llm-models: keeping up with LLM frontier model versions

#cli #python #llm #tooling

The Problem

With the flurry of new LLMs published almost daily, it may be confusing for developers to keep track of which exact models are available through various API services at any given time. When gemini 3 was released, I could not find the correct model name for a while (turned out to be "gemini-3-pro-preview")

The Solution

I built (with Claude Code help) a simple CLI app to list available models for the major providers.

Usage


$ llm_models -h
usage: llm_models [-h] -p {OpenAI,Anthropic,xAI,GoogleAI,VertexAI} [-r REGION]

List available LLM models from various providers

options:
  -h, --help            show this help message and exit
  -p {OpenAI,Anthropic,xAI,GoogleAI,VertexAI}, --provider {OpenAI,Anthropic,xAI,GoogleAI,VertexAI}
                        The LLM provider backend.
                        - 'GoogleAI': Google AI Studio (API Key). Global/Auto-routed.
                        - 'VertexAI': Google Cloud Vertex AI (IAM Auth). Region-specific.
  -r REGION, --region REGION
                        Google Cloud region (e.g., 'us-central1').
                        *Required* if provider is VertexAI. Ignored for other providers.

$ llm_models -p Anthropic
Listing available Anthropic models...
================================================================================
Model: claude-haiku-4-5-20251001 (Claude Haiku 4.5)
Model: claude-sonnet-4-5-20250929 (Claude Sonnet 4.5)
Model: claude-opus-4-1-20250805 (Claude Opus 4.1)
Model: claude-opus-4-20250514 (Claude Opus 4)
Model: claude-sonnet-4-20250514 (Claude Sonnet 4)
Model: claude-3-7-sonnet-20250219 (Claude Sonnet 3.7)
Model: claude-3-5-haiku-20241022 (Claude Haiku 3.5)
Model: claude-3-haiku-20240307 (Claude Haiku 3)
Model: claude-3-opus-20240229 (Claude Opus 3)