How to Use GPT-5 Nano in Muse
GPT-5 Nano handles summaries, classification, and routine text extraction. It scored below GPT-5 Mini on OpenAI's long-context retrieval evaluation, so keep tasks focused and check extracted details.
Prompts to try with GPT-5 Nano in Muse
Copy an example into Muse, or ask in your own words.
Use GPT-5 Nano to summarize the meeting transcript in this conversation in 120 words. Then list decisions and action items, including an owner or deadline only when explicitly stated.
Use GPT-5 Nano with minimal reasoning to label each customer review in this conversation as positive, neutral, negative, or mixed. Return the review number, sentiment, and one supporting quote.
Use GPT-5 Nano to extract the order number, product name, and requested action from each customer message I shared. Return a table and write 'not stated' for missing details.
Use GPT-5 Nano to rewrite the notice above in plain English for a new customer. Keep all dates and conditions intact, and stay under 100 words.
Use GPT-5 Nano with minimal reasoning to classify the support messages above as billing, account access, bug report, or other. Assign one category per message and include a short phrase supporting the choice.
How to set up GPT-5 Nano in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse 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-5 Nano
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-nano", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse finds GPT-5 Nano on Spiral, shows the price and runs it.
GPT-5 Nano providers and prices
Spiral runs GPT-5 Nano through OpenAI. Open a card for today's price, with every fee included.
Up to $0.002134 per run at the default inputs. $0.065 per 1M input tokens, $0.0065 per 1M cached input tokens, $0.52 per 1M output tokens.
Settings you can ask for
Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Parallel tool calls | on or off |
Every API field of GPT-5 Nano is on its tool page: open its card above.
What can you do with GPT-5 Nano in Muse?
GPT-5 Nano can turn text you share into short recaps, consistent labels, and extracted details. Give it a clear output format and a focused source passage.
Support ticket classification
Assign incoming ticket text to billing, account access, bug report, or other. Define each label and request a supporting phrase for review.
Meeting recaps
Turn a supplied meeting transcript into a short recap with decisions and action items. Keep owners and deadlines tied to what participants actually said.
Order detail extraction
Extract order numbers, product names, and requested actions from customer messages into consistent records. Represent missing details explicitly.
Customer feedback labels
Classify reviews by sentiment and product topic. Preserve review IDs so people can trace each label to the original text.
Release note summaries
Condense supplied change descriptions into short release notes organized by fixes, features, and documentation.
Plain-language rewrites
Rewrite short notices for easier reading while preserving dates, names, and stated conditions. Specify the audience and target length.
Developer issue triage
Classify issue descriptions and summarize supplied failure logs. Return concise evidence for each category before a developer investigates.
More on GPT-5 Nano and Muse
Overview
GPT-5 Nano in other agents
More Muse guides
Questions about GPT-5 Nano in Muse
Can Muse use GPT-5 Nano?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run GPT-5 Nano like any built-in tool.
How much does GPT-5 Nano cost in Muse?
Up to $0.002134 per run at the default inputs. $0.065 per 1M input tokens, $0.0065 per 1M cached input tokens, $0.52 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need an OpenAI account to use GPT-5 Nano in Muse?
You need no OpenAI account. Muse uses one Spiral API key for every tool, and Spiral runs GPT-5 Nano on its own OpenAI account.
How long does it take to set up GPT-5 Nano in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while GPT-5 Nano runs?
GPT-5 Nano runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-5 Nano good at?
OpenAI recommends GPT-5 Nano for summarization and classification. Practical starting points include support ticket labels, short meeting recaps, and extracting named details from text.
How much text can GPT-5 Nano handle?
GPT-5 Nano has a 400,000-token context window and a maximum output allowance of 128,000 tokens. Internal reasoning also uses the output allowance, so visible answers can be shorter.
Does GPT-5 Nano know about recent events?
Its knowledge cutoff is May 31, 2024. For newer information, provide the relevant source text and ask it to answer from that material.
Can GPT-5 Nano return structured JSON?
Yes. Structured Outputs can enforce a supported JSON schema for completed responses that are not refusals, but you still need to check whether the extracted values are correct.
When should I use minimal reasoning?
Start with minimal reasoning for simple labels, extraction, formatting, and short rewrites. OpenAI advises against minimal reasoning for planning with multiple steps or workflows that depend heavily on tools.
Start using GPT-5 Nano in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


