OpenRouter Models

Discover, search, and compare the 300+ AI models available on OpenRouter. Query live data including pricing, context lengths, per-provider latency and uptime, throughput, supported modalities, and supported parameters.

Prerequisites

The OPENROUTER_API_KEY environment variable is optional for most scripts. It is only required for get-endpoints.ts (provider performance data). Get a key at https://openrouter.ai/keys

First-Time Setup

cd <skill-path>/scripts && npm install

Decision Tree

Pick the right script based on what the user is asking:

Resolve Model

Resolve an informal or vague model name to an exact OpenRouter model ID using fuzzy matching:

cd <skill-path>/scripts && npx tsx resolve-model.ts "claude sonnet"
cd <skill-path>/scripts && npx tsx resolve-model.ts "gpt 4o mini"
cd <skill-path>/scripts && npx tsx resolve-model.ts "llama 3.1"

Results include a confidence level and score:

Two-step workflow: First resolve the informal name with resolve-model.ts, then feed the resolved id into other scripts (compare-models.ts, get-endpoints.ts, etc.).

List Models

cd <skill-path>/scripts && npx tsx list-models.ts

Filter by Category

Server-side category filtering:

cd <skill-path>/scripts && npx tsx list-models.ts --category programming

Categories: programming, roleplay, marketing, marketing/seo, technology, science, translation, legal, finance, health, trivia, academia

Sort Results

cd <skill-path>/scripts && npx tsx list-models.ts --sort newest      # Recently added first
cd <skill-path>/scripts && npx tsx list-models.ts --sort price       # Cheapest first
cd <skill-path>/scripts && npx tsx list-models.ts --sort context     # Largest context first
cd <skill-path>/scripts && npx tsx list-models.ts --sort throughput  # Most output tokens first

Models with upcoming expiration_date values trigger a stderr warning.

Search Models

cd <skill-path>/scripts && npx tsx search-models.ts "claude"
cd <skill-path>/scripts && npx tsx search-models.ts --modality image
cd <skill-path>/scripts && npx tsx search-models.ts "gpt" --modality text

Modalities: text, image, audio, file

Compare Models

Compare two or more models side-by-side with pricing in per-million-tokens format. Uses exact ID matching — openai/gpt-4o matches only that model, not variants like gpt-4o-mini.

cd <skill-path>/scripts && npx tsx compare-models.ts "anthropic/claude-sonnet-4" "openai/gpt-4o"
cd <skill-path>/scripts && npx tsx compare-models.ts "anthropic/claude-sonnet-4" "openai/gpt-4o" "google/gemini-2.5-pro" --sort price

Sort options: price (cheapest first), context (largest first), speed/throughput (most output tokens first)

Provider Performance (Endpoints)

Get per-provider latency, uptime, and throughput for any model:

cd <skill-path>/scripts && npx tsx get-endpoints.ts "anthropic/claude-sonnet-4"
cd <skill-path>/scripts && npx tsx get-endpoints.ts "anthropic/claude-sonnet-4" --sort throughput
cd <skill-path>/scripts && npx tsx get-endpoints.ts "openai/gpt-4o" --sort latency

Sort options: throughput (fastest tokens/sec first), latency (lowest p50 ms first), uptime (most reliable first), price (cheapest first)

Returns for each provider:

• Latency (p50/p75/p90/p99 in ms) — median to worst-case response times
• Throughput (p50/p75/p90/p99 tokens/sec) — generation speed
• Uptime — percentage over the last 30 minutes
• Status — operational or degraded
• Provider-specific pricing — some providers offer discounts
• Supported parameters — varies by provider (some don't support all features)

Output Formats

list-models.ts / search-models.ts

{
  "id": "anthropic/claude-sonnet-4",
  "name": "Anthropic: Claude Sonnet 4",
  "description": "...",
  "created": 1747930371,
  "context_length": 1000000,
  "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "input_cache_read": "0.0000003"
  },
  "architecture": {
    "tokenizer": "Claude",
    "modality": "text+image->text",
    "input_modalities": ["text", "image"],
    "output_modalities": ["text"]
  },
  "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 64000,
    "is_moderated": false
  },
  "per_request_limits": null,
  "supported_parameters": ["max_tokens", "temperature", "tools", "reasoning", "..."]
}

compare-models.ts

{
  "id": "anthropic/claude-sonnet-4",
  "name": "Anthropic: Claude Sonnet 4",
  "context_length": 1000000,
  "max_completion_tokens": 64000,
  "per_request_limits": null,
  "pricing_per_million_tokens": {
    "prompt": "$3.00",
    "completion": "$15.00",
    "cached_input": "$0.30"
  },
  "modalities": { "input": ["text", "image"], "output": ["text"] },
  "supported_parameters": ["max_tokens", "temperature", "..."],
  "is_moderated": false
}

get-endpoints.ts

{
  "model_id": "anthropic/claude-sonnet-4",
  "model_name": "Anthropic: Claude Sonnet 4",
  "total_providers": 5,
  "endpoints": [
    {
      "provider": "Anthropic",
      "tag": "anthropic",
      "status": "operational",
      "uptime_30m": "100.00%",
      "latency_30m_ms": { "p50": 800, "p75": 1200, "p90": 2000, "p99": 5000 },
      "throughput_30m_tokens_per_sec": { "p50": 45, "p75": 55, "p90": 65, "p99": 90 },
      "context_length": 1000000,
      "max_completion_tokens": 64000,
      "pricing_per_million_tokens": { "prompt": "$3.00", "completion": "$15.00", "cached_input": "$0.30" },
      "supports_implicit_caching": true,
      "supported_parameters": ["max_tokens", "temperature", "tools", "..."]
    }
  ]
}

Key Fields

Presenting Results

• When a user mentions a model by informal name, use resolve-model.ts first, then feed the resolved id into other scripts
• Convert pricing to per-million-tokens format for readability
• When comparing, use a markdown table with models as columns
• For provider endpoints, highlight the fastest (lowest p50 latency) and most reliable (highest uptime) providers
• Call out notable supported parameters: tools, structured_outputs, reasoning, web_search_options
• Note cache pricing when available — it can cut input costs 90%+
• Flag models with expiration_date as deprecated
• When a model has multiple providers at different prices, mention the cheapest option