A curated directory of LLM APIs that offer permanent free tiers for text inference, documenting rate limits, context windows, modalities, and links to API key pages. It is an informational resource for developers seeking external model endpoints without trial credits.
Project overview
It focuses exclusively on permanent free tiers for LLM text inference and catalogs the technical specifications of each provider, including rate limits, context windows, and supported modalities.
Project type
Model Runtime
Deployment
Refer to project documentation
License
CC0-1.0
Best for
Developers looking for external LLM API providers that offer permanent free tiers for text inference.
Key capabilities
Provides a categorized directory of companies and platforms offering permanent free tiers for LLM text inference.
Documents technical specifications for each listed API, including base URL, rate limits, context windows, and max output.
Lists specific models available under each provider's free tier along with their supported modalities.
Limitations and risks
Inference relies on various external LLM API providers, requiring external network calls and depending on third-party services.
The list specifically excludes APIs that only offer trial credits or time-limited promotions.
Getting started
Open the README.md file to read the curated list of free LLM APIs, as no setup is required to consume the information.
Alternatives and comparisons
Provides a way to run and manage large language models locally via CLI or REST API, suitable for users who need local execution rather than external APIs.
Enables LLM inference with minimal setup via a C/C++ implementation, supporting local execution and various hardware accelerations.
An inference and serving engine for LLMs that provides high throughput and memory efficiency for users hosting their own model endpoints.