# Muse Glimmer 30B API prices

Muse Glimmer 30B (muse) — 131k context, 131k max output.
9 metered per-token offers from 9 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| EmpirioLabs AI | $0.2 | $0.8 | $0.05 | 131k |
| Kilo Gateway | $0.3 | $1.1 | $0.04 | 131k |
| OpenRouter | $0.3 | $1.1 | $0.04 | 131k |
| Eden AI | $0.3 | $1.2 | $0.04 | 131k |
| Eden AI | $0.35 | $1.5 | $0.04 | 131k |
| Eden AI | $0.35 | $1.5 | $0.04 | 131k |
| Fireworks AI | $0.35 | $1.5 | $0.04 | 131k |
| NanoGPT | $0.35 | $1.5 | $0.04 | 131k |
| Vercel AI Gateway | $0.35 | $1.5 | $0.04 | 131k |

## Summary

- Cheapest input: $0.2 per 1M tokens (EmpirioLabs AI)
- Cheapest output: $0.8 per 1M tokens (EmpirioLabs AI)
- First-party: not listed separately
- Free offers: Nvidia, Requesty
- Subscription plans (not per-token): none
- Released: 2026-08-10
- Inputs: image, pdf, text

HTML page: https://llmprice.gitlab.io/models/muse-glimmer-30b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json