How to Use Inkling Small in Muse
Inkling Small suits coding tasks, tool use, and reasoning through detailed instructions. In the maker’s tests, it surpassed Inkling on reasoning and agentic coding, while Inkling retained better knowledge coverage and factuality.
Prompts to try with Inkling Small in Muse
Copy an example into Muse, or ask in your own words.
Use Inkling Small to explain the error message and code I pasted above. Identify the likely cause, suggest a correction, and show an input that would test it.
Use Inkling Small to compare these two proposals against the stated requirements. Return a table of tradeoffs and list the unanswered questions.
Use Inkling Small with more thinking effort to check my mathematical solution. Find the first incorrect step, explain why it fails, and give a corrected solution.
Use Inkling Small to rewrite the message above in Spanish for a customer. Preserve every name, date, and number, and keep the tone polite and direct.
Use Inkling Small to answer my question using only the labeled excerpts above. Cite the supporting passage for each conclusion and say when the excerpts do not contain an answer.
How to set up Inkling Small 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 Inkling Small
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": "thinkingmachines/inkling-small", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse finds Inkling Small on Spiral, shows the price and runs it.
Inkling Small providers and prices
Spiral runs Inkling Small through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.006411 per run at the default inputs. $0.585 per 1M input tokens, $1.56 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 | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 262144 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | none, minimal, low, medium, high, or max | high | How much the model reasons. |
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Thinking Machines: Inkling Small is on its tool page: open its card above.
What can you do with Inkling Small in Muse?
Inkling Small can help work through technical questions and turn detailed instructions into usable drafts. Give it the relevant evidence and a clear definition of a finished answer.
Repair a reproducible bug
Give Inkling Small the failing behavior, relevant code, and expected result. Ask for a focused patch and a regression check.
Review a code change
Ask Inkling Small to compare an implementation against its requirements and flag specific correctness problems with examples.
Compare algorithm choices
Have Inkling Small compare two approaches under explicit memory, runtime, and edge-case constraints.
Answer questions from supplied documents
Provide labeled excerpts and ask Inkling Small to support each answer with a passage, leaving unsupported questions unanswered.
Turn requirements into acceptance criteria
Ask Inkling Small to turn a product brief into observable checks and identify requirements that need clarification.
Draft replies from approved guidance
Give Inkling Small a customer message and the relevant policy text. Request a concise reply that makes no unsupported promises.
Update a forecast
Ask Inkling Small to estimate the probability of a clearly defined event from dated evidence and explain what would change the estimate.
Rewrite multilingual messages
Use Inkling Small to rewrite a message in a requested language while preserving names, dates, numbers, and the intended tone.
More on Inkling Small and Muse
Overview
Inkling Small in other agents
Questions about Inkling Small in Muse
Can Muse use Inkling Small?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Inkling Small like any built-in tool.
How much does Inkling Small cost in Muse?
Up to $0.006411 per run at the default inputs. $0.585 per 1M input 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 Muse plan is separate.
Do I need an OpenRouter account to use Inkling Small in Muse?
You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs Inkling Small on its own OpenRouter account.
How long does it take to set up Inkling Small in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while Inkling Small runs?
Inkling Small runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.
What is Inkling Small good at?
Coding and reasoning are clear strengths in the maker’s evaluations. Try it for debugging, reviewing an implementation, or working through a specification with several constraints.
How does Inkling Small compare with Inkling?
Inkling Small surpassed Inkling on the maker’s reasoning and agentic coding benchmarks. Inkling retained an advantage in knowledge coverage and factuality, so the better choice depends on the task.
How much context can Inkling Small handle?
The maker specifies up to 1 million tokens of context. Treat that as context capacity, not a promised answer length, and give the model a focused question about the material.
Does Inkling Small support languages other than English?
Yes. The maker describes general multilingual support and support for multiple programming languages; check its output with examples from your intended language and task.
When should I increase thinking effort?
Try more thinking effort for difficult debugging or reasoning tasks, then compare results on representative examples. Higher effort can need more room for generation and does not guarantee a better answer.
Start using Inkling Small 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


