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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.99% | 99.92%◆ (best) | 99.92%◆ (best) | 746ms | 2.41s | 110 tps◆ (best) | 131K | $0.300 / $1.20◆ (best) | |
| Healthy | 100%◆ (best) | 99.92% | 99.90% | 99.90% | 545ms | 4.29s | 46 tps | 131K | $0.300 / $1.10◆ (best) | |
Phalaphala | Healthy | 100%◆ (best) | 99.52% | 99.45% | 99.45% | 1.45s | 88.3s | 38 tps | 131K | $0.300 / $1.10◆ (best) |
Togethertogether | Healthy | 100%◆ (best) | 99.61% | 99.53% | 99.53% | 385ms◆ (best) | 2.09s◆ (best) | 72 tps | 131K | $0.350 / $1.50 |
Fireworksfireworks | No data | — | 99.11% | 99.10% | 99.10% | 443ms | 6.37s | 55 tps | 131K | $0.350 / $1.50 |
- DeepInfra100%◆ (best)Healthy24h 99.99%
- 7d
- 99.92%◆ (best)
- 30d
- 99.92%◆ (best)
- p50
- 746ms
- p99
- 2.41s
- Throughput
- 110 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.300 / $1.20◆ (best)
deepinfra/bf16bf16 - Parasail100%◆ (best)Healthy24h 99.92%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 545ms
- p99
- 4.29s
- Throughput
- 46 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.10◆ (best)
parasail/bf16bf16 - Phala100%◆ (best)Healthy24h 99.52%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 1.45s
- p99
- 88.3s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.10◆ (best)
phala - Together100%◆ (best)Healthy24h 99.61%
- 7d
- 99.53%
- 30d
- 99.53%
- p50
- 385ms◆ (best)
- p99
- 2.09s◆ (best)
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.350 / $1.50
together - No data24h 99.11%
- 7d
- 99.10%
- 30d
- 99.10%
- p50
- 443ms
- p99
- 6.37s
- Throughput
- 55 tps
- Context
- 131K
- $/Mtok
- $0.350 / $1.50
fireworks
Measured 50s 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, averaged over the hour.
Throughput
Median tokens per second.