Agent skill

9Router AI Gateway Setup

by decolua in decolua/9router

Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.

MITAuto-check passedAI & LLM Engineering

Install 9Router AI Gateway Setup

skills CLI
$ npx skills add decolua/9router --skill 9router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install decolua/9router 9router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/9router .claude/skills/9router && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
9router
GitHub stars
30k
Token cost
~744 tokens
SKILL.md length
110 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.

  • Pointing an agent at a 9Router gateway for the first time
  • SKILL.md covers Setup, Discover models, Capability skills and Errors
  • Calls curl; needs NINEROUTER_KEY
  • Finding which models a 9Router instance offers for images or speech

What it does

9Router is a local or remote AI gateway that offers one key and many providers with automatic fallback behind OpenAI-compatible REST. Setup is two environment variables, NINEROUTER_URL, which defaults to a local address on port 20128 or can be a server or tunnel URL, and NINEROUTER_KEY, taken from the dashboard and needed only when API keys are required. Requests go to the v1 paths with a bearer header, and a health endpoint confirms the gateway is up.

Models are discovered by kind: separate listing endpoints return chat models, image models, text-to-speech models and others, and the id field of each entry is the model name to use. Combos show up with the owner set to combo.

The skill is an entry point that indexes capability skills for chat and code generation, image generation, text-to-speech, speech-to-text, embeddings, web search and web fetch, each fetched from a raw GitHub URL when needed. Common errors are mapped to fixes: 401 means refresh the key, 400 on model format means check the model list, and 503 means wait for the retry-after time or add a provider account.

When your agent uses it

  • Pointing an agent at a 9Router gateway for the first time
  • Finding which models a 9Router instance offers for images or speech
  • Calling chat, embeddings or web search through one OpenAI-compatible endpoint
  • Debugging 401, 400 or 503 errors from the gateway

Example prompts

  • “Set up NINEROUTER_URL for my local 9Router and check the health endpoint.”
  • “List the image generation models my 9Router exposes.”
  • “I get a 503 All accounts unavailable from 9Router, so what should I do?”

Requirements

  • A running 9Router instance with its URL in NINEROUTER_URL
  • NINEROUTER_KEY, when the gateway requires an API key

What it can do on your machine

Read from SKILL.md and the folder at commit a99cf57. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • NINEROUTER_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

9Router AI Gateway Setup loads about 744 tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 110 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~744

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from decolua/9router at commit a99cf57, republished under its MIT licence (© decolua). 110 words, ~744 tokens.

Download SKILL.mdSave it as .claude/skills/9router/SKILL.md (or your agent's skills folder).
name
9router
description
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.

9Router

Local/remote AI gateway exposing OpenAI-compatible REST. One key, many providers, auto-fallback.

Setup

bash
export NINEROUTER_URL="http://localhost:20128"      # or VPS / tunnel URL
export NINEROUTER_KEY="sk-..."                      # from Dashboard → Keys (only if requireApiKey=true)

All requests: ${NINEROUTER_URL}/v1/... with header Authorization: Bearer ${NINEROUTER_KEY} (omit if auth disabled).

Verify: curl $NINEROUTER_URL/api/health → {"ok":true}

Discover models

bash
curl $NINEROUTER_URL/v1/models                  # chat/LLM (default)
curl $NINEROUTER_URL/v1/models/image            # image-gen
curl $NINEROUTER_URL/v1/models/tts              # text-to-speech
curl $NINEROUTER_URL/v1/models/embedding        # embeddings
curl $NINEROUTER_URL/v1/models/web              # web search + fetch (entries have `kind` field)
curl $NINEROUTER_URL/v1/models/stt              # speech-to-text
curl $NINEROUTER_URL/v1/models/image-to-text    # vision

Use data[].id as model field in requests. Combos appear with owned_by:"combo".

Response shape:

json
{ "object": "list", "data": [
  { "id": "openai/gpt-5", "object": "model", "owned_by": "openai", "created": 1735000000 },
  { "id": "tavily/search", "object": "model", "kind": "webSearch", "owned_by": "tavily", "created": 1735000000 }
]}

Capability skills

When the user needs a specific capability, fetch that skill's SKILL.md from its raw URL:

Errors

  • 401 → set/refresh NINEROUTER_KEY (Dashboard → Keys)
  • 400 Invalid model format → check model exists in /v1/models/<kind>
  • 503 All accounts unavailable → wait retry-after or add another provider account

© decolua, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/9router of decolua/9router.

Open the folder on GitHubat commit a99cf57

Compare with similar skills

9Router AI Gateway Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

9Router AI Gateway Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
9Router AI Gateway Setup this skilldecolua/9router30k—~744Automated safety check: PassMIT
Using Ccproxy Inspectorstarbaser/ccproxy350—~2.7kAutomated safety check: PassCustom licence
Using Ccproxy APIstarbaser/ccproxy350—~4kAutomated safety check: PassCustom licence
ClawRouter LLM GatewayBlockRunAI/ClawRouter6.6k—~6.8kAutomated safety check: PassMIT
Caching Architecturemajiayu000/litellm-rs117—~2kAutomated safety check: PassMIT
Neon AI Gatewayneondatabase/agent-skills100—~5.1kAutomated safety check: NotesApache-2.0

Similar skills

  • Using Ccproxy Inspector

    starbaser/ccproxy

    Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic.

    350 GitHub stars~2.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Using Ccproxy API

    starbaser/ccproxy

    Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting.

    350 GitHub stars~4k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • ClawRouter LLM Gateway

    BlockRunAI/ClawRouter

    Describes ClawRouter, a local proxy that forwards each LLM request to the blockrun.ai gateway, which routes to a cheaper capable model, paid by USDC wallet or API key credit.

    6.6k GitHub stars~6.8k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Caching Architecture

    majiayu000/litellm-rs

    LiteLLM-RS response caching architecture. An agent skill from majiayu000/litellm-rs.

    117 GitHub stars~2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Neon AI Gateway

    neondatabase/agent-skills

    Official

    One API and one credential for frontier and open-source LLMs, built into your Neon branch and powered by Databricks.

    100 GitHub stars~5.1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check: notes
  • Codex CLI OmniRoute Config

    diegosouzapw/OmniRoute

    A step-by-step workflow for pointing the OpenAI Codex CLI at an OmniRoute gateway on Linux, macOS or Windows, plus settings that keep multi-hour sessions alive.

    74k GitHub stars~686 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from decolua/9router

All 9 skills in this repo
  • Sends chat and code-generation requests through a 9Router gateway using OpenAI or Anthropic message formats, with streaming and auto-fallback combos.

    30k GitHub stars~635 tokensUpdated 8 days ago
    Auto-check passed
  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    30k GitHub stars~604 tokensUpdated 8 days ago
    Auto-check passed
  • Generates images through a 9Router gateway's image endpoint, with model discovery, the request fields and per-provider quirks for OpenAI, Gemini, MiniMax and others.

    30k GitHub stars~830 tokensUpdated 8 days ago
    Auto-check passed
  • 9Router Speech-to-Text

    decolua/9router

    Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.

    30k GitHub stars~745 tokensUpdated 8 days ago
    Auto-check passed
  • 9Router Text to Speech

    decolua/9router

    Turns text into spoken audio through a 9Router server, choosing among voices from OpenAI, ElevenLabs, Deepgram, Edge TTS and other providers.

    30k GitHub stars~765 tokensUpdated 8 days ago
    Auto-check passed
  • Submits text-to-video or image-to-video jobs to xAI Grok Imagine through 9Router, then polls the job and downloads the finished MP4.

    30k GitHub stars~992 tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about 9Router AI Gateway Setup

What does 9Router AI Gateway Setup do?

Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills. 9Router is a local or remote AI gateway that offers one key and many providers with automatic fallback behind OpenAI-compatible REST. Setup is two environment variables, NINEROUTER_URL, which defaults to a local address on port 20128 or can be a server or tunnel URL, and NINEROUTER_KEY, taken from the dashboard and needed only when API keys are required.

When should I use 9Router AI Gateway Setup?

9Router AI Gateway Setup fits situations like: pointing an agent at a 9Router gateway for the first time; finding which models a 9Router instance offers for images or speech; calling chat, embeddings or web search through one OpenAI-compatible endpoint; debugging 401, 400 or 503 errors from the gateway.

How do I install 9Router AI Gateway Setup in Claude Code?

Run `npx skills add decolua/9router --skill 9router -a claude-code`. Or copy the skill folder (skills/9router in decolua/9router) into .claude/skills/9router in your project. Claude Code loads it when a task matches its description.

How do I install 9Router AI Gateway Setup in Codex?

Run `npx skills add decolua/9router --skill 9router -a codex`. Or copy the skill folder (skills/9router in decolua/9router) into .agents/skills/9router in your project. Codex loads it when a task matches its description.

Can I use 9Router AI Gateway Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add decolua/9router --skill 9router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/9router, .gemini/skills/9router, .github/skills/9router and .opencode/skills/9router in your project.

What does 9Router AI Gateway Setup need to run?

Going by SKILL.md and its folder, 9Router AI Gateway Setup needs the command-line tools its instructions call (curl) and credentials named NINEROUTER_KEY. Our summary lists: A running 9Router instance with its URL in NINEROUTER_URL; NINEROUTER_KEY, when the gateway requires an API key.

Does 9Router AI Gateway Setup access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is 9Router AI Gateway Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does 9Router AI Gateway Setup use?

9Router AI Gateway Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does 9Router AI Gateway Setup use?

About 744 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to 9Router AI Gateway Setup?

Skills that share tags, products or a category with 9Router AI Gateway Setup: Using Ccproxy Inspector (starbaser/ccproxy, 350 stars), Using Ccproxy API (starbaser/ccproxy, 350 stars), ClawRouter LLM Gateway (BlockRunAI/ClawRouter, 6.6k stars) and Caching Architecture (majiayu000/litellm-rs, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 9Router AI Gateway Setup?

decolua (a GitHub user) maintains it in decolua/9router, which has 30,435 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 1, 2026.

Source: decolua/9router on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.