Muse Spark Open
Metamuse-spark-open
Released Oct 15, 2026
Providers
3
Context
1.0M
Input
$1.25/M
Output
$4.25/M
BAA-eligible on 2 of 3 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.
Aliases:musesparkopenmeta-muse-spark-open
Meta's open-weight 816B-parameter mixture-of-experts model (about 42B active), trained for agentic coding, with a 1M-token context window. Supports image input, tool calling, structured output, and reasoning effort.
baseten/muse-spark-openQuantfp4
- Input
- $1.25/M
- Output
- $4.25/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.15/M
- Cache write
- $1.25/M
- Thinking out
- $4.25/M
FlexPriority / Fast
fireworks/muse-spark-openQuantUnspecified
- Input
- $1.25/M
- Output
- $4.25/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.15/M
- Cache write
- $1.25/M
- Thinking out
- $4.25/M
Flex
nebius/muse-spark-openQuantfp4
- Input
- $1.25/M
- Output
- $4.25/M
- Context
- 1.0M
- Max out
- 131K
- Caching
- Not offered
- Thinking out
- $4.25/M
FlexPriority / Fast