OpenAI compatible API · Attested · Public status
DigitalOcean Gradient AI performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for DigitalOcean Gradient AI.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
digitalocean
209 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 | — |
|---|---|
| p95 TTFT | — |
| p50 TTFB | — |
| Effective throughput | — |
| Uptime | 0.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| deepseek/deepseek-r1-distill-llama-70b | — | — | — | 0.00% | — | 9 |
| deepseek/deepseek-v3.2 | — | — | — | 0.00% | — | 11 |
| deepseek/deepseek-v4-flash | — | — | — | 0.00% | — | 3 |
| deepseek/deepseek-v4-pro | — | — | — | 0.00% | — | 9 |
| google/gemma-4-31b-it | — | — | — | 0.00% | — | 15 |
| meta-llama/llama-3.3-70b-instruct | — | — | — | 0.00% | — | 7 |
| meta-llama/llama-4-maverick | — | — | — | 0.00% | — | 9 |
| minimax/minimax-m2.5 | — | — | — | 0.00% | — | 9 |
| mistralai/ministral-3-14b-instruct | — | — | — | 0.00% | — | 9 |
| moonshotai/kimi-k2.5 | — | — | — | 0.00% | — | 14 |
| moonshotai/kimi-k2.6 | — | — | — | 0.00% | — | 13 |
| nvidia/nemotron-3-nano-omni | — | — | — | 0.00% | — | 5 |
| nvidia/nemotron-3-super-120b | — | — | — | 0.00% | — | 11 |
| nvidia/nemotron-3-ultra-550b | — | — | — | 0.00% | — | 10 |
| nvidia/nemotron-nano-12b-v2-vl | — | — | — | 0.00% | — | 11 |
| qwen/qwen3-32b | — | — | — | 0.00% | — | 9 |
| qwen/qwen3-coder-flash | — | — | — | 0.00% | — | 11 |
| qwen/qwen3.5-397b-a17b | — | — | — | 0.00% | — | 5 |
| xiaomi/mimo-v2.5-pro | — | — | — | 0.00% | — | 5 |
| z-ai/glm-5 | — | — | — | 0.00% | — | 12 |
| z-ai/glm-5.1 | — | — | — | 0.00% | — | 8 |
| z-ai/glm-5.2 | — | — | — | 0.00% | — | 14 |