What is or-research-models?

A research workflow for broadly exploring the AI models listed on OpenRouter, a service that provides access to models from different providers. It is for surveying a topic or category rather than selecting one specific model.

Use it to survey models by provider, ability such as vision or reasoning, price range, or recent additions. It can investigate questions such as which open-source vision models are available.

It helps when you want to understand what is available before making a choice. It separates open-ended research from direct recommendations or side-by-side comparisons.

or-research-models — Skill for Claude Code by danielrosehill

Install

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.

Any agent

npx skills add danielrosehill/Claude-Open-Router-Model-Research-Plugin --skill or-research-models

Clone the repo

git clone --depth 1 https://github.com/danielrosehill/Claude-Open-Router-Model-Research-Plugin

Made for: Claude Code.

Or install open-router-model-research, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models)

Your own site

<a href="https://agentmods.dev/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-open-router-model-research-plugin/or-research-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 745 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00086	$0.00745
Opus 5	$0.00043	$0.00373
Sonnet 5	$0.00017	$0.00149
Haiku 4.5	$0.00009	$0.00075

Measured 12d ago against content hash e62aeca1cd24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

or-research-models 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 12d ago.

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 -s https://openrouter.ai/api/v1/models -H "Accept: application/json"

skills/or-research-models/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open-Ended OpenRouter Model Research

Survey-style exploration of the OpenRouter catalog for a topic, family, or use case the user is curious about — broader and looser than a recommendation flow.

When to use

The user is exploring rather than choosing. Examples:

"What's the state of open-source vision models on OpenRouter right now?"
"Show me what DeepSeek has on OpenRouter"
"What new models showed up on OR this month?"
"I'm curious about cheap reasoning models on OpenRouter"

If the user wants a concrete pick, route to or-recommend-model. If they want to compare specific models, route to or-compare-models. Use this skill only for genuinely open-ended exploration.

Workflow

Step 1: Pin down the theme

The theme might be:

A provider / family (openai/, anthropic/, meta-llama/, deepseek/, qwen/)
A capability (reasoning, vision, audio, tool use, long context, multilingual)
A price tier (free, sub-$1/M, premium)
A recency cut (recently added — sort by created descending)

If the theme is fuzzy, ask one clarifying question to narrow it.

Step 2: Gather the slice

Fetch the catalog and filter to the relevant slice:

curl -s https://openrouter.ai/api/v1/models -H "Accept: application/json"

Apply the filter and sort meaningfully (by created date for recency, by price for budget themes, by context for long-context themes).

Step 3: Add light external context

Where useful, briefly contextualize the slice with external knowledge — what's the family known for, what's the recent narrative, what is the trade-off space. Keep this short (a few sentences). For deep dives on individual models, route to or-evaluate-model.

Step 4: Present

Use a structure suited to exploration, not just a flat table:

# <Theme> on OpenRouter

## Snapshot
- N models match this theme as of <fetch date>
- Price range: $... – $... per 1M tokens
- Context range: ... – ...

## Notable models

### <Model A>
- Why it stands out: ...
- Catalog facts: ...

### <Model B>
- ...

## What's missing / what to watch
- Gaps you noticed in the slice
- Models recently added or removed (if known)

## Suggested next steps
- "Want to compare A and B?" → or-compare-models
- "Want a recommendation for a specific task?" → or-recommend-model
- "Want to deep-dive on one of these?" → or-evaluate-model

Read the full file on GitHub · 83 lines

Changes

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.

12d ago First seen · 83 lines · 86 tokens per session scan A e62aeca1cd24

Subscribe to this mod's changes

or-research-models is a skill published in the GitHub repository danielrosehill/Claude-Open-Router-Model-Research-Plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 745 once invoked, about $0.0004 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 2026-08-31.

Data and AI Research

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

or-research-models