Muse Spark Open
Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.
Input / output
$1.56 / $5.31
per 1M tokens
Context
1M
128K max output
Reasoning
low, medium, high, xhigh
default xhigh
Cached input
$0.1875
88% off input
Modalities
Text, image
out: text
Pricing
USD per 1M tokensInput
$1.56
Cached input
$0.1875
Output incl. reasoning
$5.31
| Similar models | Input | Output |
|---|---|---|
| Muse Spark Open | $1.56 | $5.31 |
| DeepSeek V4 Pro 0813 | $1.65 | $4.95 |
| GLM 5.3 | $1.75 | $5.50 |
| GPT-6.1 Terra | $1.00 | $5.00 |
| GLM 5.2 | $1.40 | $4.40 |
Prompt caching is automatic; see Prompt caching.
Specs
- Model ID
muse-spark-open- Endpoint
POST /api/v1/chat/completions- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Reasoning effort
reasoning_effort: low | medium | high | xhigh· default xhigh · guide- Served precision
- Not disclosed
- Added
- Oct 15, 2026
- Weights
- Open
Capabilities
Modalities
- Text
- Input and output
- Image
- Input only · up to 10
- Audio
- Not supported
- Video
- Not supported
Features
- Streaming (SSE)
- Supported
- Function calling
- Supported
- Structured output (json_schema)
- Supported
- Reasoning effort
- low, medium, high, xhigh
- Prompt caching
- Supported
- Web search
- venice_parameters
- X search
- Not supported
- Log probabilities
- Not supported
- Fine-tuning
- Not supported
- Image generation
- Not supported
POST
/api/v1/chat/completionsRecommendedcurl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-open",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "xhigh"
}'Privacy
Tier 1
Anonymized
Included
Tier 2 · this model
Private
Zero data retention, enforced by contract. Prompts and outputs aren’t stored.
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available