LlamaIndex

LlamaIndex: set the base URL and API key in integration code.

Published instructions · App version: unverified

Chat, ping, invoke and content-generation examples may send real billable requests. Check the model, balance, rate and minimum before running them. GET /v1/models checks authentication and the catalogue only. Set up environment variables safely

Base URL to paste

OpenAI SDKs generally use a URL ending in /v1; Anthropic SDKs use the root URL. Avoid adding /v1 twice. Protocol compatibility does not guarantee every provider feature.

https://thapi.cloud/v1

Prerequisites

pip install llama-index-llms-openai-like

Recommended model: claude-fable-5

Quick way — command / config

import os
from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="claude-fable-5",
    api_base="https://thapi.cloud/v1",
    api_key=os.environ["STALI_API_KEY"],
    context_window=1000000,
    is_chat_model=True,
)
print(llm.complete("Hello!"))

Where to place file / fill Settings

Environment variableany

STALI_API_KEY

Set STALI_API_KEY in the Python process environment using Quick start. A .env file is not loaded automatically; keep keys out of Git.

Verify connection

complete() returns text

Troubleshooting

Symptom	Reason	How to handle
Connection error	api_base is missing /v1.	api_base="https://thapi.cloud/v1"

LangChain