Skills
.Work. You
Rest

omniroute-chat

Community

Chat and generate code with auto-fallback providers.

Software Engineering#code-generation#tool-use#provider-routing#sse-streaming#token-compression#llm-chat#auto-fallback
Authordiegosouzapw
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It solves the problem of flaky model access and rate limits when trying to call many different AI providers for chat, code generation, or reasoning-based tasks.

Core Features & Use Cases

  • OpenAI-compatible and Anthropic-compatible chat endpoints: Send prompts in the /v1/chat/completions or /v1/messages formats (and optionally /v1/responses) with SSE streaming.
  • Combo auto-fallback routing: Use routing “combos” (like auto, cost-optimized, subscription) to automatically fail over across multiple providers.
  • Token savings via RTK compression: Reduces tokens for tool outputs and reasoning/context to help avoid limits, with an option to disable via X-Omniroute-Rtk: off.
  • Tool-use support: Works with OpenAI tools and Anthropic tools blocks, compressing tool results to save tokens.

Quick Start

Ask your AI client to call POST to $OMNIROUTE_URL/v1/chat/completions (or $OMNIROUTE_URL/v1/messages) with Authorization: Bearer $OMNIROUTE_KEY, streaming enabled, and a model name you want to route.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: omniroute-chat
Download link: https://github.com/diegosouzapw/OmniRoute/archive/main.zip#omniroute-chat

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.