models-dev
Typed Python interface to models.dev API data
Decision gist · record as of 2026-08-14
Yes, if you need offline access to LLM model metadata. The package is lightweight, actively maintained, has no dependencies, and covers a broad catalog (2000+ models from 75+ providers). Install it when you want to avoid HTTP calls for model lookups or need typed access to pricing and capability data. Not necessary if you only work with one provider's SDK or rarely need to query model details.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Low friction: zero runtime dependencies, ~75 KB installed, and actively maintained with hourly update checks.
- Latest release 85 days old; repository shows recent activity.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for most projects.
last release 2026-05-21 (85 days) · last repo commit 2026-08-14 · 4 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 142,328 downloads/mo, #11,212 on PyPI
Alternatives
Verify before relying
pip install models-dev
from models_dev import providers, get_provider, get_model
openai = get_provider("openai")
gpt4o = get_model("openai", "gpt-4o")
print(gpt4o.cost.input, gpt4o.limit.context)- How frequently the package actually publishes updates when models.dev changes (claimed hourly check, but release cadence unknown).
- Whether the 2000+ model count and 75+ provider figure remain current or are static snapshots in the package.
What it is and what it does
models-dev is a typed Python package that bundles the models.dev catalog—a community-maintained registry of LLM models—as local data. Instead of making HTTP calls to fetch model metadata, you import and query structured Python objects for provider information, pricing, context limits, modalities, and capabilities. The package is designed to stay in sync with the upstream catalog through hourly update checks and frequent releases.
It has zero runtime dependencies and ships as a ~75 KB wheel, making it lightweight and easy to integrate into projects that need to reference LLM model details at runtime—such as prompt engineering frameworks, cost calculators, or model-selection logic. The data is pre-typed, so IDEs and type checkers can validate queries.
Use it for
- Look up pricing and context limits for a specific LLM model before making an API call.
- Filter available models by capability (e.g., find all reasoning-enabled models across providers).
- Build a model-selection tool that compares input/output costs or modality support.
- Populate a UI dropdown or CLI menu with current provider and model names without external API calls.
- Validate model names and provider identities in a local configuration file or request handler.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need offline access to LLM model metadata.
The package is lightweight, actively maintained, has no dependencies, and covers a broad catalog (2000+ models from 75+ providers). Install it when you want to avoid HTTP calls for model lookups or need typed access to pricing and capability data. Not necessary if you only work with one provider's SDK or rarely need to query model details.
Install
models-dev on PyPI
Before you install
Low friction: zero runtime dependencies, ~75 KB installed, and actively maintained with hourly update checks. Latest release 85 days old; repository shows recent activity.
Requires Python 3.10 or later.
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for most projects.
Quickstart
pip install models-dev
from models_dev import providers, get_provider, get_model
openai = get_provider("openai")
gpt4o = get_model("openai", "gpt-4o")
print(gpt4o.cost.input, gpt4o.limit.context)Verify before relying
- How frequently the package actually publishes updates when models.dev changes (claimed hourly check, but release cadence unknown).
- Whether the 2000+ model count and 75+ provider figure remain current or are static snapshots in the package.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 85 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 142,328 / month, #11,212 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Typing :: Typed |
Evidence: models_dev-1.0.398-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm model catalog lookup”
- models-devProvides a typed Python interface to models.dev, a…
- unitxtUnitxt provides a unified framework for evaluating AI model…
- genai-pricesCalculates pricing for LLM API calls across multiple providers by…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also litellm-enterprise · unclecode-litellm · llm-openai-plugin · llama-index-llms-openai-like · llm · fhlmi · any-llm-sdk · code-puppy · llm-anthropic