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
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 | 1144 ms |
|---|---|
| p95 TTFT | 2693 ms |
| Effective throughput | 72 tok/s n=6 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemma-4-26b-a4b-it | 651 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.1-8b-instruct | 765 ms | — | 100.00% | — | 3 |
| qwen/qwen3.6-35b-a3b | 868 ms | — | 100.00% | — | 2 |
| minimax/minimax-m3 | 894 ms | 93 tok/s n=1 | 100.00% | — | 3 |
| openai/gpt-oss-20b | 1083 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b-a55b | 1144 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.2 | 1200 ms | 71 tok/s n=1 | 100.00% | — | 1 |
| nvidia/nemotron-3.5-lightning-30b-a3b | 1229 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1342 ms | 181 tok/s n=1 | 100.00% | — | 2 |
| google/gemma-4-31b-it | 1467 ms | 72 tok/s n=1 | 100.00% | — | 3 |
| deepseek/deepseek-v4.1-flash | 1521 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1602 ms | — | 100.00% | — | 3 |
| ibm-granite/granite-4.2-8b | 2338 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 2361 ms | 52 tok/s n=2 | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 2867 ms | — | 100.00% | — | 1 |