OpenAI compatible API · Attested · Public status
Wafer performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Wafer on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Waferwafer
25 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 | 1916 ms |
|---|---|
| p95 TTFT | 3765 ms |
| Effective throughput | 76 tok/s n=4 |
| Uptime | 92.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash-0731-fast | 722 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.3-flash | 766 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 1213 ms | 76 tok/s n=2 | 80.00% | — | 5 |
| qwen/qwen3.8-27b | 1288 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 1612 ms | 232 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | 1916 ms | 37 tok/s n=1 | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 2643 ms | — | 88.89% | — | 9 |