OpenAI compatible API · Attested · Public status
Weights & Biases performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Weights & Biases on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Weights & Biaseswandb
34 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 | 1257 ms |
|---|---|
| p95 TTFT | 3020 ms |
| Effective throughput | 161 tok/s n=8 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| meta-llama/llama-3.3-70b-instruct | 636 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 911 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-8b-instruct | 1146 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.3-flash | 1173 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b-a55b | 1227 ms | — | 100.00% | — | 7 |
| nvidia/nemotron-3.5-lightning-30b-a3b | 1257 ms | — | 100.00% | — | 4 |
| moonshotai/kimi-k2.7-code | 1678 ms | 62 tok/s n=2 | 100.00% | — | 3 |
| ibm-granite/granite-4.2-8b | 2115 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 2207 ms | 300 tok/s n=2 | 100.00% | — | 8 |
| deepseek/deepseek-v4-flash-0731 | 2453 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 2898 ms | 188 tok/s n=1 | 100.00% | — | 1 |
| google/gemma-4-31b-it | 4290 ms | 168 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.2 | — | 154 tok/s n=2 | — | — | 0 |