OpenAI compatible API · Attested · Public status
DigitalOcean Gradient AI performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for DigitalOcean Gradient AI on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
DigitalOcean Gradient AIdigitalocean
31 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 | 1525 ms |
|---|---|
| p95 TTFT | 2905 ms |
| Effective throughput | 72 tok/s n=5 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| nvidia/nemotron-3-nano-omni | 835 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-nano-12b-v2-vl | 1071 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-ultra-550b | 1300 ms | — | 100.00% | — | 4 |
| minimax/minimax-m2.5 | 1332 ms | — | 100.00% | — | 2 |
| meta-llama/llama-4-maverick | 1394 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.5-pro | 1499 ms | 72 tok/s n=1 | 100.00% | — | 3 |
| google/gemma-4-31b-it | 1525 ms | — | 100.00% | — | 3 |
| mistralai/ministral-3-14b-instruct | 1549 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v4-pro | 1599 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.2 | 1631 ms | 84 tok/s n=2 | 100.00% | — | 5 |
| qwen/qwen3.5-397b-a17b | 1734 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 2787 ms | 28 tok/s n=2 | 100.00% | — | 1 |