← All models
Balanced — strong quality at a mid priceOpen Weights
Muse Glimmer 30B (batch) Pricing
Meta · meta-muse-glimmer-30b-batch
Input / 1M tokens
$0.175
Output / 1M tokens
$0.750
Context window
131,072 tokens
≈ 175 pages of text
Max output
117,964 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0005
1,000 requests / month$0.51/mo10,000 requests / month$5.10/mo100,000 requests / month$51.00/moEstimate your own workloadOpens the calculator with Muse Glimmer 30B (batch) preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Suitable for batch multimodal workloads with 128k context and high output limits at low per-token cost when self-hosted.
The business tradeoff
30B scale limits performance on complex reasoning relative to larger models; open-weights deployment shifts all infrastructure, scaling, and maintenance costs to the user.
Cheaper from Meta
Head-to-head
Vendor list rates, as of Sep 8, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.