Inference Overview

WiLine Edge Cloud Inference gives you a single endpoint to run large language models, generate embeddings, transcribe audio, and synthesize speech. The API is fully OpenAI-compatible — any SDK or tool that works with OpenAI works here unchanged, by pointing base_url at https://inference.wiline.com/v1.

---

Open the Overview

After logging in to the WiLine Edge Cloud:

1. In the left sidebar, expand Inference.
2. Click Overview.

You'll land on a page with four areas: the Start building quickstart, three action cards (create a key, code examples, playground), the Most popular models list, and a link to all model endpoints.

Figure 1: The Inference Overview — the Start building quickstart, the create-key / code-examples / playground cards, the Most popular models list, and the link to all model endpoints.

---

Before you start

You need an API key to authenticate every request. Keys are account-scoped and give access to every model on your endpoint.

Go to API Keys to create one, then save it as an environment variable:

export WEC_API_KEY="your-key-here"

Use a separate key per app or environment (dev, staging, production) so you can rotate or revoke one without affecting the others.

---

Make your first request

Base URL: https://inference.wiline.com/v1

cURL

curl https://inference.wiline.com/v1/chat/completions \
  -H "Authorization: Bearer $WEC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.wiline.com/v1",
    api_key=os.environ["WEC_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(resp.choices[0].message.content)

Available endpoints

The API exposes 7 endpoints covering chat, text completion, embeddings, audio transcription, speech synthesis, and model discovery. See the API Reference for the full interactive list — parameters, request schemas, response schemas, and a live request builder for every endpoint.

---

Where to go from here

API Reference

Interactive docs for every endpoint — parameters, request schemas, response schemas, and a live request builder.

Code Examples

Copy-paste snippets for chat, streaming, tool calling, embeddings, and audio — in cURL and Python.

Playground

Chat with any model in the browser. Tune prompts, switch models, and adjust parameters — no code required.

Models Hub

Browse every available model with its context window, capabilities, streaming support, and pricing.

---

Most popular models

Model	Provider	Tags	Description
deepseek-ai/DeepSeek-V3.1	DeepSeek	Reasoning, 128K	State-of-the-art reasoning model with a 128k context window and tool calling support.
z-ai/GLM-5.2	Z.ai	Reasoning, 1M	High-capacity MoE model with a 1M token context window.
meta/llama-4-maverick	Meta	Text + Vision, 1M	Multimodal MoE model supporting text and image input with a 1M context window.

note

Prices shown per 1M tokens. Check the Models Hub or WEC pricing page for current rates.