Back to Models
Muse Spark Open
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
10/15/2026
1,048,576 tokens
Specifications
Modalities
Input
text
image
video
file
audio
Output
text
Supported Parameters
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
Max Output Tokens
943,718Reasoning Configuration
- Default
- Thinking on (effort: medium)
- Selectable effort levels
- xhighhighmediumlow
- Turning thinking off
- Not possible (always thinks)
Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"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.
Frequently asked questions
- Is Muse Spark Open available on FastMetal?
- Not at the moment. Muse Spark 1.3, from the same lab, is available on the FastMetal API today.
- What is the context window of Muse Spark Open?
- 1,048,576 tokens, shared between the prompt and the response.