort "none".

Reasoning effortnone, low, medium, high, or xhighmedium

How much the model reasons.

Frequency penalty-2 to 2

Taken only with reasoning effort "none".

Parallel tool callson or off

Every API field of GPT-5.6 Luna is on its tool page: open its card above.

What can you do with GPT-5.6 Luna in Devin?

Turn a defined requirement into a code change with tests, or locate the code responsible for a reported behavior. GPT-5.6 Luna can handle scoped implementation and code retrieval when you provide acceptance criteria.

Extract renewal terms

Turn supplied contract text into a table of renewal dates, notice periods, and supporting passages. Mark missing terms explicitly.

Find code behind a behavior

Trace a reported behavior to relevant functions and tests. Request file references and a concise explanation of the execution path.

Implement a scoped change

Apply a clearly specified code change, add a regression test, and check the result against acceptance criteria.

Classify support conversations

Sort supplied conversations by issue type and urgency, preserving a supporting passage for each classification.

Compare policy revisions

Compare two supplied policy texts and list changed obligations, exceptions, and unresolved conflicts with section references.

Check a decision against evidence

Evaluate a proposed decision against supplied requirements and evidence. Request unmet conditions, conflicting evidence, and questions that would change the recommendation.

Questions about GPT-5.6 Luna in Devin

Can Devin use GPT-5.6 Luna?

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run GPT-5.6 Luna like any built-in tool.

How much does GPT-5.6 Luna cost in Devin?

Up to $0.006402 per run at the default inputs. $0.26 per 1M input tokens, $0.026 per 1M cached input tokens, $0.325 per 1M cache write tokens, $1.56 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 OpenAI account to use GPT-5.6 Luna in Devin?

No. Spiral runs GPT-5.6 Luna on its own OpenAI account. You sign in to Spiral once and never paste a key.

How long does it take to set up GPT-5.6 Luna in Devin?

About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.

Does Devin wait while GPT-5.6 Luna runs?

GPT-5.6 Luna runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.

What is GPT-5.6 Luna good at?

Document extraction, code retrieval, customer-interaction classification, and well-specified implementation are supported uses. Give it a defined task and an output you can check.

What does GPT-5.6 Luna Pro change?

It uses the same underlying model as GPT-5.6 Luna with pro reasoning mode. That mode applies extra model work to difficult tasks; reasoning effort remains a separate control.

How much text can GPT-5.6 Luna handle?

OpenAI documents a 1,050,000-token context window, with up to 922,000 input tokens and 128,000 generated tokens. Reasoning consumes part of the generated-token budget, so that maximum does not promise an equally long visible answer.

How should I prompt GPT-5.6 Luna?

State the task directly, supply the relevant material, and define what a successful answer must contain. Specify constraints such as length, required evidence, and how to handle missing information.

Which tasks deserve more reasoning?

Test extra reasoning on difficult tasks that require exploring alternatives, running checks, or revising an approach. Use representative examples to judge whether the extra work improves the result.

Get started

Start using GPT-5.6 Luna in Devin

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Devin:

Set up Devin

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options