llm-providers-list 0.1.2

A unified source of truth for LLM providers, models, pricing, and capabilities.

LLM Providers

A unified source of truth for LLM providers, models, pricing, and capabilities.

Accessible via Rust and Python.

Installation   •   Usage   •   Supported Providers   •   Contributing

Philosophy

Managing LLM provider configurations across multiple projects and languages is a pain. LLM Providers solves this by maintaining a single, curated JSON source of truth for:

• Model IDs & Names
• Context Windows & Max Output Tokens
• Pricing (Input/Output)
• Capabilities (Tool Support, Vision, etc.)

This data is embedded at compile-time into a Rust crate for zero-latency access and exposed to Python via high-performance bindings.

Features

• 🚀 Zero-Latency: Data is compiled into the binary; no runtime I/O or API calls.
• 🦀 Rust Native: Type-safe structs (Provider, Model) for robust development.
• 🐍 Python Ready: Seamless integration via pip install llm-providers-list.
• 🔄 Unified Schema: Consistent data structure across all providers (OpenAI, Anthropic, DeepSeek, etc.).
• 📦 Rich Metadata: Includes pricing, context length, and tool support flags.

Installation

Install via pip:

pip install llm-providers-list

Usage

import llm_providers_list
import json

# List all supported providers
print(llm_providers_list.list_providers())
# Output: ['aliyun', 'anthropic', 'deepseek', 'openai', ...]

# Get provider object (Rich Type)
openai = llm_providers_list.get_provider("openai")
print(f"Label: {openai.label}")
print(f"Base URL: {openai.base_url}")

for model in openai.models:
    print(f"Model: {model.name}, Price: ${model.input_price}/1M tokens")

# Get raw JSON info
info = llm_providers_list.get_provider_info("anthropic")
print(info)

Supported Providers

• OpenAI (GPT-4o, GPT-3.5, o1)
• Anthropic (Claude 3.5 Sonnet, Haiku, Opus)
• DeepSeek (Chat, Reasoner)
• Aliyun (Qwen Max, Plus, Turbo)
• Tencent (Hunyuan)
• Moonshot (Kimi)
  • Moonshot AI (CN)
  • Moonshot AI Global
• MiniMax
  • MiniMax (CN)
  • MiniMax Global
• Zhipu (GLM-4)
  • BigModel (Zhipu CN)
  • Z.ai (Zhipu Global)
• Volcengine (Doubao)
• LongCat

Contributing

Contributions are welcome! To add a new provider or update existing models:

1. Edit providers.json in the root directory.
2. Run tests to ensure validity:

   cargo test
   

3. Submit a Pull Request.

License

MIT