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
42 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 | 1389 ms |
|---|---|
| p95 TTFT | 4122 ms |
| Effective throughput | 24 tok/s n=5 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash | 2321 ms | 75 tok/s n=1 | 100.00% | — | 11 |
| nvidia/nemotron-3-ultra-550b | 1072 ms | — | 100.00% | — | 2 |
| xiaomi/mimo-v2.5-pro | 1109 ms | 64 tok/s n=1 | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 1258 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-nano-12b-v2-vl | 1264 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-397b-a17b | 1354 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-nano-omni | 1369 ms | — | 100.00% | — | 2 |
| mistralai/ministral-3-14b-instruct | 1389 ms | — | 100.00% | — | 4 |
| moonshotai/kimi-k2.6 | 1587 ms | 16 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.2 | 1666 ms | 24 tok/s n=2 | 100.00% | — | 1 |
| meta-llama/llama-4-maverick | 2018 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.5 | 2962 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3.2 | 3685 ms | — | 100.00% | — | 3 |