meta/muse-glimmer-30b

meta/muse-glimmer-30b is a efficient-tier language model from RouterPlus. meta/muse-glimmer-30b is a proprietary model available exclusively through RouterPlus's API. The Muse family is RouterPlus's model series for this capability tier.

meta/muse-glimmer-30b is priced at $0.3/1M input tokens and $1.2/1M output tokens. Output tokens are 4× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, meta/muse-glimmer-30b costs approximately $0.90 per 1,000 API calls. Prompt caching reduces repeated input tokens to $0.04/1M — a 87% discount that compounds significantly for applications with long shared system prompts, multi-turn conversations, or document Q&A where the same context is reused across many queries.

Its 131K-token context window handles most long-document tasks — roughly 75,000 words or a full novel — without requiring chunking or retrieval augmentation. Maximum output length is 131K tokens — sufficient for long-form content generation, detailed code files, and extended reports.

meta/muse-glimmer-30b is best suited to general language tasks. Supported capabilities include streaming token output for real-time UIs. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how meta/muse-glimmer-30b compares to similar models across these dimensions.

meta/muse-glimmer-30b sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. Unlike open-weights alternatives, meta/muse-glimmer-30b is only available via RouterPlus's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing meta/muse-glimmer-30b to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (N/A/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.