How to Use GPT Luna Latest in opencode
Use GPT Luna Latest for focused tasks such as sorting requests, extracting details, and making scoped code changes. Unlike the named GPT-6 Luna model, it follows the latest Luna release, so retest recurring work when the target changes.
Prompts to try with GPT Luna Latest in opencode
Copy an example into opencode, or ask in your own words.
Use GPT Luna Latest to investigate the failing test in this project. Reproduce the failure, make the smallest justified fix, and report the tests you actually ran.
Use GPT Luna Latest to review the current diff for behavior changes. List concrete bugs with file locations and reproduction steps, and leave style preferences out.
Use GPT Luna Latest to add regression coverage for this bug using the project's existing test framework. Show that the test fails before the fix and passes afterward.
Use GPT Luna Latest to trace how this project validates incoming requests. Summarize the relevant functions and identify any branch that accepts malformed input.
Use GPT Luna Latest to draft release notes from the current diff. Group changes by user impact and include only behavior supported by the code.
How to set up GPT Luna Latest in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode 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 GPT Luna Latest
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-luna-latest", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: opencode finds GPT Luna Latest on Spiral, shows the price and runs it.
GPT Luna Latest providers and prices
Spiral runs GPT Luna Latest through OpenAI. Open a card for today's price, with every fee included.
Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 per 1M output tokens.
Settings you can ask for
Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | a number up to 1 | Taken only with reasoning effort "none". | |
| Logprobs | on or off | Taken only with reasoning effort "none". | |
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | Taken only with reasoning effort "none". | |
| Top logprobs | 0 to 20 | Taken only with reasoning effort "none". | |
| Presence penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Reasoning effort | none, low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Frequency penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Parallel tool calls | on or off |
Every API field of GPT Luna Latest is on its tool page: open its card above.
What can you do with GPT Luna Latest in opencode?
Turn reproducible failures into scoped patches, tests, and concise review notes with GPT Luna Latest. Give it the relevant project context and a clear acceptance condition for each change.
Support request triage
Use GPT Luna Latest to assign incoming requests to defined categories and flag messages that need human review. Include category definitions and an uncertain option.
Extract details from messages
Ask GPT Luna Latest to pull names, dates, requested actions, and reference numbers from supplied text. Require a supporting excerpt for each value.
Daily operations digest
Have GPT Luna Latest condense supplied updates into completed work, blockers, and next actions. Keep missing owners and deadlines explicit.
Scoped bug fixes
Give GPT Luna Latest a reproducible failure and ask for a small code change with a relevant regression test. Review the patch and test results before accepting it.
Turn notes into action items
Ask GPT Luna Latest to convert meeting text into decisions and tasks. Preserve the difference between an agreed action and a suggestion.
Draft answers from approved material
Use GPT Luna Latest to draft concise replies from supplied help text. Ask it to identify unanswered questions instead of filling gaps.
Review extracted records
Ask GPT Luna Latest to compare records with their source text and flag unsupported values, missing details, and contradictions for review.
More on GPT Luna Latest and opencode
Overview
GPT Luna Latest in other agents
Questions about GPT Luna Latest in opencode
Can opencode use GPT Luna Latest?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run GPT Luna Latest like any built-in tool.
How much does GPT Luna Latest cost in opencode?
Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need an OpenAI account to use GPT Luna Latest in opencode?
No. Spiral runs GPT Luna Latest 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 Luna Latest in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while GPT Luna Latest runs?
GPT Luna Latest runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.
What is GPT Luna Latest good for?
Start with focused, repeatable work: sorting requests, extracting details, and summarizing supplied text. These are practical applications of OpenAI's positioning of GPT-6 Luna for focused tasks at high volume.
Does GPT Luna Latest always mean the same model?
No. It follows the latest Luna release, and the current listing identifies GPT-6 Luna as its target. Retest representative tasks when that target changes.
How much text can GPT Luna Latest handle?
The current GPT-6 Luna target has a 1,050,000-token context window and a maximum output of 128,000 tokens. Reasoning also uses the output allowance, so leave room beyond the visible answer you want.
Which reasoning effort should I try?
Medium is GPT-6 Luna's default. As a practical starting point, try lower effort for straightforward extraction and higher effort for debugging or ambiguous decisions, then compare results on your actual examples.
How should I prompt GPT Luna Latest?
Give it one clear task, the source material, and a precise definition of a useful answer. Specify the length, required details, and what to do when information is missing.
Start using GPT Luna Latest in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


