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
37 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 | 1839 ms |
|---|---|
| p95 TTFT | 3608 ms |
| Effective throughput | 49 tok/s n=2 |
| Uptime | 94.59% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| xiaomi/mimo-v2.5-pro | 2156 ms | — | 90.91% | — | 11 |
| z-ai/glm-5.2 | 961 ms | 65 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1146 ms | 33 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 1217 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-nano-12b-v2-vl | 1221 ms | — | 100.00% | 1 provider_error |
4 |
| deepseek/deepseek-v4-pro | 1262 ms | — | 100.00% | — | 4 |
| minimax/minimax-m2.5 | 1409 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3-ultra-550b | 1839 ms | — | 100.00% | 3 provider_error |
3 |
| meta-llama/llama-4-maverick | 2243 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 2423 ms | — | 75.00% | 1 provider_error |
4 |
| nvidia/nemotron-3-nano-omni | 2704 ms | — | 100.00% | 1 provider_error |
2 |