MMeta · Released Aug 9, 2026
Muse Glimmer 30B
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
- Released
- Aug 9 2026
- Context window
- 131K 16K out
- Input / 1M tokens
- $0.30 from Free
- Output / 1M tokens
- $1.20 from Free
Where to run it
14 providers compared
Free to try on Requesty, Nvidia — free endpoints are often limited-time and rate-limited. Cheapest: EmpirioLabs AI at $0.20 / $0.80 per 1M input / output tokens — 87% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Requestyfree · may be limited-time | Free | Free | — | 131K | 20K | — | Free |
| Nvidiafree · may be limited-time | Free | Free | — | 131K | 131K | — | Free |
| EmpirioLabs AI | $0.20 | $0.80 | $0.05 | 131K | 33K | — | Cheapest |
| Vultr | $0.25 | $1.00 | — | 131K | 131K | — | +25% |
| DeepInfraBF16 | $0.30 | $1.20 | $0.04 | 131K | 16K | 100%24h | +50% |
| Kilo Gateway | $0.30 | $1.20 | $0.04 | 131K | 16K | — | +50% |
| DevPass (LLM Gateway) | $0.30 | $1.20 | $0.04 | 131K | 131K | — | +50% |
| Together | $0.35 | $1.50 | $0.04 | 131K | 118K | 99.1%24h | +82% |
| NanoGPT | $0.35 | $1.50 | $0.04 | 131K | 131K | — | +82% |
| Vercel AI Gateway | $0.35 | $1.50 | $0.04 | 131K | 131K | — | +82% |
| LLM Gateway | $0.35 | $1.50 | $0.04 | 131K | 118K | — | +82% |
| Eden AI | $0.35 | $1.50 | $0.04 | 131K | 131K | — | +82% |
| AI/ML API | $0.48 | $2.06 | $0.055 | 131K | 131K | — | +150% |
| LLMTR | $2.00 | $5.00 | $0.50 | 131K | 131K | — | +686% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Muse Glimmer 30B. Scores appear here automatically once it does.
Specs
Details
- Model ID
meta/muse-glimmer-30b- Developer
- Meta
- Release date
- Aug 9, 2026 ·
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- API price
- $0.30 / $1.20 per 1M input / output tokens
- Providers
- 14
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.