Skip to main content

Vultr

Cloud-hosted AI inference with serverless GPU computing for scalable language model serving.

Vultr

Cloud-hosted AI inference with serverless GPU computing for scalable language model serving.

Authentication

Auth Type
API Key
Platform Key
Not configured
Self-serve
Available

Add your Vultr API key from Organization → Integrations → AI Vendors. Keys are encrypted at rest and scoped to your organization.

Available Models

5 enabled models across 1 category.

Text5

DeepSeek V3.2DeepSeek-V3.2

chatModel, languageModel, completionModel

functionCalling

GLM 5 FP8GLM-5-FP8

chatModel, languageModel, completionModel

functionCalling

GPT OSS 120Bgpt-oss-120b

chatModel, languageModel, completionModel

functionCalling

Kimi K2 InstructKimi-K2.5

chatModel, languageModel, completionModel

functionCalling

MiniMax M2.5MiniMax-M2.5

chatModel, languageModel, completionModel

functionCalling