Trinity Large Thinking vs DeepSeek V4.1 Flash
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareTrinity Large ThinkingDeepSeek V4.1 Flash
| Trinity Large Thinking | 1/2 | 100% | 99.97% | 99.99% | 742ms | 3.24s | 202 tps | 262K | $0.220 / $0.850 |
| DeepSeek V4.1 Flash | 29/44 | 100% | 99.98% | 99.89% | 288ms | 2.23s | 338 tps | 1.0M | $0.004 / $0.600 |
Measured 4m ago. Each figure is the best available across that model's providers.
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest P50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.