OVHcloud AI Endpoints logo

OVHcloud AI Endpoints

France EU EU hosted

OVHcloud AI Endpoints

OVHcloud AI Endpoints is a managed generative AI API service from France. It gives developers serverless access to pre-trained language, reasoning, vision, embedding, image, and speech models without requiring them to deploy inference infrastructure. Its OpenAI-compatible chat-completions and responses routes support common application patterns including text generation, structured output, and function calling. Access can be authenticated with API keys, and usage is billed according to the selected model.

Pricing

Usage-based pricing varies by model and task. Language-model input and output are priced per million tokens, and the public catalog shows the current rates for each model. Limited trial credits are available, but they are not an ongoing free plan.

Read more on the pricing page of the service.

Hosting

OVHcloud states that AI Endpoints runs on its own infrastructure in European data centers. Its documented OpenAI-compatible service endpoint uses the OVHcloud-operated ai.cloud.ovh.net domain.

Domain name Usage type Lookup type Hosting provider
oai.endpoints.kepler.ai.cloud.ovh.net Core Service Web Report
Other products in category Large language model (LLM) APIs
Scaleway Generative APIs logo

Scaleway Generative APIs

France EU EU hosted Free plan

Scaleway Generative APIs is a managed model-inference service from France. Its serverless APIs provide OpenAI-compatible access to language, reasoning, vision, audio, embedding, and reranking models, while dedicated deployments can serve curated or customer-selected models. Text-generation endpoints support chat completions, structured outputs, tool calling, streaming, and batch processing. Serverless usage is billed by token or task and includes an ongoing free tier.

Nebius Token Factory logo

Nebius Token Factory

Netherlands EU EU hosted

Nebius Token Factory provides managed inference for open-source language models through an OpenAI-compatible API. Developers can use it for chat completions, reasoning, code generation, embeddings, and related application workloads without managing model-serving infrastructure. Its public serverless endpoints use token-based billing, while optional dedicated endpoints provide reserved capacity and regional deployment controls. The service supports API-key authentication, a browser-based playground, and model-specific performance tiers.


Any suggestions?

Sign up for an account to suggest changes or new products.

Sign Up