MODEL PROOF
Muse Spark 1.3
FRONTIER
Nothing scores at least as high for less, or higher for the same price, under this workload.
- Independent LMArena score
- 1,493.6 ± 4.81 · 30,142 votes
- Context window
- 1.05M
- Maximum output
- 943.72K
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Published input price
- $1.25 / 1M tokens
- Published output price
- $4.25 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Meta: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at the maker’s precision or better, at its standard rate.
Every price dimension · USD per million tokens
| Input | $1.25/M |
|---|---|
| Output | $4.25/M |
| Cached input | $0.150/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
| Web search | $0.0025/call |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
2 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Googlegoogle-vertex/global Endpoint terms
| $1.25 | $4.25 | undeclared | 99.86% |
| Metameta Endpoint terms
| $1.25 | $4.25 | undeclared | 99.93% |
Independent scores
| LMArena Elo | 1493.6max |
|---|---|
| LMArena row | muse-spark-1.3-max |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Websites #2 1355
- Native Android apps #2 1287
- SVG #6 1305
- ASCII art #6 1334
- Web apps #6 1275
- Full-stack apps #6 1288
- Data visualisation #7 1341
- Blender3d #8 1145
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 1M |
|---|---|
| Max output | 943K |
| Input modes | text, image, video, file, audio |
| Tool use | yes |
| Reasoning | always on |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Held | Input types kept at the published record of 2026-10-06 while a newer upstream value is reviewed. |
| Quality data | verified |
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
Questions this page answers
What does Muse Spark 1.3 cost?
$1.25/M in, $4.25/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Muse Spark 1.3 have an independent quality score?
Muse Spark 1.3 has an LMArena score in this catalogue.
What beats Muse Spark 1.3?
Nothing scores at least as high as Muse Spark 1.3 for less, or higher for the same price.
Does this page use Artificial Analysis scores for Muse Spark 1.3?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT