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
| Provider | DigitalOcean Gradient AI |
|---|---|
| Provider website | https://www.digitalocean.com/products/gradient-ai-platform |
| Models | 22 public models |
| Prepaid routes | 22 |
| BYOK routes | 22 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| 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
43 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 | 2402 ms |
|---|---|
| Effective throughput | 11 tok/s n=4 |
| Uptime | 90.70% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| moonshotai/kimi-k2.5 | 861 ms | 861 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-nano-12b-v2-vl | 904 ms | 904 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 1178 ms | 1177 ms | 54 tok/s n=1 | 100.00% | — | 2 |
| deepseek/deepseek-r1-distill-llama-70b | 1262 ms | 1262 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 1499 ms | 1499 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-flash | 1517 ms | 1516 ms | — | 100.00% | — | 1 |
| mistralai/ministral-3-14b-instruct | 1674 ms | 1674 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash | 1917 ms | 1917 ms | 8 tok/s n=2 | 100.00% | — | 2 |
| meta-llama/llama-4-maverick | 2047 ms | 2047 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v3.2 | 2402 ms | 2402 ms | — | 100.00% | — | 4 |
| google/gemma-4-31b-it | 2872 ms | 2872 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-nano-omni | 3155 ms | 3155 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v4-pro | 3766 ms | 3766 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 3806 ms | 3805 ms | 15 tok/s n=1 | 100.00% | — | 4 |
| nvidia/nemotron-3-ultra-550b | 3998 ms | 3997 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.5 | 4056 ms | 4056 ms | — | 100.00% | — | 1 |
| z-ai/glm-5 | 4728 ms | 4728 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.1 | 1458 ms | 1457 ms | — | 50.00% | — | 2 |
| nvidia/nemotron-3-super-120b | — | — | — | 0.00% | — | 3 |
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 | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-r1-distill-llama-70bDeepSeek: R1 Distill Llama 70B |
— | 8,192 | 2 | $1.04445/1M | $1.04445/1M | prepaid BYOK |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 103#64 | 163,840 | 2 | $0.26375/1M | $0.844/1M | prepaid BYOK |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#41 | 1,048,576 | 2 | $0.07174/1M | $0.17724/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 117#31 | 1,048,576 | 2 | $0.91785/1M | $1.8357/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#73 | 262,144 | 2 | $0.1899/1M | $0.5275/1M | prepaid BYOK |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 2 | $0.68575/1M | $0.68575/1M | prepaid BYOK |
meta-llama/llama-4-maverickMeta: Llama 4 Maverick |
IQ 90#103 | 1,048,576 | 2 | $0.211/1M | $0.73428/1M | prepaid BYOK |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 105#63 | 204,800 | 2 | $0.237375/1M | $0.9495/1M | prepaid BYOK |
mistralai/ministral-3-14b-instructMinistral 3 14B Instruct |
— | 262,144 | 2 | $0.211/1M | $0.211/1M | prepaid BYOK |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
IQ 111#46 | 262,144 | 2 | $0.395625/1M | $2.136375/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#23 | 262,144 | 2 | $0.8018/1M | $3.376/1M | prepaid BYOK |
nvidia/nemotron-3-nano-omniNemotron Nano 3 Omni |
— | 65,536 | 2 | $0.5275/1M | $0.9495/1M | prepaid BYOK |
nvidia/nemotron-3-super-120bNemotron-3-Super-120B |
— | 1,000,000 | 2 | $0.174075/1M | $0.37769/1M | prepaid BYOK |
nvidia/nemotron-3-ultra-550bNemotron 3 Ultra |
— | 131,072 | 2 | $0.9495/1M | $1.7935/1M | prepaid BYOK |
nvidia/nemotron-nano-12b-v2-vlNemotron Nano 12B v2 VL |
— | 128,000 | 2 | $0.211/1M | $0.633/1M | prepaid BYOK |
qwen/qwen3-32bQwen: Qwen3 32B |
— | 131,072 | 2 | $0.26375/1M | $0.58025/1M | prepaid BYOK |
qwen/qwen3-coder-flashQwen3 Coder Flash |
— | 262,144 | 2 | $0.47475/1M | $1.7935/1M | prepaid BYOK |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | 2 | $0.31861/1M | $2.030875/1M | prepaid BYOK |
xiaomi/mimo-v2.5-proXiaomi: MiMo-V2.5-Pro |
IQ 115#36 | 1,050,000 | 2 | $0.422/1M | $1.5825/1M | prepaid BYOK |
z-ai/glm-5Z.ai: GLM 5 |
IQ 105#60 | 204,800 | 2 | $0.79125/1M | $2.532/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#38 | 204,800 | 2 | $1.028625/1M | $4.5365/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#19 | 1,048,576 | 2 | $0.7385/1M | $2.321/1M | prepaid BYOK |
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 22 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.