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
26 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 | 2298 ms |
|---|---|
| p95 TTFT | 9033 ms |
| Effective throughput | 116 tok/s n=3 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| openpipe/qwen3-14b-instruct | 854 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 1035 ms | — | 100.00% | — | 2 |
| jetbrains/mellum2-12b-a2.5b-instruct | 1229 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-70b-instruct | 1256 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.1 | 1280 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-8b-instruct | 1469 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 1628 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 2258 ms | 150 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3.5-35b-a3b | 2298 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 2659 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 2767 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 2858 ms | — | 100.00% | — | 1 |
| qwen/qwen3-30b-a3b-instruct-2507 | 3062 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3-ultra-550b-a55b | 3389 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-27b | 3857 ms | — | 100.00% | — | 1 |
| ibm-granite/granite-4.1-8b | 9033 ms | — | 100.00% | — | 3 |
| minimax/minimax-m3 | — | 116 tok/s n=2 | — | — | 0 |