Best for coding
Good code quality, debugging and technical explanation.
Model · Meta
Muse Spark Open
Muse Spark Open is served by Meta through OpenRouter. It provides 1.05M tokens of context and supports text, vision, audio, video, files inputs.
Context window
1.05M tokens
Input / 1M tokens
$1.25
Output / 1M tokens
$4.25
Key facts
| Provider | Meta |
| OpenRouter ID | meta/muse-spark-open |
| Modalities | Text, Vision, Audio, Video, Files |
| Best for | Coding, Multimodal, Long Context |
Source
openrouter.ai/api/v1/models Verified 2026-10-16 Drift-checked daily 06:00 CST Best-fit workloads
Best for long context
Large context window for documents and transcripts.
Best multimodal
Handles images, files, audio or video inputs.
Cost estimates
These examples use the 2026-10-16 input and output prices. Cache discounts, provider surcharges and tool fees are excluded.
| Workload | Input | Output | Estimated cost |
|---|---|---|---|
| Quick test | 20,000 | 5,000 | $0.046 |
| Product chat month | 500,000 | 125,000 | $1.16 |
| Document batch | 5,000,000 | 1,000,000 | $10.50 |
Strengths
- ✓ Open weights: meta-models/Muse-Spark-Open-816B-A42B on Hugging Face, so the checkpoint can leave Meta's API
- ✓ 1,048,576-token window and a 943,718-token output ceiling — the same shape as Muse Wonder
- ✓ $1.25 / $4.25 per million, a third of Muse Wonder's input price, tuned for agentic coding
Limitations
- ! The weights are gated behind a manual access request and carry Meta's own Muse Model License, not an OSI licence
- ! 816B total parameters with 42B active: open weights, not a laptop model
- ! OpenRouter does not apply moderation to it, where Muse Wonder is moderated
OpenRouter API quickstart
Run these examples from your server or edge function. Keep the OpenRouter API key private and do not expose it in browser code.
cURL
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta/muse-spark-open",
"messages": [{ "role": "user", "content": "Summarize this document in five bullet points." }],
"max_tokens": 500
}'JavaScript / TypeScript
const response = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "meta/muse-spark-open",
messages: [{ role: "user", content: "Summarize this document in five bullet points." }],
max_tokens: 500,
}),
});
const data = await response.json();
console.log(data.choices[0].message.content);How to evaluate Muse Spark Open
- Run five real tasks from your product, not generic demo prompts.
- Record token usage, latency and output quality.
- Estimate cost using your real input/output mix.
- Compare it against one model with a similar price and one stronger model.
Compare models View on OpenRouter ↗
Muse Spark Open FAQ
What is Muse Spark Open?
Muse Spark Open is a Meta model available through OpenRouter. It supports text, vision, audio, video, files inputs and is suited for coding, multimodal, long context workloads.
How much does Muse Spark Open cost on OpenRouter?
The 2026-10-16 snapshot lists $1.25 per 1M input tokens and $4.25 per 1M output tokens. Verify current pricing on OpenRouter before production.
How large is Muse Spark Open's context window?
Muse Spark Open offers 1.05M tokens of context in the current snapshot. Provider-specific limits and surcharges may apply.
Pricing and context data are based on a 2026-10-16 snapshot. Provider limits can change; always verify on OpenRouter before production.