Meta: Muse Glimmer 30B
by MetaMeta: Muse Glimmer 30B is a large language model from Meta. It costs $0.300 per million input tokens and $1.20 per million output tokens. Its context window is 131K tokens.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $1.20
- Cached input / 1M
- $0.040
- Context window
- 131K
On repeated prefixes
tokens
Who serves it cheapest
2 hosts serve Muse Glimmer 30B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfraCheapestbf16 | $0.300 | $1.20 | 131K | - | 100.0% |
| Together | $0.350 | $1.50 | 131K | - | 82.6% |
The spread between DeepInfra and Together is 1.2× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 17.5
- Coding index
- 49.0
- Agentic index
- 8.5
About 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...
Specifications
| Model ID | meta/muse-glimmer-30b |
|---|---|
| Provider | Meta |
| Context window | 131K tokens |
| Max output | 16K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - meta-models/Muse-Glimmer-30B |
| Released | August 9, 2026 |
Cheaper alternatives
Models that cost less than Muse Glimmer 30B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Meta: Muse Glimmer 30B cost?
$0.300 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.040 per million tokens.
What is the context window of Meta: Muse Glimmer 30B?
131K tokens, with up to 16K tokens of output per request.
Which provider serves Meta: Muse Glimmer 30B cheapest?
DeepInfra at $0.300 per million input tokens - 1.2× cheaper than Together, the most expensive of the 2 hosts serving it.