Changelog

• Before: 30-55ms
• After: 5-10ms (cache hits) / 15-25ms (cache misses)
• Estimated improvement: 40-80% latency reduction

Add comprehensive SDK features (v0.2.0) New Features:

• Vision/Image support with create_with_image() convenience method
• Audio input/output support
• Video content support
• Web Search with create_with_web_search() convenience method
• Reasoning Mode support (glm-4.7)
• Extended Thinking (Gemini) support
• Models API (list, retrieve)
• Responses API (OpenAI format)
• Messages API (Anthropic format)
• Rerank API (BAAI/bge-reranker-v2-m3, Qwen models)
• Helper utilities for base64 encoding

Includes 81 unit tests covering all new functionality.

PyPI Package: https://pypi.org/project/apertis/

Fix API response compatibility issues (v0.1.1)

• Make id, object, created fields optional in ChatCompletion
• Make id, object, created, model fields optional in ChatCompletionChunk
• Make Usage fields optional to handle empty usage objects in streaming
• Fix streaming by using httpx send() with stream=True instead of stream context manager

Tested with real API calls:

• Chat completions: working
• Streaming: working
• Embeddings: working
• Tool calling: working

🎉 Apertis Python SDK Released

We're excited to announce the official release of the Apertis Python SDK, now available on PyPI.

This SDK enables Python developers to integrate Apertis into their applications with ease, providing unified access to 470+ AI models across multiple providers through a single, consistent API.

---

📦 Installation

pip install apertis

PyPI: https://pypi.org/project/apertis

Highlights

• Official Python SDK: First-party Apertis SDK for Python developers.
• 470+ Models via One API
• Access models from OpenAI, Anthropic, Google, and more through Apertis.
• Unified Interface: Consistent request and response patterns for chat and embeddings.
• Production-Ready

Designed for reliability, extensibility, and integration into real-world Python workflows.

🆕 Changelog

v1.0.0 — Initial Release

• Initial public release of the Apertis Python SDK
• Support for chat-based text generation
• Support for text embedding models
• Unified API client with Apertis authentication
• Flexible model routing via Apertis model IDs
• Pythonic SDK design for scripts, services, and notebooks

Resources

• PyPI: https://pypi.org/project/apertis/
• Documentation: https://docs.apertis.ai
• GitHub: https://github.com/apertis-ai
• Model Pricing: https://apertis.ai/models

We're excited to support the Python community and can't wait to see what you build with Apertis 🚀

🎉 Apertis Is Now an Official Community Provider in Vercel AI SDK

Great news — Apertis is now officially listed as a Community Provider in the Vercel AI SDK.

Our provider has been merged into the official AI SDK repository and is now available on the Vercel AI SDK website, making Apertis a first-class option for developers building with the AI SDK ecosystem.

---

✅ Officially Live

• 🔗 Vercel AI SDK Community Providers

https://ai-sdk.dev/providers/community-providers/apertis

• 📦 NPM Package

https://www.npmjs.com/package/@apertis/ai-sdk-provider

---

What This Means for Developers

• Official AI SDK Integration

Apertis is now recognized and documented as a community provider by the Vercel AI SDK team.

• 470+ Models via One Provider

Access OpenAI, Anthropic, Google, and many more models through Apertis.

• Drop-in AI SDK Experience

Use Apertis with the same generateText, streaming, tool calling, and embedding APIs you already know.

• Production-Ready

Fully compatible with AI SDK 6+ and the LanguageModelV3 specification.

---

Quick Example

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

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