Meta · Model
Muse Spark Open API pricing, cost and context window
Muse Spark Open costs $1.25 per million input tokens and $4.25 per million output tokens. Cached input costs $0.15. It reads up to 1,048,576 tokens. Prices checked 2026-10-16. By blended price it is number 5 of Meta’s 6 current models here, counting from the cheapest.
- Input / 1M
- $1.25
- Output / 1M
- $4.25
- Cached / 1M
- $0.15
- Context
- 1,048,576
- Max output
- Not published
- Released
- 2026-10-15
Estimate your cost with Muse Spark OpenCompare all Meta modelsCount tokens for Muse Spark Open
Pricing
How much does Muse Spark Open cost per million tokens?
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $1.25 | $4.25 |
| Cached input (read) | $0.15 | – |
Output costs 3.4× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 12% of the normal input price.
Work out your monthly Muse Spark Open bill in the cost calculatorSee what prompt caching saves
Examples
How much does a typical Muse Spark Open request cost?
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00275 | $83.65 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00831 | $126.31 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0233 | $141.74 |
| Document summariser | 8,000 / 600 | 300 | $0.0126 | $114.52 |
Change any number in the cost calculator.
Context
What is Muse Spark Open’s context window and max output?
Muse Spark Open accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $1.31 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
What can Muse Spark Open do?
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text, image, video, file, audio
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
What is the Muse Spark Open API model ID?
- OpenRouter
meta/muse-spark-open- Open weights
- meta-models/Muse-Spark-Open-816B-A42B
Use the OpenRouter ID when calling it through OpenRouter; Meta’s own API may name it differently. See the model ID reference for the providers we document.
Meta
Where does Muse Spark Open sit in Meta’s line-up?
Ranked by blended price (three parts input to one part output, $2 per 1M for Muse Spark Open), it is number 5 of Meta’s 6 current models here, counting from the cheapest. One step down, Muse Spark 1.3 costs $2 blended, the same. Unlike Muse Spark Open, it doesn’t accept audio and is API-only. One step up, Muse Wonder costs $8 (4× as much). Unlike Muse Spark Open, it is API-only. See every Meta model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Llama 4 Scout | $0.18 | $0.59 | 131,072 | 2025-04-05 |
| Llama 4 Maverick | $0.1875 | $0.6525 | 128,000 | 2025-04-05 |
| Muse Glimmer 30B | $0.30 | $1.20 | 131,072 | 2026-08-09 |
| Muse Spark 1.3 | $1.25 | $4.25 | 1,048,576 | 2026-09-02 |
| Muse Spark Open (this page) | $1.25 | $4.25 | 1,048,576 | 2026-10-15 |
| Muse Wonder | $4 | $20 | 1,048,576 | 2026-10-12 |
Meta’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
What are cheaper alternatives to Muse Spark Open?
- GPT-6 LunaOpenAI90% cheaper
- Claude Haiku 5.5Anthropic90% cheaper
- Qwen3.8 Omni FlashQwen89% cheaper
- GLM 5.3 FlashZ.ai88% cheaper
- Nemotron 3.5 Super VLNVIDIA88% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Which models cost about the same?
- DeepSeek V4 Pro 0813DeepSeek$1.32 / $3.96
- GLM 5V TurboZ.ai$1.20 / $4
- GPT-5.4 MiniOpenAI$0.75 / $4.50
- Gemini 3.8 FlashGoogle$0.825 / $4.125
- Kimi K2.7 CodeMoonshot AI$0.6712 / $3.35
Current models from other major providers, closest blended price.
FAQ
Muse Spark Open questions
How much does Muse Spark Open cost?
Muse Spark Open costs $1.25 per million input tokens and $4.25 per million output tokens, with cached input at $0.15. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00358. Use the LLM cost calculator for your own workload.
What is Muse Spark Open’s context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Muse Spark Open support prompt caching and batch requests?
Yes, cached input is billed at $0.15 per million tokens (12% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Muse Spark Open?
With the same essentials (image input and tool calling), the cheapest options are GPT-6 Luna (90% cheaper), Claude Haiku 5.5 (90% cheaper), Qwen3.8 Omni Flash (89% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Muse Spark Open?
On OpenRouter it is meta/muse-spark-open. Meta’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
When was Muse Spark Open released?
Muse Spark Open was first listed on 2026-10-15. It is the first model in its line in our data. Release dates here are when our price source first listed each model.
Is Muse Spark Open open source?
Yes, Muse Spark Open has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.