Muse Spark 1.2 vs Muse Spark 1.3
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Muse Spark 1.2meta/muse-spark-1.2 | Muse Spark 1.3meta/muse-spark-1.3 |
|---|---|---|
| Maker | meta | meta |
| Kind | Chat | Chat |
| Input per 1M tokens | $1.3125 | $1.3125 |
| Cached input per 1M tokens | $0.1575 | $0.1575 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $4.4625 | $4.4625 |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Max output | 1,048,576 tokens | 1,048,576 tokens |
| Capabilities | Reasoning, tool use, vision, file input | Reasoning, tool use, vision, file input |
| Takes | Text, image, pdf | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Yes, on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2026-08-05 | 2026-09-02 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| 1,000 tokens in, 200 out | $0.002205 | $0.002205 |
| 10,000 tokens in, 1,000 out | $0.017588 | $0.017588 |
| 100,000 tokens in, 4,000 out | $0.1491 | $0.1491 |