skills.rest
zester4
zester4COMMUNITY
Explore all skills by this author →
GitHub

openrouter-models

Query OpenRouter for AI model pricing, capabilities, and provider performance data.

2|1|Updated Jun 9, 2026
Search Tags:#typescript#pricing#api#llm#model comparison#latency#openrouter
One-click install
npx skills add https://github.com/zester4/zilmate --skill openrouter-models-zester4
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openrouter-models
Source: https://github.com/zester4/zilmate/tree/main/.agents/skills/openrouter-models
Command: npx skills add https://github.com/zester4/zilmate --skill openrouter-models-zester4

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tsx, and includes scripts (resource) components.

What problem does it solve? Choosing the right AI model and provider requires comparing live pricing, context lengths, latency, and uptime across hundreds of options, which is tedious to research manually. ## Core Features & Use Cases - Model Discovery & Search: List, filter by category, sort by price or throughput, and search 300+ OpenRouter models by name or modality. - Model Comparison & Resolution: Compare models side-by-side on pricing and context, and resolve informal names like "claude sonnet" to exact model IDs via fuzzy matching. - Provider Performance Analysis: Inspect per-provider latency percentiles, uptime, throughput, and pricing for any model. - Use Case: Before routing production traffic, ask which provider is fastest for Claude Sonnet and get p50 latency, uptime, and per-million-token pricing for each endpoint. ## Quick Start Ask the assistant to compare the pricing and context length of Claude Sonnet 4 and GPT-4o on OpenRouter.

Frequently Asked Questions about openrouter-models

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compare AI model pricing on OpenRouter?▼

Run compare-models.ts with two or more model IDs to get side-by-side pricing in per-million-token format, context lengths, and supported parameters. Add --sort price to order results from cheapest to most expensive.

How do I find the fastest provider for an OpenRouter model?▼

Run get-endpoints.ts with the model ID and --sort throughput to rank providers by p50 tokens per second. The output also includes latency percentiles, uptime over the last 30 minutes, and provider-specific pricing.

Do I need an OpenRouter API key to list models?▼

No, the OPENROUTER_API_KEY is optional for listing, searching, resolving, and comparing models. It is only required for get-endpoints.ts, which fetches per-provider performance data.

How do I resolve an informal model name to an OpenRouter model ID?▼

Run resolve-model.ts with a query like "claude sonnet" or "gpt 4o mini". It uses fuzzy matching and returns up to five candidates with confidence scores; high-confidence matches can be used directly in other scripts.

Can I filter OpenRouter models by category or modality?▼

Yes, list-models.ts supports --category for server-side filtering by categories like programming or finance, and search-models.ts supports --modality to filter by text, image, audio, or file input and output modalities.

Related Skills

Explore More Software Engineering Skills→
SynthFlowAISynthFlowAI

setup-api-key

Configure a Synthflow API key in .env and validate it with curl.

Official
Intermediate
nimadorostkarnimadorostkar
25

model-selection

Determine cost-effective LLM configurations and routing strategies for production tasks.

Community
Advanced
patricio0312revpatricio0312rev
5

cost-latency-optimizer

Optimize LLM applications for cost and latency via caching, model selection, batching, and prompt optimization.

Community
Advanced
HouseGarofaloHouseGarofalo
3

litellm

Call over 100 LLM providers through a unified interface.

Official
Intermediate