Trinity Large Thinking
arcee-ai/trinity-large-thinking
Compare with Virtuoso Large, GLM 5.2, DeepSeek V4 Flash 0731
CompareTrinity Large Thinking
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Arcee AIarcee-ai | Healthy | 100% | 99.98% | 373ms | 750ms | 37 tps | 262K | $0.250 / $0.800 |
Parasailparasail/fp4fp4 | Down | 75.76% | 99.84% | 176ms | 1.03s | 66 tps | 262K | $0.220 / $0.850 |
- Arcee AI100%Healthy24h 99.98%
- p50
- 373ms
- p99
- 750ms
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.250 / $0.800
arcee-ai - Parasail75.76%Down24h 99.84%
- p50
- 176ms
- p99
- 1.03s
- Throughput
- 66 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.850
parasail/fp4fp4
Measured 55s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.