Vendor
Meta models
6 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
6
0 routable here
Median list price
$1.25
3:1 input to output per 1M tokens
Every Meta model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor | Sep 2, 2026 | 1.0M | $0.10 | $0.20 | - | reasoning tools |
| Muse Spark 1.3meta/muse-spark-1.3 | Sep 2, 2026 | 1.0M | $1.25 | $4.25 | - | reasoning tools |
| Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor | Aug 21, 2026 | 1.0M | $0.10 | $0.20 | - | reasoning tools |
| Muse Glimmer 30Bmeta/muse-glimmer-30b | Aug 9, 2026 | 131K | $0.30 | $1.10 | - | reasoning tools open weights |
| Muse Spark 1.2meta/muse-spark-1.2 | Aug 5, 2026 | 1.0M | $1.25 | $4.25 | 47 | reasoning tools |
| Muse Spark 1.1meta/muse-spark-1.1 | Jul 16, 2026 | 1.0M | $1.25 | $4.25 | - | reasoning tools |
Frequently asked
- What is the cheapest Meta model?
- Muse Spark 1.3 Contributor at $0.10 per 1M input tokens and $0.20 per 1M output tokens (vendor list price).
- Which Meta model has the largest context window?
- Muse Spark 1.3 Contributor accepts 1.0M tokens of context.
- How do I route to Meta models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example meta/muse-spark-1.3-contributor); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Meta with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Meta flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.