OpenAI compatible API · Attested · Public status
Nscale performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Nscale on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Nscalenscale
28 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 | 2014 ms |
|---|---|
| p95 TTFT | 4002 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| openai/gpt-oss-120b | 1136 ms | — | 100.00% | — | 1 |
| qwen/qwen2.5-coder-7b-instruct | 1462 ms | — | 100.00% | — | 3 |
| qwen/qwen3-32b | 1504 ms | — | 100.00% | — | 4 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1739 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-20b | 1950 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b | 2014 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 2528 ms | — | 100.00% | — | 4 |
| qwen/qwen3-4b-instruct-2507 | 2988 ms | — | 100.00% | — | 5 |
| qwen/qwen2.5-coder-3b-instruct | 3534 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3-nano-30b-a3b-bf16 | 4028 ms | — | 100.00% | — | 1 |