LONG MEMORY · 雪国
Llama
7 models from Meta, living in Snow Country.
| Model | Context | Input | Output | Accepts |
|---|---|---|---|---|
| Muse Spark Openmeta/muse-spark-open | 1.05M | $1.25 | $4.25 | text, audio, files, images, video |
| Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor | 1.05M | $0.100 | $0.200 | text, files, images, video |
| Muse Spark 1.3meta/muse-spark-1.3 | 1.05M | $1.25 | $4.25 | text, files, images, video |
| Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor | 1.05M | $0.100 | $0.200 | text, files, images, video |
| Muse Spark 1.2meta/muse-spark-1.2 | 1.05M | $1.25 | $4.25 | text, files, images, video |
| Muse Spark 1.1meta/muse-spark-1.1 | 1.05M | $1.25 | $4.25 | text, files, images, video |
| Llama 4 Scoutmeta-llama/llama-4-scout | 1.31M | $0.100 | $0.300 | text, images |
Questions and answers
Which Llama model has the largest context window?
Llama 4 Scout (Meta), with 1.31M tokens.
Which Llama model is cheapest per input token?
Llama 4 Scout, at $0.100 per million input tokens ($0.300 per million output tokens).
Which Llama models accept images?
Muse Spark Open, Muse Spark 1.3 Contributor, Muse Spark 1.3, Muse Spark 1.2 Contributor, Muse Spark 1.2, Muse Spark 1.1 and 1 more (7 of 7).
Which Llama models support reasoning?
Muse Spark Open, Muse Spark 1.3 Contributor, Muse Spark 1.3, Muse Spark 1.2 Contributor, Muse Spark 1.2, Muse Spark 1.1 (6 of 7).
Answers are computed from the 2026-10-24 catalog snapshot.