Llama 3.3 70B Instruct vs Muse Spark 1.3 Contributor
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 | Llama 3.3 70B Instructmeta/llama-3.3-70b | Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor |
|---|---|---|
| Maker | meta | meta |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.756 | $0.105 Lower |
| Cached input per 1M tokens | Not applicable | $0.0021 |
| Cache write per 1M tokens | Not applicable | Same as input |
| Output per 1M tokens | $0.756 | $0.21 Lower |
| Context window | 128,000 tokens | 1,048,576 tokens Larger |
| Max output | 8,192 tokens | 1,048,576 tokens Larger |
| Capabilities | Tool use | Reasoning, tool use, vision, file input |
| Takes | Text | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Not on every provider |
| Released | 2024-12-06 | 2026-09-02 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Llama 3.3 70B Instruct | Muse Spark 1.3 Contributor |
|---|---|---|
| 1,000 tokens in, 200 out | $0.000907 | $0.000147 |
| 10,000 tokens in, 1,000 out | $0.008316 | $0.00126 |
| 100,000 tokens in, 4,000 out | $0.078624 | $0.01134 |