Changelog

Add GLM 4.7 Flash

🎉 Apertis is Now an Official LiteLLM Model Provider

We're proud to announce that Apertis has become an official model provider for LiteLLM.

With this integration, LiteLLM users can route requests to 470+ AI models through Apertis while retaining LiteLLM’s powerful proxy, routing, and observability features.

---

✨ Highlights

• Official LiteLLM Provider

Apertis is now natively supported as a model provider within the LiteLLM SDK ecosystem.

• Multi-Model Access via Apertis

Access OpenAI, Anthropic, Google, and more through a single provider configuration.

• Seamless LiteLLM Compatibility

Works with existing LiteLLM proxy, routing, fallback, and load-balancing setups.

• Centralized Authentication & Usage Control

Simplify API key management and cost tracking via Apertis.

---

🚀 Getting Started

Configure Apertis as a provider in LiteLLM:

• https://docs.litellm.ai/docs/providers/apertis
• https://docs.apertis.ai

---

We're excited to work closely with the LiteLLM community and enable more flexible, scalable multi-model deployments with Apertis.

🎉 Apertis is Now an Official LlamaIndex Model Provider

We're excited to announce that Apertis is now an official model provider for LlamaIndex.

This integration allows LlamaIndex users to seamlessly access 470+ models across multiple providers through Apertis, using a single, unified API.

---

✨ What This Means

• Native Provider Integration

Apertis is now recognized as an official model provider in the LlamaIndex ecosystem.

• 470+ Models via One Gateway reminder

Use OpenAI, Anthropic, Google, and more without changing your application logic.

• Drop-in Compatibility

Works seamlessly with existing LlamaIndex workflows and abstractions.

• Unified Auth & Billing

Manage keys, usage, and costs centrally through Apertis.

---

🚀 Getting Started

Refer to the LlamaIndex documentation to configure Apertis as your model provider:

• https://docs.apertis.ai
• https://www.llamaindex.ai

---

🔗 Resources

• https://developers.llamaindex.ai/python/examples/llm/apertis/
• https://docs.apertis.ai/installation/llamaindex

---

We're excited to support the LlamaIndex community and look forward to enabling more flexible, multi-model AI applications with Apertis.

🚀 @apertis/ai-sdk-provider v1.1.1

We're excited to announce the release of `@apertis/ai-sdk-provider`, the official Apertis provider for the Vercel AI SDK.

This release brings full compatibility with AI SDK 6+ and unlocks seamless access to 470+ AI models across multiple providers — all through a single, unified interface.

---

✨ Key Highlights

• AI SDK 6+ Compatible

Fully implements the LanguageModelV3 specification.

• 470+ Models, One Provider

Access models from OpenAI, Anthropic, Google, and more via Apertis.

• Chat & Embeddings Support

Built-in support for both chat generation and text embeddings.

• Streaming Out of the Box

Real-time streaming responses with zero additional setup.

• Native Tool Calling

First-class support for function / tool calling.

---

📦 Installation

npm install @apertis/ai-sdk-provider ai

⚡ Quick Start

import { apertis } from '@apertis/ai-sdk-provider';
import { generateText } from 'ai';

const { text } = await generateText({
  model: apertis('gpt-5.2-chat'),
  prompt: 'Hello, world!',
});

console.log(text);

🆕 What's New in v1.1.1

• Implemented ProviderV3 interface for full AI SDK 6+ compatibility
• Added embedding model support via apertis.textEmbeddingModel()
• Improved API response schema flexibility
• Removed deprecated completion model endpoint

🔗 Resources

• https://www.npmjs.com/package/@apertis/ai-sdk-provider
• https://github.com/apertis-ai/apertis-sdk
• https://docs.apertis.ai
• https://apertis.ai/token