Run open models in production

For teams building AI products: call open models through one OpenAI‑compatible API, billed per token, or reserve a dedicated endpoint.

Start building Talk to an expert

Serverless inference

Call any open model in our catalogue through one OpenAI‑compatible API. Billed per token, with no base fee.

Start building API documentation

Prompt caching

Repeated prompt starts still in GPU memory are billed at the cached input price, where listed.

request.sh

BASE_URL=https://api.lyceum.technology/openai/v1

curl $BASE_URL/chat/completions \
  -H "Authorization: Bearer $LYCEUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Base URL
Runs in European data centres.
OpenAI‑compatible, and Anthropic‑compatible for Claude Code
Any of 23 open models
Billed per token, no base feeGLM-5.3: $1.40 input, $4.40 output per million tokens

Dedicated endpoints

Reserved capacity
GPUs reserved for your endpoint, planned around your production workload.
Model configuration
Agreed before launch, so your model fits your workload.
Where it runs
The data centre is agreed for your workload. Tell us if you need a specific EU location.
Commercial terms
Commitment pricing, agreed per contract, so you know the cost before you launch.

Talk to an expert

Which option fits your workload

Per-token billing follows your traffic, so quiet hours cost nothing. A dedicated endpoint is priced for the capacity you reserve, so the busier you keep it, the less each token costs.

Need the whole machine?

Explore Compute

Per token costs lessTraffic comes and goes: stay on the API.

Dedicated costs lessSteady all day: ask us to price it against your token bill.

Bring the tools you already use

Serverless or dedicated, you call it through the same OpenAI‑compatible API. Create a key in your dashboard, then point Claude Code, OpenCode or your own app at it.

Claude Code

Point Claude Code at our Anthropic-compatible endpoint and choose a supported open model.

Set up Claude Code Walkthrough with GLM-5.3 Flash

Terminal

export ANTHROPIC_BASE_URL="https://api.lyceum.technology/anthropic"
export ANTHROPIC_AUTH_TOKEN="$LYCEUM_API_KEY"
export ANTHROPIC_MODEL="z-ai/glm-5.3"

claude

Install Claude Code and set LYCEUM_API_KEY

OpenCode

Add Lyceum as a custom OpenAI-compatible provider, with your endpoint and model.

Set up OpenCode OpenCode provider guide

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "lyceum/z-ai/glm-5.3",
  "provider": {
    "lyceum": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.lyceum.technology/openai/v1",
        "apiKey": "{env:LYCEUM_API_KEY}"
      },
      "models": {
        "z-ai/glm-5.3": { "name": "GLM-5.3" }
      }
    }
  }
}

Save in your project and set LYCEUM_API_KEY

Your application

Use any OpenAI-compatible client. Set the base URL, your API key and a model ID.

API quickstart API documentation

app.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LYCEUM_API_KEY"],
    base_url="https://api.lyceum.technology/openai/v1",
)

response = client.chat.completions.create(
    model="z-ai/glm-5.3",
    messages=[{"role": "user", "content": "Hello!"}],
)

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