Muse Glimmer 30B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Phalaphala | Healthy | 100%◆ (best) | 99.91% | 98.33% | 99.23% | 3.02s | 10.5s | 26 tps◆ (best) | 131K | $0.300 / $1.10◆ (best) |
Togethertogether | Healthy | 98.41% | 98.19% | 99.60%◆ (best) | 99.40% | 2.25s◆ (best) | 7.79s◆ (best) | 24 tps | 131K | $0.350 / $1.50 |
| Degraded | 96.13% | 93.64% | 99.05% | 99.75%◆ (best) | 14.2s | 31.5s | 8.0 tps | 131K | $0.300 / $1.20◆ (best) | |
Fireworksfireworks | No data | — | — | — | 98.44% | — | — | — | 131K | $0.350 / $1.50 |
| No data | — | — | — | — | — | — | — | 131K | $0.300 / $1.10◆ (best) |
- Phala100%◆ (best)Healthy24h 99.91%
- 7d
- 98.33%
- 30d
- 99.23%
- p50
- 3.02s
- p99
- 10.5s
- Throughput
- 26 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.300 / $1.10◆ (best)
phala - Together98.41%Healthy24h 98.19%
- 7d
- 99.60%◆ (best)
- 30d
- 99.40%
- p50
- 2.25s◆ (best)
- p99
- 7.79s◆ (best)
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.350 / $1.50
together - DeepInfra96.13%Degraded24h 93.64%
- 7d
- 99.05%
- 30d
- 99.75%◆ (best)
- p50
- 14.2s
- p99
- 31.5s
- Throughput
- 8.0 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.20◆ (best)
deepinfra/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 98.44%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.350 / $1.50
fireworks - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.300 / $1.10◆ (best)
parasail/bf16bf16
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.