OpenAI compatible API · Attested · Public status
Regolo performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Regolo on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Regoloregolo
30 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 | 1574 ms |
|---|---|
| p95 TTFT | 3554 ms |
| Effective throughput | 99 tok/s n=2 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| mistralai/mistral-small-2603 | 954 ms | — | 100.00% | — | 2 |
| qwen/qwen3.8-27b | 1028 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 1162 ms | — | 100.00% | — | 4 |
| openai/gpt-oss-120b | 1499 ms | 153 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.5-9b | 1515 ms | — | 100.00% | — | 3 |
| swiss-ai/apertus-70b-instruct | 1574 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-122b-a10b | 1965 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 2030 ms | 45 tok/s n=1 | 100.00% | — | 6 |
| openai/gpt-oss-20b | 2469 ms | — | 100.00% | — | 4 |
| qwen/qwen3-coder-next | 2838 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 2979 ms | — | 100.00% | — | 1 |