How to Use Muse Ember in ChatGPT
Muse Ember handles focused coding tasks, routing, and document extraction. Choose it for repeated execution; Muse Spark and Muse Wonder are better choices for hard one-shot coding and knowledge-heavy questions.
Prompts to try with Muse Ember in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Muse Ember to classify the support tickets in this conversation as billing, bug, or feature request. Return a table with the ticket number, category, and one supporting excerpt.
Use Muse Ember to extract the parties, effective date, renewal date, and notice period from the contract text above. Include a supporting passage for each value and mark anything missing.
Use Muse Ember to summarize the report above in 300 words. Cover findings, decisions, and unanswered questions, with section references.
Use Muse Ember to route the requests above to support, sales, or engineering using the responsibility descriptions I supplied. Give one sentence explaining each choice and flag unclear cases.
Use Muse Ember to normalize the contact records above into a table with name, organization, and email. Follow the supplied formatting rules and leave unavailable information blank.
How to set up Muse Ember in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT 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 Muse Ember
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": "meta/muse-ember", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: ChatGPT finds Muse Ember on Spiral, shows the price and runs it.
Muse Ember providers and prices
Spiral runs Muse Ember through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens.
Settings you can ask for
Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 943718 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Temperature | 0 to 2 | ||
| Reasoning effort | minimal, low, medium, high, xhigh, or max | max | How much the model reasons. |
| Repetition penalty | 0 to 2 |
Every API field of Meta: Muse Ember is on its tool page: open its card above.
What can you do with Muse Ember in ChatGPT?
Turn supplied text into summaries, extracted records, and categorized requests with Muse Ember. Keep each request specific and state the structure you want back.
Focused code repairs
Give Muse Ember a failing check, the relevant code, and a narrow acceptance criterion. Ask for a targeted fix and the verification result.
Bounded code migrations
Use Muse Ember to port one function or module against a supplied reference and test suite. Define the interfaces and required behavior before requesting the change.
Support ticket classification
Have Muse Ember assign each ticket to a defined category and include a short supporting excerpt for review.
Request routing
Give Muse Ember the available handlers and their responsibilities. Ask it to select a destination for each incoming request and explain the selection briefly.
Document extraction
Ask Muse Ember to extract dates, names, obligations, or totals from supplied document text into a consistent JSON structure, with source references and missing values marked explicitly.
Document summaries
Use Muse Ember to summarize each supplied report with the same headings: findings, decisions, open questions, and supporting passages.
Record normalization
Have Muse Ember convert inconsistent text records into a defined structure. Supply normalization rules and require ambiguous entries to be flagged.
More on Muse Ember and ChatGPT
Overview
Muse Ember in other agents
Questions about Muse Ember in ChatGPT
Can ChatGPT use Muse Ember?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Muse Ember like any built-in tool.
How much does Muse Ember cost in ChatGPT?
Up to $0.002668 per run at the default inputs. $0.13 per 1M input 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 ChatGPT plan is separate.
Do I need an OpenRouter account to use Muse Ember in ChatGPT?
No. Spiral runs Muse Ember on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Muse Ember in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Muse Ember runs?
Muse Ember runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.
What is Muse Ember best suited for?
Use it for focused work you repeat: coding subtasks, request routing, document summaries, and extracting information into a consistent structure.
When should I choose Muse Spark or Muse Wonder instead?
Meta recommends them for hard one-shot coding problems, knowledge-heavy questions, and visual coding. Give Muse Ember a narrower task when the broader problem needs those capabilities.
How much text can Muse Ember handle?
Meta documents a 1,048,576-token context window and up to 524,288 output tokens. Internal reasoning also consumes the output budget, so that maximum is not a promise of an equally long visible answer.
Can Muse Ember return structured JSON?
Yes. Use schema-constrained output for extraction and classification tasks that need a consistent JSON structure.
How much reasoning should I use?
Start with the lowest effort that passes your task checks. Leave enough output budget for both internal reasoning and the answer you need.
Start using Muse Ember in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


