Muse Spark Open pricing, context and benchmark
Muse Spark Open is a coding-optimized open-weight model.
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Muse Spark Open |
| Model ID | meta/muse-spark-open |
| Provider | Meta |
| Release date | 15 October 2026 |
| Status | Generally available |
| Input context | 1,048,576 tokens |
| Output context | 943,718 tokens |
| Official input pricing | $1.25 per 1M tokens |
| Official output pricing | $4.25 per 1M tokens |
| Cache read pricing | $0.15 per 1M tokens (88% off input) |
| Market input pricing | $1.25 per 1M (cheapest route) |
| Market output pricing | $4.25 per 1M (cheapest route) |
| Input modalities | text · image · video · file · audio |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 5 endpoints |
| Artificial Analysis index | 25 (#12 of 26) |
| Speed | 198 tokens/s, 10.14s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $1.25 in |
| Image | ✓ yes | no | $1.25 in |
| Audio | ✓ yes | no | $1.25 in |
| Video | ✓ yes | no | $1.25 in |
| File (PDF) | ✓ yes | no | $1.25 in |
What is 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...
Muse Spark Open carries a 1.05M token window, uses the Other tokenizer and is served by Meta. On Hoodgen it sits in the Multimodal tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
Release and what changed from the previous version
| Property | Muse Wonder | Muse Spark Open | Change |
|---|---|---|---|
| Released | Oct 2026 | Oct 2026 | Same release window |
| Context | 1.05M | 1.05M | Unchanged |
| Max output | 944K | 944K | Unchanged |
| Input price | $4 | $1.25 | Cheaper |
| Output price | $20 | $4.25 | Cheaper |
| Input modalities | text, image, video, file, audio | text, image, video, file, audio | Unchanged |
| AA index | 44 | 25 | Newer benchmark run |
Features and capabilities
Benchmark results and performance
Artificial Analysis Intelligence Index v5.0.1 blends nine evaluations. Muse Spark Open scores 25 , ranking #12 of 26.
What can you do with Muse Spark Open?
Prompt caching and how to cut the bill
Cached input bills at $0.15 per million instead of $1.25, a 88% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
Muse Spark Open pricing
Official pricing
- $0.15 cached input
- 1.05M context
- text, image, video, file, audio input
- 5 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Makora | standard | $1.25 | $4.25 | $0.15 | 100.0% |
| Modal | standard | $1.25 | $4.25 | $0.15 | 99.8% |
| Together | standard | $1.25 | $4.25 | $0.15 | 100.0% |
| Nebius | standard | $1.25 | $4.25 | $0.15 | 96.4% |
| BaseTen | standard | $1.25 | $4.25 | $0.15 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0182 | $9.09 | 8634 |
| List price | $0.0182 | $9.09 | 8634 |
API and developer information
| Model ID | meta/muse-spark-open |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+file+audio+video->text |
| Max prompt tokens | 1,048,576 |
| Max completion tokens | 943,718 |
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": "Summarise this document." }],
"max_tokens": 1024
}'Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 943,718 tokens per request. Long deliverables have to be chunked. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
Muse Spark Open vs other Meta models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Muse Spark Open | 1.05M | $1.25 | $4.25 | 25 | Oct 2026 |
| Muse Wonder | 1.05M | $4 | $20 | 44 | Oct 2026 |
| Muse Spark 1.3 | 1.05M | $1.25 | $4.25 | 37 | Sep 2026 |
| Muse Spark 1.2 | 1.05M | $1.25 | $4.25 | n/a | 2026 |
| Muse Spark 1.1 | 1.05M | $1.25 | $4.25 | n/a | 2026 |
| Muse Glimmer 30B | 131K | $0.3 | $1.2 | n/a | 2026 |
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Meta and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
Muse Spark Open questions, answered
Start chatting with Muse Spark Open
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.