Openrouter Model Catalog

What it does

When your agent uses it

• Choosing models
• Comparing pricing
• Checking capabilities

Example prompts

• “openrouter models”
• “list models”
• “model catalog”
• “/openrouter-model-catalog”

Requirements

• Python 3
• A credential in OPENROUTER_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Bash(python3:*), Bash(curl:*), Bash(jq:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1List the catalog per List All Models: curl -s https://openrouter.ai/api/v1/models | jq '.data | length'; add ?supported_parameters=tools…
2. 2Read Model Object Shape to interpret each entry — pricing.prompt/pricing.completion are per token (multiply by 1M for readable rates)…
3. 3Filter programmatically per Python: Query and Filter — free models, tool-calling models, cheapest paid models sorted by prompt price, and…
4. 4Compare per-provider pricing and quantization for a single model via GET /api/v1/models/{id}/endpoints per List Providers for a Model.
5. 5Pick behavior with a suffix per Model Variants (:free, :nitro, :floor, :extended, :thinking), or delegate selection entirely to…
6. 6Sanity-check choices against the Popular Model Quick Reference, but always verify live pricing via /api/v1/models — prices change…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Grep
  • Bash(python3:*)
  • Bash(curl:*)
  • Bash(jq:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • jq
  • pip

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • openrouter.ai

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

• Credentials

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

  • OPENROUTER_API_KEY

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

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Openrouter Model Catalog loads about 2.2k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 597 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~65

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.1k

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

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 597 words, ~2,191 tokens.

name

openrouter-model-catalog

description

Query, filter, and select from OpenRouter's 400+ model catalog. Use when choosing models, comparing pricing, or checking capabilities. Triggers: 'openrouter models', 'list models', 'model catalog', 'compare models', 'available models'.

allowed-tools

Read, Write, Edit, Grep, Bash(python3:*), Bash(curl:*), Bash(jq:*)

compatibility

Designed for Claude Code

version

1.20.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, openrouter, models, catalog

# Full catalog (no auth required)
curl -s https://openrouter.ai/api/v1/models | jq '.data | length'
# → 400+

# Filter to text output models only
curl -s "https://openrouter.ai/api/v1/models?supported_parameters=tools" | jq '.data | length'

{
  "id": "anthropic/claude-3.5-sonnet",
  "name": "Claude 3.5 Sonnet",
  "description": "Anthropic's most intelligent model...",
  "context_length": 200000,
  "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "image": "0.0048",
    "request": "0"
  },
  "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 8192,
    "is_moderated": false
  },
  "per_request_limits": null,
  "architecture": {
    "modality": "text+image->text",
    "tokenizer": "Claude",
    "instruct_type": null
  }
}

import requests

models = requests.get("https://openrouter.ai/api/v1/models").json()["data"]

# Find all free models
free_models = [m for m in models if m["pricing"]["prompt"] == "0"]
print(f"Free models: {len(free_models)}")

# Models with tool calling support
# (query with supported_parameters)
tool_models = requests.get(
    "https://openrouter.ai/api/v1/models?supported_parameters=tools"
).json()["data"]
print(f"Tool-calling models: {len(tool_models)}")

# Sort by prompt price (cheapest first, excluding free)
paid = [m for m in models if float(m["pricing"]["prompt"]) > 0]
paid.sort(key=lambda m: float(m["pricing"]["prompt"]))
for m in paid[:10]:
    cost_per_m = float(m["pricing"]["prompt"]) * 1_000_000
    print(f"  ${cost_per_m:.2f}/M tokens — {m['id']} ({m['context_length']//1000}K ctx)")

# Filter by context length (128K+)
large_ctx = [m for m in models if m["context_length"] >= 128_000]
print(f"128K+ context models: {len(large_ctx)}")

# See all providers and their pricing for a specific model
curl -s "https://openrouter.ai/api/v1/models/anthropic/claude-3.5-sonnet/endpoints" | jq '.data[] | {
  provider: .provider_name,
  price_prompt: .pricing.prompt,
  price_completion: .pricing.completion,
  context_length: .context_length,
  quantization: .quantization
}'

# Let OpenRouter pick the best model
response = client.chat.completions.create(
    model="openrouter/auto",
    messages=[{"role": "user", "content": "Write a SQL query to find duplicate emails"}],
    max_tokens=200,
)
print(f"Auto-selected: {response.model}")  # Shows which model was chosen

models = requests.get("https://openrouter.ai/api/v1/models").json()["data"]
free = [m for m in models if m["pricing"]["prompt"] == "0"]
large = [m for m in models if m["context_length"] >= 128_000]
print(f"Total: {len(models)}, free: {len(free)}, 128K+: {len(large)}")
# Total: 267, free: 12, 128K+: 45   (counts drift as the catalog changes)

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

Files

SKILL.md and 5 other files (references) in skills/.curated/openrouter-model-catalog of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/errors.md
• references/examples.md
• references/model-categories.md
• references/model-information-api.md
• references/model-selection-criteria.md

Open the folder on GitHubat commit cfae287