AI model comparison
Muse Ember vs Muse Spark 1.3
Side by side comparison of Muse Ember and Muse Spark 1.3 on pricing, benchmark scores, context window, and more.
Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1.05M
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.
- Input / 1M
- $1.25
- Output / 1M
- $4.25
- Context
- 1.05M
Comparing image generators? Compare image models
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Muse Ember
10.3x cheaper for a typical chat
Higher intelligence score
Muse Spark 1.3
36.6 vs 36 on Artificial Analysis
Larger context window
Tie
1.05M vs 1.05M tokens
Newer release
Muse Ember
Released November 9, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
Muse Ember vs Muse Spark 1.3 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $0.10 | $1.25 |
| Output tokensPer 1M tokens | $0.50 | $4.25 |
| Cached input (read)Per 1M tokens | $0.00 | $0.15 |
| Cache writePer 1M tokens | $0.13 | Not available |
| Web searchPer request | $0.0025 | $0.0025 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Coding task
30K in, 4K out
Long document summary
150K in, 2K out
Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | ||
|---|---|---|
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 944K tokens | 944K tokens |
| Input types | Audio, File, Image, Text, Video | File, Image, Text, Video |
| Output types | Text | Text |
| Reasoning effort levels | Max, Extra high, High, Medium, Low, Minimal | Max, Extra high, High, Medium, Low, Minimal |
| Default reasoning effort | Max | Medium |
| Release date | November 9, 2026 | September 2, 2026 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Not supported | Not supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Our take
Muse Ember is 10.3x cheaper for a typical chat. Muse Spark 1.3 scores higher on the Artificial Analysis Intelligence Index (36.6 vs 36). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Muse Ember or Muse Spark 1.3 cheaper?
Muse Ember is cheaper for a typical chat (2K input tokens and 500 output tokens). Muse Ember costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, while Muse Spark 1.3 costs $1.25 per 1M input tokens and $4.25 per 1M output tokens.
Which has a bigger context window, Muse Ember or Muse Spark 1.3?
Muse Ember supports up to 1.05M tokens of context, compared with 1.05M for Muse Spark 1.3.
Is Muse Ember smarter than Muse Spark 1.3?
On the Artificial Analysis Intelligence Index, Muse Ember scores 36 and Muse Spark 1.3 scores 36.6, putting Muse Spark 1.3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Muse Ember and Muse Spark 1.3 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Muse Ember and Muse Spark 1.3 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Muse Ember and Muse Spark 1.3 at the same time. Compare the answers side by side and keep the best one.