DigitalOcean Gradient AI
Explore DigitalOcean Gradient AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
DigitalOcean Gradient AIdigitalocean
No provider claim
These privacy labels describe DigitalOcean Gradient AI, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | DigitalOcean Gradient AI |
|---|---|
| Routing status | Active |
| Provider website | https://www.digitalocean.com/products/gradient-ai-platform |
| Models | 14 public models |
| Credits routes | 14 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | No provider-ZDR claim is tracked here. DigitalOcean's Gradient AI model and pricing documentation is linked for data-handling review. Policy source |
Measured performance
30 samplesContinuously sampled across DigitalOcean Gradient AI's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1413 ms |
|---|---|
| Effective throughput | 46 tok/s n=6 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| minimax/minimax-m2.5 | 896 ms | — | 100.00% | — | 2 |
| xiaomi/mimo-v2.5-pro | 1109 ms | 62 tok/s n=2 | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 1258 ms | — | 100.00% | — | 5 |
| nvidia/nemotron-3-nano-omni | 1388 ms | — | 100.00% | — | 2 |
| mistralai/ministral-3-14b-instruct | 1413 ms | — | 100.00% | — | 5 |
| nvidia/nemotron-nano-12b-v2-vl | 1435 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 1587 ms | 16 tok/s n=1 | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash | 1721 ms | 46 tok/s n=2 | 100.00% | — | 2 |
| meta-llama/llama-4-maverick | 2018 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b | 3145 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 3585 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-397b-a17b | 3753 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.2 | — | 6 tok/s n=1 | — | — | 0 |
DigitalOcean Gradient AI performance history · Full provider & model leaderboard.
Models served by DigitalOcean Gradient AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 103#77 | 163,840 | $0.26375/1M | $0.079125/1M | $0.844/1M |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 116#37 | 1,048,576 | $0.07174/1M | $0.017935/1M | $0.17724/1M |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 114#47 | 1,048,576 | $0.91785/1M | $0.18357/1M | $1.8357/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 103#80 | 262,144 | $0.1899/1M | $0.03798/1M | $0.5275/1M |
meta-llama/llama-4-maverickMeta: Llama 4 Maverick |
IQ 85#127 | 128,000 | $0.211/1M | Not published | $0.73428/1M |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 106#74 | 196,608 | $0.3165/1M | $0.0633/1M | $1.266/1M |
mistralai/ministral-3-14b-instructMinistral 3 14B Instruct |
— | 262,144 | $0.211/1M | Not published | $0.211/1M |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 118#35 | 262,144 | $1.00225/1M | $0.20045/1M | $4.22/1M |
nvidia/nemotron-3-nano-omniNemotron Nano 3 Omni |
— | 65,536 | $0.5275/1M | Not published | $0.9495/1M |
nvidia/nemotron-3-ultra-550bNemotron 3 Ultra |
— | 131,072 | $0.9495/1M | Not published | $1.7935/1M |
nvidia/nemotron-nano-12b-v2-vlNemotron Nano 12B v2 VL |
— | 128,000 | $0.211/1M | Not published | $0.633/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.58025/1M | $0.117105/1M | $3.6925/1M |
xiaomi/mimo-v2.5-proXiaomi: MiMo-V2.5-Pro |
IQ 112#55 | 1,050,000 | $0.422/1M | $0.0844/1M | $1.5825/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#28 | 1,048,576 | $0.7385/1M | $0.110775/1M | $2.321/1M |
Questions
Does DigitalOcean Gradient AI have zero data retention?
TrustedRouter does not currently mark DigitalOcean Gradient AI as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is DigitalOcean Gradient AI end-to-end encrypted?
TrustedRouter does not currently mark DigitalOcean Gradient AI as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which DigitalOcean Gradient AI models are available through TrustedRouter?
This page currently lists 14 public DigitalOcean Gradient AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.