Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nirholas/three.ws/openrouter-ai-models-guidenpx skills add nirholas/three.ws --skill openrouter-ai-models-guidegit clone --depth 1 https://github.com/nirholas/three.wsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nirholas/three.ws/openrouter-ai-models-guide)<a href="https://agentmods.dev/skills/nirholas/three.ws/openrouter-ai-models-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/openrouter-ai-models-guide.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.01353 |
| Opus 5 | $0.00032 | $0.00677 |
| Sonnet 5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
openrouter-ai-models-guide scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://openrouter.ai/api/v1/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenRouter AI Models Guide
OpenRouter provides a unified API for 200+ AI models. This guide covers model selection, pricing, routing, and integration with SperaxOS.
What Is OpenRouter?
A single API endpoint that routes requests to 200+ models:
Your App → OpenRouter API → Model Provider
├── OpenAI (GPT-4, o1, o3)
├── Anthropic (Claude 4, Sonnet, Haiku)
├── Google (Gemini 2.5, Pro, Flash)
├── Meta (Llama 4, Maverick)
├── Mistral (Large, Medium)
├── DeepSeek (V3, R1)
└── 50+ more providers
Quick Start
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4-20250514",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Model Selection Guide
By Task
| Task | Recommended Model | Why |
|---|---|---|
| Complex reasoning | claude-sonnet-4, o3 | Best logical reasoning |
| Coding | claude-sonnet-4, deepseek-v3 | Best code generation |
| Creative writing | claude-sonnet-4, gpt-4o | Most creative output |
| Fast responses | gemini-flash, claude-haiku | Lowest latency |
| Long context | gemini-pro-2.5 (1M), claude-sonnet-4 (200K) | Largest context windows |
| DeFi analysis | claude-sonnet-4, gpt-4o | Best structured data handling |
| Vision/images | gpt-4o, gemini-pro | Best image understanding |
| JSON output | claude-sonnet-4, gpt-4o | Most reliable structured output |
| Budget | deepseek-v3, llama-4 | Cheapest per token |
By Price (per 1M tokens)
| Tier | Input | Output | Models |
|---|---|---|---|
| Free | $0 | $0 | Selected models with limits |
| Budget | $0.10-0.50 | $0.30-1.50 | DeepSeek, Llama, Gemma |
| Standard | $1-5 | $3-15 | GPT-4o, Claude Sonnet, Gemini Pro |
| Premium | $10-15 | $30-60 | o3, Claude Opus |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 161 lines · 64 tokens per session scan A c5a9c3605c74
openrouter-ai-models-guide is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,353 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
llm-router
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which…
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
system2-attention
System 2 attention mechanisms for deliberate, slow reasoning in transformer architectures.
security-copilot
Guidance for Microsoft Security Copilot - the generative-AI security platform that helps analysts investigate, hunt, summarise, and respond using natural language, plugins, promptbooks, and embedded experiences. Covers SCU provisioning, plugins, promptbooks, governance, and the standalone vs embedded experience…