OpenAI compatible API · Attested · Public status
DigitalOcean Gradient AI
DigitalOcean Gradient AI models on TrustedRouter with prices, routes, policy notes, and source links.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
digitalocean
No provider claim
| Provider | DigitalOcean Gradient AI |
|---|---|
| Models | 23 public models |
| Prepaid routes | 23 |
| BYOK routes | 23 |
| 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
189 samplesContinuously sampled across DigitalOcean Gradient AI's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 3923 ms |
|---|---|
| Throughput | — |
| Uptime | 94.71% |
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| mistralai/ministral-3-14b-instruct | 1111 ms | 1111 ms | — | 100.00% | — | 6 |
| minimax/minimax-m2.5 | 1526 ms | 1526 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 1534 ms | 1534 ms | — | 100.00% | — | 6 |
| meta-llama/llama-4-maverick | 1821 ms | 1821 ms | — | 80.00% | — | 5 |
| moonshotai/kimi-k2.5 | 2157 ms | 2157 ms | — | 100.00% | — | 11 |
| deepseek/deepseek-v3.2 | 2419 ms | 2418 ms | — | 100.00% | — | 10 |
| nvidia/nemotron-3-nano-omni | 2713 ms | 2712 ms | — | 100.00% | — | 7 |
| nvidia/nemotron-nano-12b-v2-vl | 2998 ms | 2997 ms | — | 83.33% | — | 6 |
| xiaomi/mimo-v2.5-pro | 3065 ms | 3065 ms | — | 100.00% | — | 8 |
| google/gemma-4-31b-it | 3799 ms | 3799 ms | — | 100.00% | — | 12 |
| z-ai/glm-5 | 3842 ms | 3842 ms | — | 100.00% | — | 11 |
| deepseek/deepseek-r1-distill-llama-70b | 3862 ms | 3862 ms | — | 83.33% | — | 6 |
| meta-llama/llama-3.3-70b-instruct | 3923 ms | 3923 ms | — | 100.00% | — | 7 |
| nvidia/nemotron-3-super-120b | 3986 ms | 3986 ms | — | 100.00% | — | 11 |
| qwen/qwen3-32b | 4575 ms | 4575 ms | — | 100.00% | — | 11 |
| deepseek/deepseek-v4-pro | 4639 ms | 4639 ms | — | 100.00% | 1 unsupported_route |
7 |
| deepseek/deepseek-v4-flash | 5942 ms | 5942 ms | — | 87.50% | — | 8 |
| z-ai/glm-5.2 | 6494 ms | 6493 ms | — | 100.00% | — | 12 |
| qwen/qwen3-coder-flash | 7333 ms | 7333 ms | — | 100.00% | — | 8 |
| qwen/qwen3.5-397b-a17b | 7350 ms | 7350 ms | — | 62.50% | 1 unsupported_route |
8 |
| xiaomi/mimo-v2.5 | 8583 ms | 8583 ms | — | 100.00% | — | 10 |
| nvidia/nemotron-3-ultra-550b | 9108 ms | 9108 ms | — | 87.50% | — | 8 |
| z-ai/glm-5.1 | 12467 ms | 12467 ms | — | 75.00% | — | 8 |
DigitalOcean Gradient AI performance history · Full provider & model leaderboard.
Provider models
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 | $1.0395/1M | $1.0395/1M | prepaid BYOK |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 104#54 | 163,840 | 2 | $0.44625/1M | $1.428/1M | prepaid BYOK |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash |
IQ 109#42 | 1,048,576 | 2 | $0.1176/1M | $0.2352/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 114#27 | 1,048,576 | 2 | $1.4616/1M | $2.9232/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#65 | 262,144 | 2 | $0.189/1M | $0.525/1M | prepaid BYOK |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 2 | $0.6825/1M | $0.6825/1M | prepaid BYOK |
meta-llama/llama-4-maverickMeta: Llama 4 Maverick |
IQ 90#90 | 1,048,576 | 2 | $0.2625/1M | $0.9135/1M | prepaid BYOK |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 106#52 | 204,800 | 2 | $0.23625/1M | $0.945/1M | prepaid BYOK |
mistralai/ministral-3-14b-instructMinistral 3 14B Instruct |
— | 262,144 | 2 | $0.21/1M | $0.21/1M | prepaid BYOK |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
IQ 111#39 | 262,144 | 2 | $0.39375/1M | $2.12625/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#19 | 262,144 | 2 | $0.798/1M | $3.36/1M | prepaid BYOK |
nvidia/nemotron-3-nano-omniNemotron Nano 3 Omni |
— | 65,536 | 2 | $0.525/1M | $0.945/1M | prepaid BYOK |
nvidia/nemotron-3-super-120bNemotron-3-Super-120B |
— | 1,000,000 | 2 | $0.2205/1M | $0.47775/1M | prepaid BYOK |
nvidia/nemotron-3-ultra-550bnvidia/NVIDIA-Nemotron-3-Ultra-550B |
— | 262,144 | 2 | $0.945/1M | $1.785/1M | prepaid BYOK |
nvidia/nemotron-nano-12b-v2-vlNemotron Nano 12B v2 VL |
— | 128,000 | 2 | $0.21/1M | $0.63/1M | prepaid BYOK |
qwen/qwen3-32bQwen: Qwen3 32B |
— | 131,072 | 2 | $0.2625/1M | $0.5775/1M | prepaid BYOK |
qwen/qwen3-coder-flashQwen3 Coder Flash |
— | 262,144 | 2 | $0.4725/1M | $1.785/1M | prepaid BYOK |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | 2 | $0.40425/1M | $2.5725/1M | prepaid BYOK |
xiaomi/mimo-v2.5Xiaomi: MiMo-V2.5 |
IQ 109#43 | 1,050,000 | 2 | $0.11025/1M | $0.294/1M | prepaid BYOK |
xiaomi/mimo-v2.5-proXiaomi: MiMo-V2.5-Pro |
IQ 113#33 | 1,050,000 | 2 | $0.63/1M | $3.15/1M | prepaid BYOK |
z-ai/glm-5Z.ai: GLM 5 |
IQ 106#50 | 204,800 | 2 | $0.7875/1M | $2.52/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 113#30 | 204,800 | 2 | $1.02375/1M | $4.515/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#16 | 1,048,576 | 2 | $1.1025/1M | $4.62/1M | prepaid BYOK |