Home › Directory › LLM APIs › TensorRT-LLM
TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA.
| Category | LLM APIs |
|---|---|
| Authentication | No auth |
| Pricing | Free |
| Website | https://github.com/NVIDIA/TensorRT-LLM |
| Docs | https://github.com/NVIDIA/TensorRT-LLM/tree/main/docs |
| Last checked | 2026-10-14 |
| As JSON | /api/v1/directory/tensorrt-llm.json |
Information is summarised in our own words and may be out of date; check the vendor's site for current terms and prices. Not affiliated with TensorRT-LLM. Suggest a correction.
More in LLM APIs
OpenAI API
Hosted GPT-family language, image, speech and embedding models behind a single REST API, with function calling and structured outputs.
Anthropic API
Access to the Claude model family over REST, with tool use, long context windows and prompt caching.
Google Gemini API
Google's multimodal Gemini models via API key, with a free tier for prototyping and support for large context inputs.
Groq
Very fast inference for open-weight models on custom hardware, exposed through an OpenAI-compatible endpoint.