OpenAI compatible API · Attested · Public status
Parasail performance
Review measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Parasail on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Parasailparasail
43 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 | 2703 ms |
|---|---|
| p95 TTFT | 5758 ms |
| p50 TTFB | 3384 ms |
| Effective throughput | 38 tok/s n=11 |
| Uptime | 90.70% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen2.5-vl-72b-instruct | 957 ms | 957 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-next | 973 ms | 973 ms | — | 100.00% | — | 2 |
| minimax/minimax-m3 | 1075 ms | 1075 ms | 53 tok/s n=2 | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 1178 ms | 1178 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash | 1409 ms | 1409 ms | 36 tok/s n=2 | 100.00% | — | 4 |
| moonshotai/kimi-k2.6 | 1650 ms | 1649 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 2104 ms | 2104 ms | 38 tok/s n=1 | 100.00% | — | 2 |
| openai/gpt-oss-20b | 2703 ms | 2702 ms | — | 100.00% | — | 4 |
| thedrummer/skyfall-36b-v2 | 2875 ms | 2875 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 3243 ms | 3243 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 3790 ms | 3790 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 3981 ms | 3980 ms | 75 tok/s n=2 | 100.00% | — | 6 |
| meta-llama/llama-4-maverick | 4149 ms | 4149 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 4271 ms | 4271 ms | 29 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3-vl-235b-a22b-instruct | 4652 ms | 4651 ms | — | 100.00% | — | 1 |
| bytedance/ui-tars-1.5-7b | — | — | — | 100.00% | — | 2 |
| thedrummer/cydonia-24b-v4.1 | — | — | — | 50.00% | — | 2 |
| arcee-ai/trinity-large-thinking | 3384 ms | 3384 ms | — | 33.33% | — | 3 |
| deepseek/deepseek-v4-pro-0423 | — | — | 36 tok/s n=1 | 0.00% | — | 1 |
| openai/gpt-oss-120b | — | — | 69 tok/s n=1 | — | — | 0 |