API DIRECTORY · AI MODELS AND INFERENCE

AI — Local / Self-Hosted Model Runners (Downloadable)

29 companies and tools in this category. Each listing links to the provider’s own website. Search the full directory

01.AI YiSelf-hosted
Official Yi language-model release and usage documentation from 01.AI.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
Ai2 OLMoSelf-hosted
Open language-model training and inference code from Ai2, with model-release and hosting examples.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
BentoMLSelf-hosted
Package models as APIs
Open documentation Pricing — No pricing page listedStatus Details
Official source checked · checked 2026-10-23Install and run this software to expose its API.
GPT4AllSelf-hosted
Desktop app with local API
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
Hugging Face TGISelf-hosted
Text Generation Inference server
Open documentation Pricing — No pricing page listedStatus Details
Official source checked · checked 2026-10-23Install and run this software to expose its API.
InclusionAI LingSelf-hosted
Official Ling mixture-of-experts language-model code and release documentation.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
JanSelf-hosted
Desktop app with local API server
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
KoboldCppSelf-hosted
Single-file runner with API
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
KServeSelf-hosted
Kubernetes model serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
LG EXAONESelf-hosted
Official LG AI Research model-release repository for EXAONE language models.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
llama.cppSelf-hosted
C++ inference with HTTP server
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
LlamafileSelf-hosted
Single-executable models with API
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
LM StudioSelf-hosted
Desktop app with local OpenAI-compatible server
Set up API access Docs Pricing Status — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
LocalAISelf-hosted
Drop-in OpenAI replacement: text, image, audio
Set up API access Docs Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
Microsoft PhiSelf-hosted
Microsoft language-model cookbook with local and hosted deployment examples.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
MLXSDK/library
Apple Silicon inference
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Programming library or SDK; no hosted API key is implied.
mlx-lmSelf-hosted
Apple Silicon inference
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
NVIDIA DynamoSelf-hosted
Distributed inference serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
NVIDIA NemotronSelf-hosted
NVIDIA model-development assets, training recipes and inference examples for Nemotron models.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.
OllamaSelf-hosted
Cloud and local language-model APIs
Open documentation Pricing Status — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
Ray ServeSelf-hosted
Scalable model serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
SGLangSelf-hosted
Fast structured serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
TabbyAPISelf-hosted
Fast GPU quantized serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
TensorRT-LLMSelf-hosted
NVIDIA serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
textgen (text-generation-webui)Self-hosted
Web UI with OpenAI-style API
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
Triton Inference ServerSelf-hosted
NVIDIA serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
vLLMSelf-hosted
High-throughput OpenAI-compatible serving
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
XinferenceSelf-hosted
Serve LLMs, embeddings, rerankers
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official source checked · checked 2026-10-23Install and run this software to expose its API.
Yandex YaLMSelf-hosted
Official YaLM-100B model release and inference documentation; a historical model project.
Open documentation Pricing — No pricing page listedStatus — No status page listedDetails
Official model-project source checked · checked 2026-11-08Model weights/code and developer documentation. Direct hosted API availability, API-key setup and token pricing were not verified; use a supported host or a compatible local deployment as documented.