Meta › Muse Spark 1.3 › Pricing
$1.25 / $4.25per 1M tokens in / out
$0.15cache read · −88%
$1.37per task at xhigh?
#92on OpenRouter by tokens · 96B / week
Price sheetper 1M tokens
| Input | $1.25 | list |
| Output | $4.25 | |
| Cache read | $0.15 | −88% vs input |
| Context · max output | 1M · 944K | tokens |
Cost per task by effort?
xhighAPI default$1.3747.5
max$1.6048.7
per taskHumanity's Last Exam
Same price per token at every effort; the bill grows with reasoning tokens. max costs 1.2× xhigh for +1.3 points.
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Metalab | $1.25 | $4.25 | 1M |
In Meta's line-upper 1M in / out
| Llama 3.1 70B | $0.72 / $0.72 | −64% |
| Llama 3.2 90B | $0.72 / $0.72 | −64% |
| Llama 3.3 70B | $0.72 / $0.72 | −64% |
| Muse Spark 1.3 | $1.25 / $4.25 | this model |
| Muse Spark Open | $1.25 / $4.25 | 0% |
| Muse Spark Open 816B A42B | $1.25 / $4.25 | 0% |
| Llama 3.1 405B | $2.40 / $2.40 | +20% |
Cheaper for the same workvs Muse Spark 1.3 at xhigh
| GPT-6.1 Sol max | -47% | score +15% | $0.72 |
| GPT-6 Sol max | -24% | score +6% | $1.04 |
| Claude Sonnet 5.5 high | -35% | score +4% | $0.88 |
| MiMo v2.6 Pro thinkingOpen | -90% | score +3% | $0.13 |
| GPT-6 Astra low | -40% | same score | $0.82 |
Pricing questions
How much does Muse Spark 1.3 cost?›
$1.25 per 1M input tokens and $4.25 per 1M output tokens. Cached input is $0.15. One Intelligence Index task costs about $1.37 at the default effort.
Is Muse Spark 1.3 free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.15 per 1M, 88% below the input price.
Is Muse Spark 1.3 cheaper than Muse Spark 1.2?›
It costs the same per token: $1.25 / $4.25.
How does effort change the price?›
The price per token is the same at every effort. Higher effort spends more reasoning tokens: a task costs $1.37 at xhigh, $1.60 at max.
What is a cheaper alternative to Muse Spark 1.3?›
GPT-6.1 Sol at max effort costs -47% per task with a score +15% on Humanity's Last Exam.