LlamaIndex LLMs Integration: Apertis

Apertis provides a unified API gateway to access multiple LLM providers including OpenAI, Anthropic, Google, and more through an OpenAI-compatible interface.

Installation

pip install llama-index-llms-apertis

Supported Endpoints

Apertis supports multiple API formats:

Setup

Get Your API Key

Obtain your API key from Apertis API.

Initialize Apertis

You can set either the environment variable APERTIS_API_KEY or pass your API key directly in the class constructor:

from llama_index.llms.apertis import Apertis
from llama_index.core.llms import ChatMessage

llm = Apertis(
    api_key="<your-api-key>",
    model="gpt-5.2",
)

Or using environment variables:

export APERTIS_API_KEY="<your-api-key>"

from llama_index.llms.apertis import Apertis

llm = Apertis(model="gpt-5.2")

Generate Chat Responses

Send a list of ChatMessage instances to generate a chat response:

from llama_index.core.llms import ChatMessage

message = ChatMessage(role="user", content="Tell me a joke")
resp = llm.chat([message])
print(resp)

Streaming Responses

To stream responses, use the stream_chat method:

message = ChatMessage(role="user", content="Tell me a story in 250 words")
resp = llm.stream_chat([message])
for r in resp:
    print(r.delta, end="")

Complete with Prompt

Generate completions with a prompt using the complete method:

resp = llm.complete("Tell me a joke")
print(resp)

Streaming Completion

To stream completions, use the stream_complete method:

resp = llm.stream_complete("Tell me a story in 250 words")
for r in resp:
    print(r.delta, end="")

Supported Models

Apertis supports models from multiple providers:

Using Different Models

# Using Claude
llm = Apertis(
    api_key="<your-api-key>",
    model="claude-sonnet-4.5",
)

# Using Gemini
llm = Apertis(
    api_key="<your-api-key>",
    model="gemini-3-flash-preview",
)

Configuration Options

Documentation

For more information, visit the Apertis Documentation.