LLM API

LLM API provides access to large language models (AI) via an OpenAI-compatible API. Use for chatbots, text generation, analysis and more.

What it is

The LLM API in WAYSCloud gives developers and teams access to powerful language models through an OpenAI-compatible interface. Use the same SDKs, libraries, and tools you already know — just point them at WAYSCloud.

All inference runs in EU datacenters. Choose from general-purpose, reasoning, and specialized coding models.

When to use

Use this when you need:

• AI-powered features in your applications (chat, summarization, generation)
• OpenAI-compatible integration with existing code and SDKs
• EU-hosted inference for data sovereignty and compliance
• Multiple model options for different use cases and budgets

When NOT to use:

• Image or video generation — use GPU Studio
• Audio transcription — use Speech Intelligence
• Pre-built chatbot with knowledge base — use Chatbot

How it works

The LLM API works like OpenAI's Chat Completions API:

1. Send a chat message with your chosen model
2. Receive a completion response (or stream tokens in real-time)
3. Optionally use reasoning models for step-by-step thinking

All requests are authenticated with your API key. Usage is billed per token.

Features

WAYSCloud LLM API is built for compatibility, performance, and data sovereignty.

Compatibility

• OpenAI-compatible Chat Completions API
• Works with official OpenAI SDKs (Python, Node.js, etc.)
• Streaming support for real-time token delivery

Models

• General-purpose models (Qwen, DeepSeek, Mixtral, LLaMA)
• Reasoning models with chain-of-thought (DeepSeek-R1, Qwen-Thinking)
• Specialized coding models (Qwen-Coder)
• Content moderation (LlamaGuard)

Infrastructure

• EU-hosted inference (no data leaves Europe)
• Per-token billing with no minimum commitment
• High availability with automatic failover

Getting started

All LLM API functionality is available via the WAYSCloud API.

List models

List available models (WAYSCloud endpoint)

curl https://api.wayscloud.services/v1/llm/models \
  -H "X-API-Key: YOUR_API_KEY"

List models

List available models (OpenAI-compatible endpoint)

Returns a list of all available LLM models.

Response Example:

{
  "object": "list",
  "data": [
    {"id": "mixtral-8x7b", "object": "model", "owned_by": "wayscloud"},
    {"id": "qwen3-80b-instruct", "object": "model", "owned_by": "wayscloud"}
  ]
}

curl https://api.wayscloud.services/v1/models \
  -H "X-API-Key: YOUR_API_KEY"

See all 5 endpoints in the LLM API reference.

Limits and quotas

Limits and quotas depend on the selected plan and region. See the dashboard or API for current constraints.

Related services

• Run an LLM Request — step-by-step API integration

• GPU Studio

• Chatbot (CaaS)

• Speech Intelligence

Open LLM API in dashboard