Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | metaMeta: Muse Spark 1.3Remove × | meta-llamaMeta: Llama 4 MaverickRemove × |
|---|---|---|
| What’s different | 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... | Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward... |
| Date | Sep 2, 2026Listed | Apr 5, 2025Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $1.25 in / $4.25 out/ 1M tokensMeta · via OpenRouter · all routes ↗meta | $0.1875 in / $0.6525 out/ 1M tokensDigitalOcean · via OpenRouter · all routes ↗digitalocean |
| Provider endpoints | 2 endpoints → | 4 endpoints → |
Specifications | ||
| Context window | 1M | 524.3K |
| Max output | 943.7K | 16.4K |
| Parameters | — | — |
| Tool calling | Supported | Supported |
| Structured output | Supported | Supported |
| Image input | Supported | Supported |
| Video input | Supported | Not reported |
| Reasoning | Supported | Not reported |
| Prompt caching | Supported | Supported |
| Open weights | Not reported | Supported |