How much does the Muse Spark 1.2 API cost?

On FastMetal, Muse Spark 1.2 is billed per token: $1.38 per 1M input tokens and $4.68 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Muse Spark 1.2 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "muse-spark-1.2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Muse Spark 1.2?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Muse Spark 1.2?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Muse Spark 1.2

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

8/5/2026

1,048,576 tokens

Input: $1.38/M

Output: $4.68/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

video

file

audio

Output

text

Supported Parameters

include_reasoning

max_tokens

reasoning

reasoning_effort

repetition_penalty

response_format

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

943,718

Reasoning Configuration

Default: Thinking on (effort: medium)
Selectable effort levels: xhigh
high
medium
low
minimal
Turning thinking off: Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention: May be retained
Training: Not used for training

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.1s

Measured through FastMetal's own gateway over the last 30 days (709 first-response samples).

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "muse-spark-1.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Muse Spark 1.2 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

There are **3** 'r's in "strawberry". Here is my reasoning step by step: 1. Write out the word and its spelling: **s-t-r-a-w-b-e-r-r-y** 2. Go through each letter one by one and check if it is an 'r': * 1. s - not an 'r' -> count = 0 * 2. t - not an 'r' -> count = 0 * 3. **r** - yes, it's an 'r' -> count = 1 * 4. a - not an 'r' -> count = 1 * 5. w - not an 'r' -> count = 1 * 6. b - not an 'r' -> count = 1 * 7. e - not an 'r' -> count = 1 * 8. **r** - yes, it's an 'r' -> count = 2 * 9. **r** - yes, it's an 'r' -> count = 3 * 10. y - not an 'r' -> count = 3 3. Final total = **3**.

13.3s response1123 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

This error means `users` is `undefined` when the component tries to render. You are calling `.map()` on `users` at line 12, but `.map()` only exists on arrays. If `users` is `undefined` or `null`, JavaScript throws: `Cannot read properties of undefined (reading 'map')`. This usually happens for 2 reasons: 1. You didn't pass the `users` prop to the component: `<UserList />` 2. Your data is async and `users` is `undefined` on the first render. For example: `const [users, setUsers] = useState()` without an initial value, and the data hasn't been fetched yet. ### Fix it You need to guarantee `users` is always an array before you call `.map()`. #### 1. Best Fix: Give it a default value U…

7.6s response1142 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here is a review of your function with a refactored, production-ready version: ### Issues in the Current Version #### 1. Readability 1. **Generic name:** `get_data` tells nothing about what it does. `get_active_items` is better. 2. **Imports inside function:** `import requests, time` should be at the top of the file. It's slower and violates PEP 8. 3. **Magic numbers:** `200`, `10`, `2` have no context. 4. **Verbose loop:** Manual `for` loop + `append` can be replaced with a list comprehension. 5. **No documentation/typing:** No docstring, no type hints, so callers don't know what it expects or returns. 6. **`== True` is redundant:** `if item["active"] == True:` should be `if item["a…

11.8s response2278 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Muse Spark 1.2 API cost?: On FastMetal, Muse Spark 1.2 is billed per token: $1.38 per 1M input tokens and $4.68 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Muse Spark 1.2 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "muse-spark-1.2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Muse Spark 1.2?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Muse Spark 1.2?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.