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
27 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 | 1377 ms |
|---|---|
| p95 TTFT | 1984 ms |
| Effective throughput | 157 tok/s n=2 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3-4b-instruct-2507 | 915 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3-nano-30b-a3b-bf16 | 1115 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1209 ms | — | 100.00% | — | 1 |
| qwen/qwen3-32b | 1248 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-r1-distill-qwen-14b | 1275 ms | — | 100.00% | — | 1 |
| qwen/qwen2.5-coder-32b-instruct | 1305 ms | — | 100.00% | — | 1 |
| mistralai/devstral-small-2505 | 1377 ms | — | 100.00% | — | 1 |
| qwen/qwen2.5-coder-7b-instruct | 1378 ms | — | 100.00% | — | 2 |
| qwen/qwen3-14b | 1454 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1484 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 1506 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 1701 ms | 157 tok/s n=2 | 100.00% | — | 2 |
| meta-llama/llama-3.1-8b-instruct | 1777 ms | — | 100.00% | — | 3 |
| qwen/qwen3.8-flash-next-fp8 | 1890 ms | — | 100.00% | — | 3 |