DigitalOcean

digitalocean

Chat Code

Updated 1 hour ago

DigitalOcean is a cloud infrastructure provider that offers AI/ML model hosting through their Gradient AI Platform. The platform provides access to open-source LLMs including DeepSeek, Qwen, GLM, and others through an OpenAI-compatible API endpoint. DigitalOcean focuses on simplicity and developer experience, offering scalable GPU droplets and managed inference services for deploying and running AI models.

Visit Website LLMs.txt

Browse 21 LLM models available from DigitalOcean. Compare prices and features.

Models (21)

Organization	Model Name	Original Model	Input	Output
Z.ai	GLM-5.2	`glm-5.2`	$1.05	$4.40	View
DeepSeek	DeepSeek-V4-Pro-Max	`deepseek-v4-pro`	$1.74	$3.48	View
Moonshot AI	Kimi K2.6	`kimi-k2.6`	$0.95	$4.00	View
Z.ai	GLM-5.1	`glm-5.1`	$0.98	$4.30	View
google	Gemma 4 31B	`gemma-4-31B-it`	$0.18	$0.50	View
Minimax	MiniMax M2.5	`minimax-m2.5`	$0.30	$1.20	View
qwen	Qwen3.5-397B-A17B	`qwen3.5-397b-a17b`	$0.55	$3.50	View
Z.ai	GLM-5	`glm-5`	$1.00	$3.20	View
Moonshot AI	Kimi K2.5	`kimi-k2.5`	$0.50	$2.70	View
Meta	Llama 4 Maverick	`llama-4-maverick`	$0.25	$0.87	View
DeepSeek	DeepSeek R1 Distill Llama 70B	`deepseek-r1-distill-llama-70b`	$0.99	$0.99	View
DeepSeek	DeepSeek-V3	`deepseek-v3`	-	-	View
Meta	Llama 3.3 70B Instruct	`llama3.3-70b-instruct`	$0.65	$0.65	View
qwen	Qwen2.5 14B Instruct	`qwen-2.5-14b-instruct`	-	-	View
Mistral	Ministral 3 (8B Instruct 2512)	`ministral-3-8b-instruct-2512`	-	-	View
Nvidia	Nemotron Nano 12B 2 VL (free)	`nemotron-nano-12b-v2-vl`	$0.20	$0.60	View
Alibaba	Qwen3 Coder Flash	`qwen3-coder-flash`	$0.45	$1.70	View
Mistral	Mistral NeMo Instruct	`mistral-nemo-instruct-2407`	$0.30	$0.30	View
Mistral	Mistral 7B Instruct v0.3	`mistral-7b-instruct-v0.3`	-	-	View
Meta	llama-3-8b-instruct	`llama3-8b-instruct`	$0.20	$0.20	View
qwen	Qwen3 Embedding 0.6B	`qwen3-embedding-0.6b`	$0.04	$0.00	View

Back to Providers Visit Website