OpenAI compatible API · Attested · Public status
StreamLake performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for StreamLake on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
StreamLakestreamlake
16 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 2521 ms |
|---|---|
| p95 TTFT | 13640 ms |
| Effective throughput | 66 tok/s n=7 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.6-35b-a3b | 1431 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3.1 | 1567 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 2106 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 2465 ms | 52 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 2521 ms | — | 100.00% | — | 3 |
| qwen/qwen3.6-27b | 3060 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.7-code | 3517 ms | 66 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 6650 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3 | 13640 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | — | 69 tok/s n=2 | — | — | 0 |
| qwen/qwen3-30b-a3b-thinking-2507 | — | — | — | 1 BadRequest |
0 |
| qwen/qwen3-vl-235b-a22b-thinking | — | — | — | 1 BadRequest |
0 |
| xiaomi/mimo-v2.5 | — | — | — | 2 BadRequest |
0 |
| z-ai/glm-5.2 | — | 66 tok/s n=2 | — | — | 0 |
| z-ai/glm-5.3 | — | 25 tok/s n=1 | — | — | 0 |