Muse Spark Open Pricing & API Specs
muse-spark-openMuse 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... Built by Meta.
Prices updated
Input price
$1.25
per 1M tokens · Standard
Output price
$4.25
per 1M tokens · Standard
Input limit
1M
tokens
Output limit
131K
tokens
Input formats
Output formats
Muse Spark Open price history
2 price records since 10/18/2026
Muse Spark Open cost calculator
$46/month
Standard pricing
Overview
What is Muse Spark Open?
Muse Spark Open is a text & reasoning and vision model from Meta priced at $1.25 input and $4.25 output per 1M tokens, with a 1M context window. It sits in the higher price range, so it fits quality-focused work; no AA Intelligence score has been published yet.
Benchmarks
Muse Spark Open benchmarks & speed
How Muse Spark Open scores on standardized evaluations, and where it lands among every model we track.
1305
DesignArena Elo
Latency & design
- DesignArena win rate
- 54.8%
- Design battles judged
- 1,906
Independent scores from Artificial Analysis and DesignArena · updated 10/30/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Muse Spark Open pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$1.25
Per 1M tokens
Cached input · Standard
$0.15
Per 1M tokens
Capabilities
Muse Spark Open Tools
Tools available when using Muse Spark Open through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not listed
Log probabilities
Supported
Deterministic seed
Supported
Parallel tool calls
Not listed
Prompt caching
Supported
Where to run it
Muse Spark Open API providers
7 providers serve Muse Spark Open. Prices are per 1M tokens; uptime is the last 24 hours.
| Provider | Input | Output | Cached | Context | Uptime |
|---|---|---|---|---|---|
| Fireworks | $1.25 | $4.25 | $0.15 | 1M | 6.89% |
| Makorafp4 | $1.25 | $4.25 | $0.15 | 1M | 100% |
| Modal | $1.25 | $4.25 | $0.15 | 1M | 99.73% |
| Together | $1.25 | $4.25 | $0.15 | 1M | 99.6% |
| Nebiusfp4 | $1.25 | $4.25 | $0.15 | 1M | 100% |
| Fireworks | $1.25 | $4.25 | $0.15 | 1M | 6.8% |
| BaseTenfp4 | $1.25 | $4.25 | $0.15 | 1M | 95.54% |
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 6.89%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 100%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 99.73%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 99.6%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 100%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 6.8%
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
- Context
- 1M
- Uptime
- 95.54%
Strengths and limitations
Strengths
- Price rank 240 of 330 tracked models (1 = cheapest, by blended price).
- Blended price at 3 input : 1 output is $2.00 per 1M tokens.
- 1M input + 250K output tokens costs about $2.31.
- Context window 1M vs a median of 262K (4.0× larger).
Limitations
- Generated tokens cost 3× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Benchmarks are directional; test accuracy, latency and reliability on your own workload before committing.
Public listed prices, checked Nov 9, 2026. Benchmarks as published by their sources. Confirm with the provider.
Same provider