How much does the Muse Glimmer 30B API cost?

On FastMetal, Muse Glimmer 30B is billed per token: $0.3693 per 1M input tokens and $1.59 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 Glimmer 30B with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "muse-glimmer-30b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Muse Glimmer 30B?

131,072 tokens, shared between the prompt and the response.

What do I need to try Muse Glimmer 30B?

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 Glimmer 30B

Meta's dense, open-weight 30B multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for long-horizon autonomous-agent tasks on consumer hardware. Always-on reasoning with a 131k-token context window and image input.

8/10/2026

131,072 tokens

Input: $0.3693/M

Output: $1.59/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

Output

text

Reasoning Configuration

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

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

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)466ms

Measured through FastMetal's own gateway over the last 30 days (602 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-glimmer-30b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Muse Glimmer 30B 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.

The word is 10 letters long. Scanning left to right: 1. **s** - not r 2. **t** - not r 3. **r** - 1st r 4. **a** - not r 5. **w** - not r 6. **b** - not r 7. **e** - not r 8. **r** - 2nd r 9. **r** - 3rd r 10. **y** - not r `s t r a w b e r r y` There is one r in `str-`, and a double `rr` in `-berry`. Total = 1 + 2 = 3 r's.

8.0s response614 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…

The error is exactly what it says: you're trying to call `.map` on `users`, but `users` is `undefined` at render time. ```js {users.map(user => ...)} ^^^^^^ ``` `Cannot read properties of undefined [reading 'map']` means `users` was never defined / passed in, so `users.map` throws. This happens very commonly with React components that receive async data. The parent renders `UserList` before the data has loaded, so the prop is `undefined` / `null` on the first render. ### Fix it by guarding the prop **1. Default parameter to an empty array - simplest** ```js function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul>…

5.6s response888 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):…

The function works but it mixes concerns and hides errors. Here are the main issues: **Readability** * Imports inside the function. `import requests` and `import time` should be at module level. * Bare `except:` catches `KeyboardInterrupt`, `SystemExit` and masks bugs. * Unused loop variable `i` and vague names `r`, `data`. * No docstring / type hints, so the contract is unclear. * `if item["active"] == True:` is redundant and will raise `KeyError` if the key is missing. **Correctness / Best practices** * `except:` should be `except requests.RequestException`. JSON parsing can also fail. * Check `r.status_code == 200` is too narrow. Use `raise_for_status` / `r.ok` for any 2xx. * Fixed 2 se…

12.0s response1795 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Muse Glimmer 30B API cost?: On FastMetal, Muse Glimmer 30B is billed per token: $0.3693 per 1M input tokens and $1.59 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 Glimmer 30B with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "muse-glimmer-30b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Muse Glimmer 30B?: 131,072 tokens, shared between the prompt and the response.
What do I need to try Muse Glimmer 30B?: 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.