upgreat.ai

LLM API

Quickstart

From zero to your first completion in three steps.

1. Get a key

Create an inference key in the Console under Inference API → Keys and export it:

bash
export UPGREAT_API_KEY="sk-..."

2. List the models

A quick way to confirm the key works and see what you can call:

bash
curl https://llm.upgreat.ai/v1/models \
  -H "Authorization: Bearer $UPGREAT_API_KEY"

3. Send a chat completion

Use the official OpenAI SDK, or plain HTTP:

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.upgreat.ai/v1",
    api_key="$UPGREAT_API_KEY",
)

resp = client.chat.completions.create(
    model="qwen3.6-27b",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Give me three uses for embeddings."},
    ],
    max_tokens=300,
)

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

Pip / npm

Install the SDK with pip install openai or npm install openai. Both target the OpenAI wire format the LLM API implements.

Where to go next