N

nexusai-client

Free

An ultra-lightweight, asynchronous Python 3.14 client to centralize and unify calls across AI providers (Cerebras, Cohere, DeepSeek, Gemini, Groq, Mistral, Nvidia NIM, OpenRouter, OrcaRouter). Powered by uv. - laurent...

Visit Website
Related by shared tags and keywordskimss-python-quickstartZotGPTmodel-tracker
generative-aiai-gatewayasynciodeepseekgeminiaiai assistantautomation

Overview

NexusAI-Client is an ultra-lightweight, strictly-typed, asynchronous Python 3.12+ gateway for multi-provider AI APIs. It unifies Cerebras, Cohere, DeepSeek, Google Gemini (Free & Pro), Groq, Mistral, Nvidia NIM, OpenRouter, and OrcaRouter behind a single interface with zero heavy SDK dependencies. The project is powered purely by httpx and python-dotenv.

It provides dynamic model management and auto-rotation, with automatic failover on HTTP 404/400 (deprecated models), HTTP 429 rate limits, and timeouts across models and providers. It supports native asynchronous and SSE streaming, allowing responses to be streamed token-by-token via stream_text() and stream_chat(). It also offers zero-cost-first smart fallback, automatically progressing from free tiers to paid backups via AIGateway.auto_fallback().

Additional capabilities include universal tool calling/function calling, guaranteed JSON outputs with json_mode=True, live account and budget inspection, and live discovery of 670+ models. It supports enterprise reasoning and search models, and native hardware accelerators such as Groq LPUs and Cerebras CS-3 Wafer-Scale engines.

Pricing

Free

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Visit Website

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

  • Teams use NexusAI-Client to unify multiple AI providers behind a single interface.
  • Teams use NexusAI-Client to stream AI responses token-by-token in real time.
  • Teams use NexusAI-Client to automatically fail over across models and providers on rate limits, deprecated models, and timeouts.
  • Teams use NexusAI-Client to prioritize free tiers before paid backups.
  • Teams use NexusAI-Client to obtain guaranteed structured JSON outputs.
  • Teams use NexusAI-Client to inspect real-time account balances and rate limits.
  • Teams use NexusAI-Client to build autonomous AI agents with universal tool calling.
  • Teams use NexusAI-Client to analyze images, charts, and PDFs with multimodal vision.

Features

Unifies calls across AI providers

Supports asynchronous Python requests

Connects to Cerebras and Cohere

Connects to DeepSeek and Gemini

Connects to Groq and Mistral

Supports Nvidia NIM and OpenRouter

Reviews

No reviews yet. Be the first to share your experience!