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
100 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 | 2995 ms |
|---|---|
| p95 TTFT | 7445 ms |
| p50 TTFB | 1625 ms |
| Effective throughput | 52 tok/s n=6 |
| Uptime | 94.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen2.5-vl-72b-instruct | 537 ms | 537 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 872 ms | 871 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 878 ms | 877 ms | 80 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3-coder-next | 982 ms | 982 ms | — | 100.00% | — | 1 |
| arcee-ai/trinity-large-thinking | 1138 ms | 1138 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 1432 ms | 1432 ms | 79 tok/s n=1 | 100.00% | — | 3 |
| meta-llama/llama-4-maverick | 1504 ms | 1504 ms | — | 100.00% | — | 3 |
| thedrummer/skyfall-36b-v2 | 1521 ms | 1521 ms | — | 100.00% | — | 3 |
| qwen/qwen3-vl-235b-a22b-instruct | 1572 ms | 1572 ms | — | 100.00% | — | 3 |
| qwen/qwen3-next-80b-a3b-instruct | 1581 ms | 1581 ms | — | 100.00% | — | 3 |
| openai/gpt-oss-20b | 1606 ms | 1606 ms | — | 100.00% | — | 2 |
| bytedance/ui-tars-1.5-7b | 1626 ms | 1625 ms | — | 100.00% | — | 5 |
| google/gemma-4-26b-a4b-it | 1643 ms | 1643 ms | — | 100.00% | — | 6 |
| meta-llama/llama-3.3-70b-instruct | 1700 ms | 1700 ms | — | 100.00% | — | 3 |
| google/gemma-3-27b-it | 2752 ms | 2752 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-8b-instruct | 2806 ms | 2806 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 2995 ms | 2995 ms | — | 100.00% | — | 3 |
| google/gemma-4-31b-it | 3093 ms | 3093 ms | 22 tok/s n=1 | 100.00% | — | 3 |
| openai/gpt-oss-120b | 3974 ms | 3974 ms | 52 tok/s n=2 | 100.00% | — | 3 |
| z-ai/glm-5.2 | 4152 ms | 1327 ms | 29 tok/s n=1 | 97.44% | — | 39 |
| thedrummer/cydonia-24b-v4.1 | 3230 ms | 3230 ms | — | 75.00% | — | 4 |
| z-ai/glm-5.1 | 1058 ms | 1058 ms | — | 50.00% | — | 4 |
| minimax/minimax-m3 | — | — | — | 0.00% | — | 1 |
| qwen/qwen3.5-35b-a3b | — | — | — | 0.00% | 3 probe_config_error |
1 |