OpenAI compatible API · Attested · Public status
DigitalOcean Gradient AI performance
Review measured TTFT, TTFB, 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
61 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 | 1709 ms |
|---|---|
| p95 TTFT | 5117 ms |
| p50 TTFB | 2023 ms |
| Effective throughput | 39 tok/s n=6 |
| Uptime | 96.72% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| xiaomi/mimo-v2.5-pro | 647 ms | 647 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-nano-omni | 727 ms | 727 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b | 981 ms | 980 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 1197 ms | 1197 ms | — | 100.00% | — | 3 |
| mistralai/ministral-3-14b-instruct | 1210 ms | 1210 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 1216 ms | 1215 ms | — | 100.00% | — | 2 |
| meta-llama/llama-4-maverick | 1388 ms | 1388 ms | — | 100.00% | — | 4 |
| qwen/qwen3-coder-flash | 1395 ms | 1395 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1414 ms | 1414 ms | 39 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 1682 ms | 1681 ms | — | 100.00% | — | 6 |
| z-ai/glm-5 | 1709 ms | 1709 ms | — | 100.00% | — | 8 |
| z-ai/glm-5.2 | 2057 ms | 2057 ms | 69 tok/s n=1 | 100.00% | — | 6 |
| nvidia/nemotron-nano-12b-v2-vl | 2243 ms | 2243 ms | — | 100.00% | — | 1 |
| qwen/qwen3-32b | 2353 ms | 2353 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v3.2 | 2712 ms | 2712 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 2915 ms | 2915 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-pro | 3312 ms | 3311 ms | 60 tok/s n=1 | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash | 4449 ms | 4449 ms | 14 tok/s n=2 | 100.00% | — | 2 |
| z-ai/glm-5.1 | 4954 ms | 4954 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-super-120b | 4043 ms | 4043 ms | — | 71.43% | — | 7 |